Comparative Legilinguistics

vol. 37/2019
DOI: http://dx.doi.org/10.14746/cl.2019.37.4

MACHINE TRANSLATION IN THE FIELD

OF LAW: A STUDY OF THE TRANSLATION
OF ITALIAN LEGAL TEXTS INTO GERMAN

EVA WIESMANN, Prof., PhD

Department of Interpreting and Translation,

University of Bologna
Corso della Repubblica 136, 47121 Forlì, Italy
[email protected]

ORCID: https://orcid.org/0000-0001-9414-8038

Abstract: With the advent of the neural paradigm, machine translation

has made another leap in quality. As a result, its use by trainee translators
has increased considerably, which cannot be disregarded in translation
pedagogy. However, since legal texts have features that pose major
challenges to machine translation, the question arises as to what extent
machine translation is now capable of translating legal texts or at least certain
types of legal text into another legal language well enough so that the post-
editing effort is limited, and, consequently, whether a targeted use
in translation pedagogy can be considered. In order to answer this question,
DeepL Translator, a machine translation system, and MateCat, a CAT system
that integrates machine translation, were tested. The test, undertaken
at different times and without specific translation memories, provided
 Eva Wiesmann: Machine Translation in…

for the translation of several legal texts of different types utilising both
systems, and was followed by systematisation of errors and evaluation
of translation results. The evaluation was carried out according
to the following criteria: 1) comprehensibility and meaningfulness
of the target text; and 2) correspondence between source and target text
in consideration of the specific translation situation. Overall, the results
are considered insufficient to give post-editing of machine-translated legal
texts a bigger place in translation pedagogy. As the evaluation
of the correspondence between source and target text was fundamentally
worse than with regard to the meaningfulness of the target text, translation
pedagogy should respond by raising awareness about differences between
machine translation output and human translation in this field,
and by improving translation approach and strengthening legal expertise.

Key words: neural machine translation; legal translation; translation

pedagogy.

MASCHINELLE ÜBERSETZUNG VON RECHTSTEXTEN:

EINE STUDIE ZUR ÜBERSETZUNG AUS DEM ITALIENISCHEN
INS DEUTSCHE

Abstract in German: Mit der Ablösung der statistischen durch die neuronale
Übersetzung hat die maschinelle Übersetzung einen weiteren Qualitätssprung
gemacht. Dadurch ist auch ihre Nutzung durch Übersetzerinnen
und Übersetzer in der Ausbildung stark gestiegen, was bei der Ausrichtung
der Didaktik und der Bewertung der studentischen Leistungen nicht
unberücksichtigt bleiben kann. Da nun aber Rechtstexte Merkmale haben, die
die maschinelle Übersetzung vor größere Herausforderungen stellen, fragt
sich, inwieweit die maschinelle Übersetzung heute schon in der Lage ist,
auch Rechtstexte oder zumindest bestimmte Textsorten oder Teile von
Textsorten so gut in eine andere Rechtssprache zu übertragen, dass sich
der Aufwand an Post-Editing in Grenzen hält, und ob folglich ein gezielter
Einsatz in der Didaktik in Erwägung gezogen werden kann.
Auf dem Prüfstand stehen zwei kostenlos online zur Verfügung stehende
Systeme, DeepL Translator und MateCat. Während DeepL Translator
ein reines mit Linguee trainiertes System der neuronalen maschinellen
Übersetzung ist, handelt es sich bei MateCat um ein CAT-System
mit Integration der zunächst statistischen und heute neuronalen maschinellen
Übersetzung, das einerseits eine Nutzung eigener Ressourcen oder
von MyMemory und andererseits eine Auswahl unter verschiedenen
Systemen der maschinellen Übersetzung oder eine Nutzung einer
Kombination von Systemen der maschinellen Übersetzung erlaubt.
Das Versuchsdesign sieht die mehrfach in verschiedenen Zeitabständen

118
 Comparative Legilinguistics 37/2019

erfolgende italienisch-deutsche Übersetzung von Texten verschiedener

Textsorten der Rechtsetzung (Gesetze), Rechtspraxis (notarielle
Immobilienkaufverträge, Klageschriften, Gerichtsurteile, Vollmachten)
und Rechtslehre (rechtswissenschaftliche Aufsätze) mit beiden Systemen
und die anschließende Systematisierung der Fehler und die Bewertung
der Übersetzungsergebnisse vor. Bei der Auswahl der Texte wurde nicht
nur auf die Provenienz aus den verschiedenen rechtlichen
Handlungsbereichen geachtet, sondern auch auf den unterschiedlichen,
mit DyLan TextTools ermittelten Schwierigkeitsgrad. Die Bewertung erfolgt
nach dem rein den Zieltext betreffenden Kriterium Verständlichkeit bzw.
Sinnhaftigkeit und dem die Relation zwischen Ausgangstext und Zieltext
betreffenden Kriterium Entsprechung unter Berücksichtigung
der Übersetzungssituation. Insgesamt ist das Ergebnis noch zu schlecht,
um dem Post-Editing von maschinell übersetzten Rechtstexten
in der Didaktik einen größeren Platz einzuräumen. Beim
rechtswissenschaftlichen Aufsatz, beim Gesetz und beim Tatbestand
der Klageschrift wurden aber vergleichsweise gute Ergebnisse erzielt.
Die Bewertung fiel bei der Relation zwischen Ausgangstext und Zieltext
grundsätzlich schlechter als in Bezug auf die Verständlichkeit bzw.
Sinnhaftigkeit des Zieltextes aus. Darauf muss die Didaktik mit einer
Verbesserung des übersetzerischen Vorgehens und einer Stärkung
der Fachkompetenz antworten. Außerdem muss sie das Bewusstsein
für die Unterschiede zwischen Human- und maschineller Übersetzung
schärfen.

Schlüsselwörter: Neuronale maschinelle Übersetzung; Rechtsübersetzung;

Übersetzungsdidaktik.

PRZEKŁAD MASZYNOWY W OBSZARZE PRAWA: STUDIUM

PRZEKŁADU TEKSTÓW PRAWNYCH Z JĘZYKA WŁOSKIEGO
NA NIEMIECKI

Abstrakt: W związku z poprawą jakości tłumaczenia maszynowego jest ono

wykorzystywane przez adeptów sztuki przekładoznawczej w coraz
to większym stopniu. Teksty prawne stanowią jednak spore wyzwanie
dla przekładu maszynowego, prowadząc do rozważań nad możliwością
wykorzystywania tłumaczenia maszynowego właśnie do pracy nad takimi
tekstami jak i nad potencjalnym zastosowaniem w nauczaniu przekładu.
W celu analizy tego zagadnienia, podjęto pracę nad systemem tłumaczenia
maszynowego DeepL Translator oraz systemem CAT integrującym
tłumaczenie maszynowe – MateCat. Badania z wykorzystaniem
obu systemów przeprowadzane były w różnym czasie, bez określonych
pamięci tłumaczeniowych dla danych tekstów prawnych, dając zarazem

119
 Eva Wiesmann: Machine Translation in…

podstawy dla oceny wyników i uszeregowania rodzajów błędów. Ocena

opierała się na określonych kryteriach: 1) zrozumienie i znaczenie tekstu
docelowego; 2) relacja między tekstami wyjściowym a wejściowym
w określonych sytuacjach tłumaczeniowych. Wyniki okazały
się być niewystarczające do uznania za przydatne w postedycji tekstów
prawnych w znacznym stopniu dla nauczania przekładu. Ocena relacji tekst
wejściowy-wyjściowy była znacznie niższa niż ta dotycząca znaczenia tekstu,
stąd postuluje się, że nauczanie przekładu powinno prowadzić
do zwiększenia świadomości, że między rezultatem przekładem
maszynowym a tłumaczeniem ludzkim występują różnice oraz usprawnień
w obszarze kompetencji prawnych i prawniczych jak i w podejściu
translatorskim.

Słowa klucze: neuronowe tłumaczenie maszynowe (NMT); tłumaczenie

prawne; nauczanie przekładu.

Research question and objective

Since neural machine translation systems are freely available

on the Internet, they are increasingly being used by trainee translators
too. In my course in Translation from Italian into German, which
is a first-year course in the BA degree program in Intercultural
and Linguistic Mediation at the University of Bologna, 45.5%
of the students stated at the beginning of the course in 2016/2017 that
they knew something of machine translation systems. This knowledge
entails, for the most part, DeepL Translator or Google Translate.
In 2017/2018 and 2018/2019, machine translation systems were used
in the MA degree program in Specialized Translation at the University
of Bologna, inter alia, in the course in Specialized Translation from
German into Italian. In this course, students have been involved
in the post-editing of several kinds of machine-translated specialized
(mostly non-legal) texts. Whether or not one wishes to use machine
translation systems in teaching, the topic of machine translation
will have to play a role in translation pedagogy because students
increasingly use machine translation systems to complete their
translations. In this regard, the following can be postulated:
(i) The use of machine translation systems must not be uncritical,
so a general idea of how such systems work and a requisite

120
 Comparative Legilinguistics 37/2019

understanding of how to deal with them is essential

for students. This is especially true where these systems
deliver such good results that the post-editing effort is limited.
(ii) The use of machine translation systems requires the re-
evaluation of the impact of the different translation skills.
In particular, specialized expertise should play a greater role.
(iii) When evaluating student achievement, the use of machine
translation systems cannot be disregarded, especially
in the case of translation from mother tongue into a foreign
language.
Legal texts have always been among the most complex
specialized texts (Killmann 2014, Prieto Ramos 2015 etc.). They have
a range of features – with differences related to legal systems,
branches of law and text types – that still pose major challenges
to machine translation. First, they are characterized by all the features
that are a challenge to machine translation generally. Matthiesen
(2017: 44–6) names the following:
(i) syntactic complexity (sentence length, hypotactic structures,
number of clause elements and complexity of the modifiers),
(ii) lexical and syntactic (but also the pragmatic and referential)
ambiguity,
(iii) phraseology,
(iv) divergences at lexical and structural level,
(v) errors in the source text.1
Secondly, there are at least the following features
that are likely to cause machine translation problems, as the author
will show later by means of examples:
(i) terminology, which is always bound to legal systems
and often attributes legal meanings to words and phrases
of common language usage,
(ii) abbreviations that occur in large numbers and where a full
stop runs the risk of being interpreted as a sentence boundary,
(iii) formulaic usage,
(iv) elliptical usage as a special form of formulaic usage,
(v) text type-specific deviations from normal language usage.
Therefore, the question arises as to what extent machine
translation is already capable of translating legal texts or, at least,

1
Errors in the source text are not often mentioned in the literature on legal texts,
but they do occur in practice, as relevant translation experience proves.

121
 Eva Wiesmann: Machine Translation in…

certain types of text or parts thereof into another legal language well
enough so that the post-editing effort is limited. The author
hypothesizes that the development of machine translation in this
regard has not progressed far enough to translate legal texts, in view
of the features mentioned above, without a major post-editing effort.
This hypothesis will be verified in the present article in order to find
out how much of a role machine translation should currently play
in an MA course in Specialized Translation from Italian into German,
which – unlike its counterpart Specialized Translation from German
into Italian – deals only with legal translation. In this context, post-
editing is not to be understood as a light post-editing but as a full post-
editing that complies with DIN EN ISO 18587 (Wallberg 2017) and
meets the requirements of the translation tasks. With such post-
editing, only stylistic imperfections are accepted as long as the target
text still reads fluently (Hansen-Schirra et al. 2017: 178).
After a brief overview of the various methods and systems
of machine translation, the test design, which serves to verify
the research hypothesis, is presented. The test, described in more
detail below, provides for the translation from Italian into German
of several legal texts of different types utilizing a pure machine
translation system (DeepL Translator) and a system integrating
machine translation (MateCat). It was followed by systematization
of errors produced by these systems and evaluation of translation
results on the basis of the criteria previously established.
In the conclusion, the considerations and implications for translation
pedagogy are discussed.

Methods and systems of machine translation

in comparison

Development of machine translation

The history of machine translation dates back to the 1930s (Burchardt

and Porsiel 2017: 12). Until the end of the 80s, machine translation
was rule-based (Hutchins 1995: 440). It implied a phase of more or

122
 Comparative Legilinguistics 37/2019

less elaborate analysis of the source text and a phase of target text
synthesis and could involve a transfer phase. Matthiesen (2017: 28–
32) distinguishes three approaches within rule-based machine
translation: 1) direct translation, 2) transfer-based translation, and 3)
interlingua-based or indirect translation. In the case of direct
translation, the target text was generated directly from the source text
with little or no linguistic (namely morphological) analysis and with
the aid of a bilingual dictionary. The translation took place at the word
level. Transfer-based translation implied a comparatively more
complex but not full linguistic (namely morphological, syntactic,
and semantic) analysis of the source text, resulting in an abstract
source text representation. This was then converted into a target text
representation, from which finally the target text was generated and
syntactically adjusted. In interlingua-based translation, a full linguistic
analysis of the source text was made and a complete abstract
interlingual representation was created, which could then be used
for synthesis. This interlingual representation was theoretically
universally applicable, but on a practical level it could only be realized
to a limited extent.
The next period of machine translation, starting
at the beginning of the 1990s, was dominated by statistical machine
translation in which a distinction can be made between 1) purely
statistical machine translation and 2) example-based machine
translation (Matthiesen 2017: 33–6). In contrast to rule-based machine
translation, statistical machine translation works with information
from aligned parallel corpora, so it is corpus-based. In example-based
machine translation, only sentences and parts of sentences existing
in the corpus are retrieved and used for translation (Werthmann
and Witt 2014: 96). If no matches are found, there is no translation
output. Purely statistical machine translation has evolved from word-
based to phrase-based machine translation. From a large number
of segments of translation corpora and monolingual corpora, a system
is built from which a translation model and a target language model
are developed. The training phase of the system is followed
by the fine-tuning phase with respect to a specific subject area
(technical, medical, economic etc) and the test phase. Statistical
machine translation is based on statistical probability calculations
and involves a two-step process (Koehn 2010: 63–78). In the first
step, the translation model is used to determine probable
correspondences in the target language for the elements of the source
123
 Eva Wiesmann: Machine Translation in…

language. In the second step, the most probable translations

for the context are selected using the language model of the target
language and the most probable word order in the target language
is generated.
The most recent and promising method of machine translation
is neural machine translation, whose peculiarity is that it works with
artificial neural networks, thus making use of artificial intelligence.
It incorporates large knowledge databases for extra-linguistic world
knowledge, but also for language-independent representations of text
meaning. The process of translation in a neural machine translation
system is the following (Forcada 2017): An appropriately trained
artificial neural network (encoder) processes the source sentence word
by word and transposes it into a mathematical representation in which
each word is represented in the context of the sentence
as a multidimensional vector. From this abstract representation
another artificial neural network (decoder) generates word by word
the target-language sentence. To train the system, built from a large
number of translation corpora segments, from which a translation
model is developed, machine learning is used. An adaptive neural
machine translation can also learn from the post-editing of translators,
whereby it applies changes made by the translator, for example,
to a legal term automatically to the rest of the text wherever that term
appears.
While rule-based machine translation no longer plays a role
today, neural machine translation has not quite displaced statistical
machine translation. As pointed out by Castilho et al. (2017: 117–8),
neural machine translation undoubtedly represents a step forward
for the field of machine translation but, depending on the subject area
and the language pair, statistical machine translation can produce
better translations. The characteristic feature of neural machine
translation is that it usually produces fluent (i.e., understandable
and meaningful) texts in which errors (i.e., the non-correspondence
between the source text and the target text) are therefore harder
to find. However, the typical errors of neural machine translation
are usually immediately apparent. These include (van Brussel et al.
2018):
(i) case sensitivity,
(ii) word repetitions,
(iii) word omissions,
(iv) word additions,
124
 Comparative Legilinguistics 37/2019

(v) words that make no sense in context,

(vi) terminological inconsistency,
(vii) wrong numbers.

DeepL Translator vs. MateCat

The systems selected for our test were DeepL Translator, a neural
machine translation system, and MateCat, a CAT system that
integrates machine translation. While the decision to select DeepL
Translator is due to the fact that this machine translation system
challenged the market position of the previous leader Google
Translate (Kyburz 2018), MateCat was chosen because it allows
to use a combination of machine translation systems.
Deepl Translator is a service of the German company DeepL,
which was founded in 2009 under the name Linguee. Since August
2017, this neural machine translation system is available online
for free. In March 2018, the subscription service DeepL Pro was
introduced, which presents itself as an optimized web translator and –
in contrast to the free service – allows to integrate SDL Trados Studio
and other CAT tools. The neural machine translation system
was trained with the translation memory Linguee, which can still
be used in addition to DeepL Translator. The source language
is automatically recognized by Deepl Translator. The freely
combinable languages are now nine (German, English, French, Italian,
Dutch, Polish, Portuguese, Russian, Spanish). Originally, the source
text could only be copied into an input-mask and could not contain
more than 5,000 characters. When entering the mask, the source text
formatting was completely lost. The target text was always displayed
in the output-mask next to it. Now the restriction in the text volume
is lifted and the source text can also be uploaded as a file. This
preserves the formatting in the target text, which can then
be downloaded as a file.
MateCat is the result of a research project undertaken by:
the international research center “Fondazione Bruno Kessler”,
the translation service provider Translated.net, the Université
du Maine and the University of Edinburgh. This CAT system first
used statistical machine translation. In November 2016, the switch

125
 Eva Wiesmann: Machine Translation in…

to neural machine translation occurred. The system has been available

online since 2014 for free and is based on Google Chrome or Safari.
It can be used both with and without registration. When using it with
registration, it is possible to include the translator’s own translation
memories and other resources (especially glossaries), when using
it without registration, the translation memory “My Memory” is used.
As far as the machine translation component is concerned, MateCat
gives the user the following options:
(i) choice of one of the integrated machine translation systems
(Google Translate, ModernMT, Yandex Translate etc.), or
(ii) use of a combination of machine translation systems
(at the time of the test, these were: Google Translate, DeepL
Translator and Microsoft Translator), or
(iii) refrain from using a machine translation system.
The freely combinable languages are presently 209. The source text
is not entered in a form, but always uploaded as a file. In this way,
the formatting of the source text is completely preserved in the target
text, which can also be downloaded as a file. Each translation
can be downloaded as a preview file before any changes are made.

Machine translation of legal texts

Previous studies

Some studies are already available on the use of machine translation

systems for the translation of legal texts. To the author's knowledge,
however, these mostly concern the use of statistical systems. Yates
(2006) examines the accuracy of Babel Fish in translating texts
of interest to law libarians and law library users. In this context,
she concentrates on Babel Fish’s output in English for portions
of Mexico and Germany's civil codes. The purpose of her study was
to determine whether Babel Fish produces translations accurate
enough for law libarians and law library users so that they can grasp
the general intent of the original texts. Because of the severe errors
that altered the meaning of such texts, she concludes that Babel Fish
is not appropriate for most uses in law libraries. Killman (2014),

126
 Comparative Legilinguistics 37/2019

on the other hand, examines the accuracy of Google Translate output

in English for a large sample of legal vocabulary items from
a collection of judgment summaries produced by the Supreme Court
of Spain. He found that Google Translate provided for accurate
translations in slightly over 64% of the cases and demonstrates that
the machine translation system performs consistently well
in the translation of legal vocabulary. Finally, Şahin and Dungan
(2014) have explored students’ use of time, performance and reaction
when they translate technical, literary, media and also legal texts from
English into Turkish using either only printed resources or only online
resources or post-editing target texts produced via Google Translate,
thus, seeing in which contexts students feel better and can achieve
better results when tested. The legal text used in their study was
an extract from the Treaty on the European Union. The analysis
of the questionnaires completed by the participants
and the evaluations of the translations suggested that novice
translators did not seem to be very comfortable with post-editing
machine translation outputs and that the perceived difficulty level
of the texts seemed to have more effect on the time use
and performance of translators than the type of resource used. Indeed,
more time was needed for the translation of the legal text, which was
reported by the participants as the most difficult.
The only study that, to my knowledge, takes legal texts into
account in exploring the use of neural machine translation systems
is that of Heiss and Soffritti (2018). These authors examine the effects
of the availability of DeepL Translator on the teaching of translation
of specialized and non-specialized texts from Italian into German.
Their analysis of quality levels of DeepL Translator’s raw output
and successive improvements with post-editing leads to the conclusion
that the results are quite promising, also with regard to legal texts.
As in our study, the legal text involved in analysis is an excerpt from a
law. So their results can be compared to ours.

Test design

In contrast to the previous studies, we focus on translation of legal

texts and neural machine translation. The aim of our test was to find

127
 Eva Wiesmann: Machine Translation in…

out to what extent machine translation, and indeed neural machine

translation, is already capable of translating legal texts or at least
certain types of text or parts thereof into another legal language well
enough so that the post-editing effort is limited. With regard
to the following question, how much of a role machine translation
should play in the course in Specialized Translation from Italian
into German at the University of Bologna, the legal languages
involved in the test were Italian as source language and German
as target language. The texts were selected from three major areas
of legal activity (legislative area, area of legal practice, area of legal
theory), which also correspond to important areas of translation
practice. As a typical representative of the legislative area, a law,
or rather an excerpt from a law, was selected; and as a typical
representative of the area of legal theory, a legal essay was chosen.
Several texts were selected from the area of legal practice, namely:
a power of attorney, a notarial real estate sale contract, a statement
of claim and a civil court judgment, which are frequently-translated
text types. The length of the source texts, in terms of number of words
and sentences and number of words per sentence, was variable.
The level of difficulty, established with DyLan TextTools, was above
80% for all texts apart from the statement of claim (fig. 1).2 Text
length and level of difficulty were later related to the test results.

Fig. 1. Length and level of difficulty of the test texts.

level of
text types text length
difficulty

24.3
2,328 96 words/
law (excerpt) 96.1%
words sentences
sentence

103.0
power of attorney 412 words 4 sentences words/ 83.0%
sentence

2
Dylan TextTools is an instrument of the Italian Istituto di Linguistica
Computazionale “Antonio Zampolli” based on the Gulpease Index, an index
of readability of a text calibrated on the Italian language.

128
 Comparative Legilinguistics 37/2019

60.8
notarial real estate 1,338 22 words/ 83.3%
sale contract words sentences
sentence

33.3
1,563 47 words/
statement of claim 69.9%
words sentences
sentence

58.1
civil court 1,627 28 words/ 81.4%
judgment words sentences
sentence

41.1
2,650 64 words/
legal essay 99.5%
words sentences
sentence

In addition, given the rapid development of the machine

translation industry, which makes an improvement in quality likely,
it seemed useful not only to compare different systems, but also
to repeat the test after a certain period of time with these systems.
For the reasons mentioned above, the systems DeepL Translator
and MateCat were selected. MateCat was used with a combination
of Google Translate, DeepL Translator and Microsoft Translator.
As period between the two test times, four months were considered
sufficient to detect possible developments. As far as DeepL Translator
is concerned, the first test time was before the introduction
of the subscription service DeepL Pro, and the second test time after,
so that it was also possible to find out whether the introduction
of the subscription service would lead to a deterioration of the output
quality of the free service or not (fig. 2).

129
 Eva Wiesmann: Machine Translation in…

Fig. 2. Test Design.

For the test in which all translations were manually analyzed

and subsequently evaluated by the author, the evaluation criteria
are given by the statement made above that the neural machine
translation mostly produces fluent (i.e., understandable
and meaningful) texts in which the errors (i.e., the non-
correspondence between source text and target text) are harder to find.
This is precisely what can lead to an uncritical use of machine
translation systems by students, especially when translating into
a foreign language. The evaluation criteria
“comprehensibility/meaningfulness of the target text”
and “correspondence between source and target text” correspond
to the branches “fluency” and “accuracy” of the multidimensional
quality metrics defined in Burchardt et al. (2014):

“Accuracy contains issue types that relate to the relationship

of the content of the source and target texts to each other. (Note:
In many contexts, Accuracy is referred to as “Adequacy.” […])
Example: A source text states that a mechanical component is made
of brass and is 25 centimeters long, but the translation states that
it is made of bronze and is 25 inches long.

Fluency contains issue types that relate to the linguistic well-

formedness of the target (or source) text, regardless of the status
of the text as a translation. In principle fluency issues can be detected
by monolingual individuals examining the text with no reference
to another language version. Example: A text accurately translates
source-language content but has grammatical and spelling problems.”

The evaluation category “comprehensibility/meaningfulness”

(like the category “fluency”) was applied to the target texts only.
In this regard, the morphological, syntactic, lexical and semantic
correctness of the target-language version were evaluated. The marks

130
 Comparative Legilinguistics 37/2019

assigned in this category for each sentence of the translated legal texts
were 0 – 3, which allows a degree of differentiation that is compatible
with manual analysis. By contrast, in the evaluation category
“correspondence between source and target text” (like in the category
“accuracy”), both the source and target texts were compared
in consideration of the specific translation situation. The evaluation
concerned the semantic and pragmatic counterparts, both at the level
of concepts and text-type conventions, depending on the given
translation situation. In this category the marks assigned were also 0 –
3. In order to objectify the assignment of marks, the distinctions
mentioned in fig. 3 were made.

Fig. 3. Evaluation grid.

comprehensibility / correspondence between
meaningfulness of the target source and target text
text in consideration of the specific
translation situation

0 completely incomprehensible, no correspondence between

no reconstructible sense source and target text

1 multiple / serious vocabulary minor correspondence between

and/or grammatical errors, only source and target text, sense
partially reconstructible sense is adequately translated
to a small extent

2 few / minor vocabulary and/or large correspondence between

grammatical errors, mostly source and target text, sense
reconstructable sense is adequately translated
to a large extent

3 completely understandable and comprehensive correspondence

meaningful between source and target text

With regard to the specific translation situation, the different

text types have partly varying translation purposes and recipients.
The texts of the types power of attorney, real estate sale contract,
statement of claim and civil court judgment, anchored in the Italian
legal system, should be translated for a recipient of the Federal
German legal system for the purpose of informing the target-culture
recipient about the content of the source texts concerning them.

131
 Eva Wiesmann: Machine Translation in…

The target texts therefore serve only as an aid to understanding, while

the source texts remain the only legally binding texts. The translation
of the legal essay relating to the Italian legal system should also serve
the sole purpose of enabling the recipient of the German legal system
to understand the source text in his own legal language. In contrast
to the texts of legal practice, however, the text of the area of legal
theory, like its translation, has a purely informative function.
The situation is different in the case of the law relating to the Italian
legal system. Exactly as in Heiss and Soffritti (2018), this should
be translated for recipients from the German-speaking part of Italy,
i.e. South Tyrol, in order to form the basis for application
and interpretation alongside the Italian text. On the conceptual level,
there are denominations for all terms in Italian and German.
In all other texts not only the denominations differ, but to a greater
or lesser extent also the concepts. An adequate representation of sense
therefore means, on the terminological level, that the terms
standardized for South Tyrol must be used for translation
of the law selected for the test, whereas for translation of all other test
texts, the terms of the Federal Republic of Germany (whose concepts
are at least partially equivalent to the Italian concepts) must be used.

Test results

Before considering the different categories of errors, the results

of the experiment will be presented in relation to the two categories
of the evaluation grid.
Overall, as shown in fig. 4 – 7,3 the results were poor,
but comparatively better results were obtained for some text types
and parts thereof. The percentage rates were calculated in both
evaluation categories by relating the average marks assigned
to the sentences of each text (or part of text) to the maximum marks
attainable for the sentences of each text (or part of text).
In the evaluation category “comprehensibility/meaningfulness”,
the best results were achieved in the legal essay and, as to DeepL

3
D 9-1 = translated with DeepL Translator on January 9th, 2018; D 10-5 = translated
with DeepL Translator on May 10th, 2018; M 9-1 = translated with MateCat
on January 9th, 2018; M 10-5 = translated with MateCat on May 10th, 2018.

132
 Comparative Legilinguistics 37/2019

Translator, in the law (fig. 4). Even in the statement of claim,

especially in the description of material facts, the result was good
(fig. 4 and 6). In the evaluation category “correspondence between
source and target text” (fig. 5 and 7), the results were always worse
than in the category “comprehensibility/meaningfulness”. Here,
too, the legal essay and, as to DeepL Translator, the law
was positioned at the top, followed by the statement of claim,
especially in relation to the description of material facts. This result
is remarkable given that the level of difficulty found with DyLan
TextTools was the highest in the legal essay and the law
but the lowest in the statement of claim (fig. 1). Such a result may
well be attributable to the length of sentences in test texts, which
was shortest in the law, the statement of claim and the legal essay
(fig. 1). However, as far as the law is concerned, there are major
differences between the output of DeepL Translator and MateCat.
Heiss and Soffritti (2018), who concentrate on the correspondence
between source and target text, come to a similar conclusion
with regard to the law. However, they do not make any comparison
with other kinds of legal texts. This is probably the reason for their
optimistic assessment of the performance of DeepL Translator
with regard to legal texts. The comparatively poorer results achieved
in the power of attorney, the contract, the court judgment and the part
of the statement of claim other than the description of the material
facts (fig. 4 – 7) are certainly also due to their stronger
characterization by the above mentioned features which notoriously
or, in relation to legal texts, presumably, present challenges
to machine translation. Among these characteristics, the syntactic
complexity and the formulaic and elliptical usage, the specific features
of the text types (e.g., one-sentence structures) and the numerous
abbreviations must be mentioned.

133
 Eva Wiesmann: Machine Translation in…

Fig. 4. Comprehensibility/meaningfulness of the target texts.

90
80
70
60
50
40
30
20
10
0
law power of contract statement of court essay
attorney claim judgment

D 9-1 D 10-5 M 9-1 M 10-5

Fig. 5. Correspondence between source and target texts in consideration

of the specific translation situation.
70

60

50

40

30

20

10

0
law power of contract statement of court essay
attorney claim judgment

D 9-1 D 10-5 M 9-1 M 10-5

134
 Comparative Legilinguistics 37/2019

Fig. 6. “Comprehensibility/meaningfulness”: single parts of the statement

of claim.
90
80
70
60
50
40
30
20
10
0
Description of material facts Rest of the statement of claim

D 9-1 D 10-5 M 9-1 M 10-5

Fig. 7. “Correspondence between source and target text”: single parts of the
statement of claim.
70

60

50

40

30

20

10

0
Description of material facts Rest of the statement of claim
D 9-1 D 10-5 M 9-1 M 10-5

As the figures show, DeepL Translator generally performed

better than MateCat. Only in the court judgment, especially
in the procedural formulas, and in the parts of the statement of claim
other than the description of material facts, the results were better with
MateCat. Another positive feature of MateCat is the conservation

135
 Eva Wiesmann: Machine Translation in…

of the layout, which was not possible at the two test times of DeepL
Translator. In terms of all text types, both systems experienced
improvement and deterioration (fig. 4 – 7), so there was no clear trend
of development. However, the introduction of the subscription service
DeepL Pro has evidently not led to a worsening of the free service
DeepL.
In total, 28 different error categories could be detected. These
are listed below and then subsequently illustrated by examples from
the texts, indicated in parentheses, whose translations have been
analyzed. For a better understanding, a translation into English
and a comment on the translation from Italian into German
are provided.

Error categories:
(i) non-translation of sentences and phrases,
(ii) non-translation of words,
(iii) non-translation or incorrect translation of abbreviations,
(iv) translation of proper names,
(v) words that do not make sense in context,
(vi) English words,
(vii) word omissions,
(viii) word repetitions,
(ix) translation of partial synonyms linked by “and” with the same
term,
(x) repetition of letters and letter sequences,
(xi) terminology,
(xii) terminological inconsistency,
(xiii) unexplainable additions,
(xiv) word sequences without syntactic interrelationship,
(xv) sense-changing sentence separations,
(xvi) wrong syntactic interpretation,
(xvii) misinterpretation of the syntax in case of clause elements after
colon,
(xviii) wrong references,
(xix) wrong interpretation of anaphors,
(xx) wrong word order,
(xxi) tempus errors,
(xxii) misinterpretation of certain grammatical structures of Italian
(si passivante, absolute participle constructions, position
of the genitive attribute),
136
 Comparative Legilinguistics 37/2019

(xxiii) wrong adjective interpretation when the adjective corresponds

to a noun with an identical form,
(xxiv) formulaic usage,
(xxv) elliptical usage,
(xxvi) morphological problems,
(xxvii) non-recognition of text-specific deviations from normal
language usage,
(xxviii) problems with specific drafting and text type conventions.

The non-translation of sentences and phrases (i) was mainly

observed in MateCat. It manifests itself in the target text as in ex. 1.

Ex. 1 (all texts).

[…] ǀǀǀ UNTRANSLATED_CONTENT_START ǀǀǀ […] ǀǀǀ
UNTRANSLATED_CONTENT_END ǀǀǀ […].

Non-translated words (ii), underlined in ex. 2, occured in both

the translations of DeepL Translator and MateCat.

Ex. 2 (civil court judgment).

source text IL TRIBUNALE CIVILE E PENALE
DI VERONA SEZIONE PRIMA

target text DAS ZIVIL- UND STRAFGERICHT

VON VERONA SEZIONE PRIMA

English translation THE CIVIL AND CRIMINAL COURT

of the source text OF VERONA FIRST SECTION
example

Also, the non-translation or incorrect translation of abbreviations

(iii; ex. 3) occurs both in the translations of DeepL Translator
and MateCat.

Ex. 3 (statement of claim, civil court judgment).

source text c.p.c.

target text italienisches Strafgesetzbuch

137
 Eva Wiesmann: Machine Translation in…

English translation of Italian Code of Civil Procedure

the source text
example

comment on the translation with “Italian Code of Criminal

German translation Procedure”

Another category of errors is the translation of proper names

(iv; ex. 4). This error occurs more frequently with MateCat than with
DeepL Translator.

Ex. 4 (statement of claim).

source text Elisabetta

target text Elisabeth

Words that do not make sense in context (v; ex. 5) are among
the characteristic errors of neural machine translation. Errors
of this kind occur in fact in both systems with which the test
was carried out.

Ex. 5 (statement of claim: description of material facts).

source text espone

target text entlarvt

English translation of states

the source text
example

comment on the translation with “unmaskes”. Since the verb

German translation “espone” introduces the description of material
facts, “entlarvt” (“unmaskes”) does not make
sense in this context.

Another category of errors that are more common with DeepL

Translator are English words (vi; ex. 6), which do not make sense
in a translation from Italian into German.

138
 Comparative Legilinguistics 37/2019

Ex. 6 (power of attorney).

source text procura speciale

target text special power

English translation of special power of attorney

the source text
example

Word omissions (vii; ex. 7) occur in both DeepL Translator

and MateCat, and the same applies to word repetitions (viii; ex. 8).
In both cases, these are characteristic errors of neural machine
translation. The omitted or repeated words in the target texts
are underlined in the examples.

Ex. 7 (statement of claim).

source text inademplendi non est ademplendum

target text non est ademplendum

Ex. 8 (civil court judgment).

source text posto che l’obbligazione restitutoria […]
costituisce […]

target text da es sich bei der bei der Rückzahlung um […]

handelt

Also, the error which consists in the translation of partial synonyms

linked by “and” (underlined in target text) with the same term (ix)
occurs in both systems (ex. 9). The same applies to the repetition
of letters and letter sequences (x; ex. 10).

Ex. 9 (statement of claim).

source text presenza di vizi e difetti

target text Vorhandensein von Mängeln und Mängeln

139
 Eva Wiesmann: Machine Translation in…

English translation of presence of defects and deficiencies

the source text
example

Ex. 10 (statement of claim).

source text CCTTUU

target text CCTTUUUUU

English translation of forensic expert reports

the source text
example

comment on the In Italian, the repetition of letters is commonly

German translation used to render the singular form of an acronym
(in the example: CTU = consulenza tecnica
d’ufficio) in the plural (CCTTUU).

Examples of terminology errors (xi; ex. 11) are common in all text
types and are frequent in Deepl Translator and MateCat.

Ex. 11 (legal essay).

source text società di capitali

target text Gesellschaften mit beschränkter Haftung

English translation of corporations

the source text
example

comment on the Instead of using the hyperonym, a hyponym was

German translation used in the target text.

Another characteristic error of neural machine translation that occurs

in both systems is terminological inconsistency (xii; ex. 12).

140
 Comparative Legilinguistics 37/2019

Ex. 12 (power of attorney).

source text scrittura privata […] scrittura privata

target text Privatvereinbarung […] Privatvertrag

English translation of privately executed agreement […] privately

the source text executed agreement
example

Additions for which there is no explanation (xiii; underlined in ex. 13)

can be found in both DeepL Translator and MateCat and the same
applies to word sequences without syntactic interrelationship
(xiv; ex. 14).

Ex. 13 (civil court judgment).

source text Orbene, ai fini della decisione, va innanzi tutto
esaminata la contestazione di inammissibilità
della domanda principale degli attori, formulata
dai convenuti sul presupposto dell’omessa
formulazione di un vero e proprio
disconoscimento (o mancato riconoscimento)
ai sensi dell’art. 214 c.p.c. della scrittura-
testamento e dell’omessa produzione in giudizio
dell’originale di quest’ultima.

target text Für die Zwecke der Entscheidung ist zunächst

die Behauptung zu prüfen, dass
die Hauptforderung der Kläger, die von
den Beklagten auf der Grundlage
der Nichtformulierung einer tatsächlichen
Nichtanerkennung (oder Nichtanerkennung)
im Sinne von Artikel 81 Absatz 1 EG-Vertrag
erhoben wurde, unzulässig ist. 214 c.p.c.
der Schreibprüfung und unterlassene Herstellung
in Gerichtsverfahren des Originals der letzteren.

English translation of For the purposes of the court’s decision, first

the source text of all, it is necessary to examine the allegation
example of inadmissibility of the plaintiffs’ main claim,
made by the defendants on the basis
of the omitted formulation of a veritable
repudiation (or non-recognition) of the will

141
 Eva Wiesmann: Machine Translation in…

in accordance with Article 214 of the Code

of Civil Procedure and the omitted presentation
of the original of the will during the proceedings.

comment on the The errors in this example are not limited

German translation to the addition of “im Sinne von Artikel 81
Absatz 1 EG-Vertrag” (in accordance with Article
81 paragraph 1 of the EU treaty). Rather,
the sense is completely distorted by the fact that
the full stop behind “art.” was interpreted
as a sentence boundary.

Ex. 14 (legal essay).

source text Quelli sopra elencati rappresentano, in estrema
sintesi, gli aspetti a nostro avviso di maggior
rilievo della Riforma, per una più approfondita
disamina dei quali rimandiamo alla trattazione
che segue.

target text Die oben aufgeführten sind, kurzum, wir glauben,

dass die wichtigsten Aspekte der Reform für eine
gründlichere Untersuchung der bezeichnen
wir die Diskussion, die folgt.

English translation of Those listed above represent, in a nutshell,

the source text the most important aspects of the Reform
example in our opinion, for a more in-depth examination
of which we refer to the following discussion.

comment on the The translation makes no sense here because

German translation the sentence construction was not correctly
interpreted.

Sense-changing sentence separations (xv) were a problem identified

already in ex. 13 from a civil court judgment. Numerous examples
from the other text types could be cited. An independent case
of wrong syntactic interpretation (xvi), on the other hand, is in ex. 15.

142
 Comparative Legilinguistics 37/2019

Ex. 15 (civil court judgment).

source text Nel corso del giudizio si sono costituiti R.S.
e C.S., quali eredi di G.S., dando atto
del sopravvenuto decesso di quest’ultimo.

target text Im Laufe des Verfahrens wurden R.S. gegründet.

und C.S., als Erben von G.S., die dessen Tod
anerkennen.

English translation of During the proceedings, R.S. and C.S. as heirs

the source text of G.S., appeared before the court and confirmed
example his death.

comment on the The problem consists here in the non-recognition

German translation of the tense of the verb “costituirsi”
and in the interpretation as a passive form
of the verb “costituire”. As a result, instead
of “appear” the translation was “found”.

A special case of syntax error is the misinterpretation of the syntax

when clause elements follow after a colon (xvii; ex. 16).

Ex. 16 (statement of claim).

source text Si producono: 1. […]; 2. […], 3. […].

target text Sie werden produziert: 1. […]; 2. […], 3. […].

English translation of The following documents are presented: 1. […];

the source text 2. […], 3. […].
example

comment on the Neither DeepL Translator nor MateCat interpret

German translation the words listed after the colon as a complement
to “produrre”. Rather, the pronoun “sie” becomes
the subject of a passive sentence.

As further problems of syntactic nature, the following can be cited:

wrong references (xviii; ex. 17), wrong interpretation of anaphors
(xix; ex. 18), wrong word order (xx; ex. 19), tense error (xxi; ex. 20),
misinterpretation of certain grammatical structures of Italian
(si passivante, absolute participal constructions, position

143
 Eva Wiesmann: Machine Translation in…

of the genitive attribute; xxii) (ex. 13: “della scrittura-testamento”

is related to “vero e proprio disconoscimento (o mancato
riconoscimento)”), wrong adjective interpretation when the adjective
corresponds to a noun with an identical form (xxiii; ex. 21).

Ex. 17 (notarial real estate sale contract).

source text A tal fine, l’acquirente dichiara: - che l’immobile
di cui al presente atto è ubicato nel Comune
in cui stabilirà entro diciotto mesi dall’acquisto
la propria residenza; […].

target text Zu diesem Zweck hat der Käufer eine Erklärung

abzugeben: - dass sich die in dieser Urkunde
bezeichnete Immobilie in der Gemeinde befindet,
in der sie innerhalb von achtzehn Monaten nach
dem Erwerb ihres Wohnsitzes errichtet wird; […].

English translation of To this end, the buyer declares: - that

the source text the apartment referred to in this deed is located
example in the municipality in which he will establish his
residence within eighteen months of purchase;
[…].

comment on the The main error in this example is that the pronoun
German translation “sie” is referred to “Immobilie” rather than
“Käufer”. This will then transform the phrase
“establishment of the residence”, into the phrase
“construction of the apartment”.

Ex. 18 (law).
source text L’atto aziendale è predisposto dalla direzione
aziendale dell’Azienda Sanitaria […]
ed è sottoposto all’approvazione della Giunta
provinciale. Esso è adottato dalla direttrice/dal
direttore generale entro i dieci giorni successivi
all’approvazione da parte della Giunta
provinciale.

target text Das Unternehmensgesetz wird von der Leitung

der Gesundheitsbehörde […] ausgearbeitet und
bedarf der Zustimmung des Provinzialrats.
Er wird vom Direktor/Generaldirektor innerhalb

144
 Comparative Legilinguistics 37/2019

von zehn Tagen nach seiner Annahme durch den

Provinzialrat angenommen.

English translation of The internal regulations will be drafted

the source text by the management of the sanitary company […]
example and submitted to the province government
for approval. Such approval will be issued
by the director/general director within ten days
of its approval by the province government.

comment on the The pronoun “er” is not related to the subject

German translation of the sentence before. Apart from that,
the translation contains various terminology
errors, in particular “atto
aziendale/Unternehmensgesetz” and “giunta
provinciale/Provinzialrat”.

Ex. 19 (power of attorney).

source text Con la presente scrittura privata, la società per
azioni di nazionalità tedesca denominata “___
AG” (di seguito, la “Società”) […] nomina
e costituisce procuratori speciali della società
i Signori […].

target text Mit dieser privaten Vereinbarung die deutsche

Firma namens “___ AG” (nachfolgend
die “Gesellschaft”) […] ernennt und bestellt
spezielle Staatsanwälte der Firma […].

English translation of With this privately executed agreement, the

the source text German public limited company “___ AG”
example (hereafter the “company”) appoints
and designates as its special attorneys Messrs:
[…].

comment on the The binomial “ernennt und bestellt” would have

German translation to be placed before the subject “die deutsche
Firma”, which, apart from that, was translated
in too a general way. A terminology error
is the translation of “procuratore speciale” with
“spezieller Staatsanwalt” (“special State
Prosecutor”) instead of “Spezialbevollmächtigter”
(“special attorney”).

145
 Eva Wiesmann: Machine Translation in…

Ex. 20 (statement of claim).

source text così come saranno dimostrati nel corso
dell’istruttoria

target text wie im Rahmen des Ermittlungsverfahrens

nachgewiesen wurde

English translation of as will be proved during the inquiry phase

the source text
example

comment on the A terminology error is the translation of the Civil

German translation Procedure term “istruttoria” with the Criminal
Procedure term “Ermittlungsverfahren”.

Ex. 21 (statement of claim).

source text La società attrice

target text Die Gesellschaft Schauspielerin

English translation of The claimant company

the source text
example

comment on the The adjective “attrice” was interpreted as a noun

German translation and translated as “actor”.

Further sources of error arise from formulaic (xxiv; ex. 22)

and elliptical (xxv; ex. 23) language usage.

Ex. 22 (statement of claim).

source text È autentica.

target text Benachrichtigen Sie.

English translation of the signature is authentic

the source text
example

146
 Comparative Legilinguistics 37/2019

comment on the The translation with “Benachrichtigen Sie”

German translation (Please notify) does not make any sense
in context.

Ex. 23 (statement of claim).

source text Con vittoria di diritti e onorari di causa.

target text Mit dem Sieg der Rechte und Gerichtsgebühren.

English translation of The defendants to pay costs.

the source text
example

comment on the The meaning of the source text formulation

German translation is not clear from the formulation. Anyone who
is unfamiliar with the conventions of the text type
and the mechanisms of the Italian Civil Procedure
can not understand it. The translation through
the two machine translation systems takes place
at the word level and is therefore
as incomprehensible as the source text.

Morphological errors (xxvi) are rare, but MateCat has a few (Ex. 24).

Ex. 24 (legal essay).

source text Principio inderogabile della Riforma

target text Verbindlichen Bestandteil der Reform

English translation of overriding principle of the reform

the source text
example

comment on the The adjective morphology corresponds

German translation to an accusative rather than a nominative.

The last two categories of errors are the non-recognition of text-

specific deviations from normal language usage (xxvii; ex. 25)
and problems with specific drafting and text type conventions
(xxviii; ex. 26).

147
 Eva Wiesmann: Machine Translation in…

Ex. 25 (notarial real estate sale contract).

source text L’anno duemilasette, il giorno ____ del mese
di febbraio

target text Das Jahr zweitausend und sieben, der Tag ____
von Februar

English translation of On the ___ of February two thousand and seven

the source text
example

comment on the The typical form of the date in a notarial deed can
German translation not be translated literally, but that is exactly what
happened in the machine translation.

Ex. 26 (notarial real estate sale contract).

Source text 59,99/1000 (cinquantanove virgola novantanove
millesimi)

Target text 59,99/1000 (fünf Punkte neunundneuzig Punkte

neunundneunzig Tausendstel)

English translation of 59.99/1000 (fifty nine point ninety nine

the source text thousandths)
example

Comment on the Translated by “five point ninety nine point ninety

German translation nine thousandths”

Considerations on translation pedagogy

Although examples were found where little or no post-editing

was required and even if the machine translation output is better
for some types of legal texts or parts thereof as shown above,
the result of the Italian-German machine translation with DeepL
Translator and MateCat is, overall, still insufficient. The development

148
 Comparative Legilinguistics 37/2019

of machine translation in this regard has therefore not progressed

far enough to translate legal texts without a major post-editing effort.
In a course such as Specialized Translation from Italian into
German, in which students have to learn to translate legal texts from
scratch, it therefore makes no sense to give post-editing of machine-
translated legal texts a bigger place in translation pedagogy. Rather,
students should first be made familiar with the current limitations
of machine translation. Secondly, they should be made aware
of the importance of an adequate translation approach and,
in particular, of acquiring the necessary legal expertise, which allows
them to assess the extent to which there is a correspondence between
source and target text in consideration of the specific translation
situation, where the translation reads fluently, i.e. is understandable
and meaningful at a first glance.
An adequate translation approach is certainly one based
on the adequacy strategies defined by Prieto Ramos (2015: 19)
for the translation of legal texts. These strategies provide
for the following steps for each of which legal expertise becomes
relevant and must be acquired in order to achieve a satisfactory
translation:
(i) analysis of the translation situation, i.e. the communicative
situation and the translation brief, in order to determine
the general elements of strategy;
(ii) legal macro-contextualisation of translation process
at the level of the legal system/s, branch/es of law and text
types and genre involved in order to determine the specific
elements of strategy;
(iii) source text analysis;
(iv) reformulation;
(v) revision and verification of the adequacy of the translation
strategy in the light of (i) and (ii).
In particular, the errors illustrated by examples found
in the translations carried out with DeepL Translator and MateCat
reveal the following:
(i) The problem is located at a level well below that
of the translation situation. The purpose and recipient
of the translation are completely disregarded,
as can be expected considering the functioning of machine
translation in general and of neural machine translation
in particular. The purpose and recipient of translation are,
149
 Eva Wiesmann: Machine Translation in…

however, fundamental to the choice of translation strategy

and they must not be overlooked when carrying
out the translation.
(ii) Apart from the fact that the target texts do not reflect the legal
system resulting from the specific translation situation, they
are also characterized by the fact that they contain linguistic
elements which have nothing to do with either the branch
of law or the text type of the source text. A leap in quality can
certainly be achieved by training a machine translation system
with specific translation memories or by combining
a) a machine translation system and b) a CAT tool with
specific translation memories. However, in order to be able
to assess the translation solutions which are either only
partially contained, or not at all, in the translation memory
and which have been purely translated with a machine
translation system, the legal expertise of the translator
is indispensable.
(iii) A machine translation system trained with specific translation
memories or a combination of a) a machine translation system
and b) a CAT tool with specific translation memories can also
improve the use of formulaic and elliptical language bound
to different text types. However, legal expertise
is indispensable here as well.
In order to familiarize students with the current limits
of machine translation and at the same time emphasize the importance
of the adequacy strategies defined by Prieto Ramos (2015: 19),
the author proposes at least the following combinable possibilities:
(i) An introduction to the functioning and typical errors
of machine translation and an overview of the errors made
by machine translation when translating legal texts of different
text types into and from different legal languages in different
translation situations. Purpose: To prevent the uncritical
use of machine translation systems.
(ii) Comparison of the human translations, carried out within
the framework of the teaching activities according
to the above defined adequacy strategies, with machine
translations carried out after human translations. Purpose:
To sharpen awareness of the importance of the adequate
translation approach, to reveal the mistakes of machine

150
 Comparative Legilinguistics 37/2019

translation and to give an idea of the post-editing effort

required.4
(iii) Carrying out a test with two comparison groups, the first
of which carries out a human translation of a legal text
in accordance with above defined adequacy strategies
and the second of which translates the same legal text
by machine and then provides for post-editing taking into
account the above defined adequacy strategies. Purpose:
To underline the importance of the order of the steps
belonging to the adequacy strategies, since it can be assumed
that a subsequent analysis of the specific translation situation,
the source text and its legal background does not lead
to the same results.

Bibliography

Burchardt, Aljoscha, et al. 2014. Multidimensional Quality Metrics

(MQM) Definition. http://www.qt21.eu/mqm-
definition/definition-2014-08-14.html (accessed May 7,
2019).
Burchardt, Aljoscha, and Jörg Porsiel. 2017. Vorwort: Was kann die
maschinelle Übersetzung und was nicht? In Maschinelle
Übersetzung. Grundlagen für den professionellen Einsatz,
ed. Jörg Porsiel, 11–8. Berlin: BDÜ-Fachverlag.
Castilho, Sheila, et al. 2017. Is Neural Machine Translation the New
State of the Art? The Prague Bulletin of Mathematical
Linguistics 108: 109–20.
Forcada, Mikel L. 2017. Making sense of neural machine translation.
Translation Spaces 6/2: 291–309.
Hansen-Schirra, Silvia, et al. 2017. Post-Editing: Strategien, Qualität,
Effizienz. In Maschinelle Übersetzung. Grundlagen für den

4
The importance of a comparison with reference texts is also underlined by Heiss
and Soffritti (2018). In addition, they point out that the entire text and the translation
situation must be kept in mind when post-editing individual text parts. Moreover, they
maintain that a theory-based approach is a prerequisite for high-quality translations
and that post-editing that takes translation theory into account should be an essential
part of translation pedagogy.

151
 Eva Wiesmann: Machine Translation in…

professionellen Einsatz, ed. Jörg Porsiel, 176–91. Berlin:

BDÜ-Fachverlag.
Heiss, Christine, and Marcello Soffritti. 2018. DeepL Traduttore
e didattica della traduzione dall’italiano in tedesco. Alcune
valutazioni preliminari. InTRAlinea. Special Issue:
Translation and Interpreting for Language Learners (TAIL).
http://www.intralinea.org/specials/article/2294 (accessed
September 13, 2019).
Hutchins, W. John. 1995. Machine Translation: A Brief History
In Concise History of the Language Sciences: from
the Sumerians to the Cognitivists, eds. Ernst F. K. Koerner
and R.E. Asher, 431–45. Oxford: Pergamon Press.
Killman, Jeffrey. 2014. Vocabulary Accuracy of Statistical Machine
Translation in the Legal Context. In Third Workshop on Post-
Editing Technology and Practice, eds. Sharon O’Brian,
Michel Simard and Lucia Specia, 85–98.
www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proc
eedings_PEWorkshop_final.pdf (accessed May 7, 2019).
Koehn, Philipp. 2010. Statistical Machine Translation. Cambridge:
Cambridge University Press.
Kyburz, Kevin. 2018. Schlägt sogar Google.
Die Übersetzungsmaschine DeepL.
https://techgarage.blog/schlaegt-sogar-google-die-
uebersetzungsmaschine-deepl/ (accessed February 28, 2019).
Matthiesen, Aaron J. 2017. Maschinelle Übersetzung im Wandel.
Die Auswirkungen von künstlicher Intelligenz auf maschinelle
Übersetzungssysteme. Mit einer vergleichenden Untersuchung
von Google Translate und Microsoft Translator. Berlin:
epubli.
Prieto Ramos, Fernando. 2015. Quality Assurance in Legal
Translation: Evaluating Process, Competence and Product
in the Pursuit of Adequacy. International Journal
for the Semiotics of Law – Revue internationale de Sémiotique
juridique 28/1: 11–30.
Şahin, Mehmet, and Nilgün Dungan. 2014. Translation testing
and evaluation: A study on methods and needs. Translation
& Interpreting 6/2: 67–90.
Van Brussel, Laura, et al. 2018. A Fine-grained Error Analysis
of NMT, PBMT and RBMT Output for English-to-Dutch.
In Eleventh International Conference on Language Resources
and Evaluation, 3799–804.

152
 Comparative Legilinguistics 37/2019

https://biblio.ugent.be/publication/8561558 (accessed May 8,

2019)
Wallberg, Ilona. 2017. DIN EN ISO 18587 – eine Norm über
den Prozess des Posteditierens. In Maschinelle Übersetzung.
Grundlagen für den professionellen Einsatz, ed. Jörg Porsiel,
160–7. Berlin: BDÜ-Fachverlag.
Werthmann, Antonia, and Andrea Witt. 2014. Maschinelle
Übersetung – Gegenwart und Perspektiven. In Translation
and Interpretation in Europe. Contributions to the Annual
Conference 2013 of EFNIL in Vilnius, ed. Gerhard Stickel,
79–103. Frankfurt et al.: Lang.
Yates, Sarah. 2006. Scaling the Tower of Babel Fish: An Analysis
of the Machine Translation of Legal Information. Law Library
Journal 98/3: 481–500.

153