Language Analysis using
Machine learning:
An overview
Rudradeb Mitra
Bio
• AI researcher published 10
research papers on topics like
logical reasoning, language
analysis, Semantic web.
• Masters from University of
Cambridge, UK.
• Involved with startups since
2010.
• Machine learning enthusiast.
What is machine learning?
• Apply previously acquired
knowledge to new or novel
situation
• Search tree, neural network,
Bayesian reasoning, logic,…
• Boom and AI winter cycle
(1974-80, 1980-87)
Arthur Samuel with his checker playing machine
But something is happening
recently…..
• AlphaGo defeated world Go
champion.
• AP is going to use machine
created news articles for
sports coverage
• Deep Mind to check NHS eye
scans for disease analysis
• People have termed it similar
to Industrial revolution
Applications
• News articles (AP), robot lawyers, designers
(wix), car industry (google, apple), tour guides,
rockets….
• Open AI, facebook, google, microsoft, twitter…
• ….machine learning will affect all domains…..
Why now?
• Big data - What do we do with
it?
• Visualize, Analyze - Human
element
• Machine learning / Deep
neural network - Learn from
the data
Language understanding
• “A computer would deserve to
be called intelligent if it could
deceive a human into
believing that it is human.” -
Alan Turing
• Language is the form of
communication.
• Basic necessity in solving AI
problems in language
understanding.
Applications of NLP
• Topic modelling
• Text summarization
• Translation
• Sentiment analysis
• Image captions and descriptions …
Historic approaches…
• Syntax tree
• Semantic - RDF, OWL
• LSA - bag of words,
similar words appear
together.

Concepts are represented
as patterns of words.
Latent Dirichlet Analysis
• Start with document, bag of words and K topics
• Output - Documents are of what topics (in %)
• Randomly/semi-randomly assign each word to a topic
• All topic assignments except for the current word in
question are correct
• Improve by reassign ‘w’ a new topic. Choose topic t
with probability p(topic t | document d) * p(word w |
topic t)
Neural Networks
Back propagation
Deep Neural network
• Many layers / neurons
• Wide / Deep network
• Data + computations power
CBOW / skip gram
word2vec
word2vec
• Applications: Sentence auto fill, playlist, genes…
• Issues: Local context. Missing global context.
• GloVe
Recurrent Neural Network
LSTM
Sentiment Analysis with RNN
Convolutional Neural
Network
General learning algorithm
AlphaGo - Building intuition
• Took 150,000 games played by good
human players and used an artificial
neural network to find patterns
• Learned to predict with high
probability what move a human
player would take
• Play against itself, to get an estimate
of how likely a given board position
was to be a winning one -
Reinforcement learning
• No detailed knowledge of Go.
Instead analyzed thousands of prior
games and engaged in a lot of self-
play.
Thank You
Questions?
mitra.rudradeb@gmail.com
Feel free to email or add me on linkedin
Reinforcement learning

Natural language Analysis

  • 1.
    Language Analysis using Machinelearning: An overview Rudradeb Mitra
  • 2.
    Bio • AI researcherpublished 10 research papers on topics like logical reasoning, language analysis, Semantic web. • Masters from University of Cambridge, UK. • Involved with startups since 2010. • Machine learning enthusiast.
  • 3.
    What is machinelearning? • Apply previously acquired knowledge to new or novel situation • Search tree, neural network, Bayesian reasoning, logic,… • Boom and AI winter cycle (1974-80, 1980-87) Arthur Samuel with his checker playing machine
  • 4.
    But something ishappening recently….. • AlphaGo defeated world Go champion. • AP is going to use machine created news articles for sports coverage • Deep Mind to check NHS eye scans for disease analysis • People have termed it similar to Industrial revolution
  • 5.
    Applications • News articles(AP), robot lawyers, designers (wix), car industry (google, apple), tour guides, rockets…. • Open AI, facebook, google, microsoft, twitter… • ….machine learning will affect all domains…..
  • 6.
    Why now? • Bigdata - What do we do with it? • Visualize, Analyze - Human element • Machine learning / Deep neural network - Learn from the data
  • 7.
    Language understanding • “Acomputer would deserve to be called intelligent if it could deceive a human into believing that it is human.” - Alan Turing • Language is the form of communication. • Basic necessity in solving AI problems in language understanding.
  • 8.
    Applications of NLP •Topic modelling • Text summarization • Translation • Sentiment analysis • Image captions and descriptions …
  • 9.
    Historic approaches… • Syntaxtree • Semantic - RDF, OWL • LSA - bag of words, similar words appear together.
 Concepts are represented as patterns of words.
  • 10.
    Latent Dirichlet Analysis •Start with document, bag of words and K topics • Output - Documents are of what topics (in %) • Randomly/semi-randomly assign each word to a topic • All topic assignments except for the current word in question are correct • Improve by reassign ‘w’ a new topic. Choose topic t with probability p(topic t | document d) * p(word w | topic t)
  • 11.
  • 12.
  • 13.
    Deep Neural network •Many layers / neurons • Wide / Deep network • Data + computations power
  • 14.
  • 15.
  • 16.
    word2vec • Applications: Sentenceauto fill, playlist, genes… • Issues: Local context. Missing global context. • GloVe
  • 17.
  • 18.
  • 19.
  • 20.
  • 21.
  • 22.
    AlphaGo - Buildingintuition • Took 150,000 games played by good human players and used an artificial neural network to find patterns • Learned to predict with high probability what move a human player would take • Play against itself, to get an estimate of how likely a given board position was to be a winning one - Reinforcement learning • No detailed knowledge of Go. Instead analyzed thousands of prior games and engaged in a lot of self- play.
  • 23.
  • 24.