Language and Intelligence

Language and Intelligence

• 1.
  Language and IntelligenceSchool of Computer Applications Language Intelligence Language & Intelligence Natural Language Processing (NLP), Machine Translation (MT), Computer Assisted Language Learning (CALL), Speech Artificial Intelligence, World Wide Mind Language Evolution, Semantics, 3D Worlds, Neural Networks, Speech and Multi-Modal Interfaces
• 2.
  Language and IntelligenceStaff Postgrad Students Dr D. Fitzpatrick A. Cahill, N. Gough, J. Hayes S. Harford, M. Hearne, Dr M. Humphrys M. Mc Carthy, C. O’Leary, J. Kelleher M. Tooher Dr J. Mc Kenna Prof J. Van Genabith Affiliated Researcher R. Walshe D. O’Connor M. Ward Dr A. Way
• 3.
  Language and IntelligenceNCLT National Centre for Language Technologies computing. dcu . ie / nclt World Wide Mind w2mind.org
• 4.
  Language Research AreasExample-Based Machine Translation (EBMT) People : Dr A. Way M. Hearne: Hybrid (Stats + rule-based) Machine Translation N. Gough: Web-Based Machine Translation Overview : We are currently investigating two approaches to MT which can broadly be described as EBMT: a) Marker-based EBMT b) DOT and LFG-DOT School of Computer Applications
• 5.
  Language Research AreasSchool of Computer Applications Example Based Machine Translation Given : John went to school Jean est allé à l’école . The butcher’s is next to the baker’s La boucherie est à côté de la boulangerie. Isolate useful fragments: John went to Jean est allé à the baker’s la boulangerie We can now translate: John went to the baker’s as Jean est allé à la boulangerie .
• 6.
  Language Research AreasSpeaker Characterisation People : Dr J. McKenna M. Tooher: Machine Learning of Speaker Characteristic Speech Dynamics and Interactions Overview : Our research aims to separate the linguistic content of speech from that containing speaker-specific information. School of Computer Applications
• 7.
  Language Research AreasSpeaker Characterisation School of Computer Applications Separate Linguistic Data from Speaker Characteristics Machine Translation New Language Bonjour Hello
• 8.
  Language Research AreasCALL use of XML technologies specific requirements for Endangered Languages e.g. computing. dcu . ie /~ mward /nawat.html interest from UNESCO, European Bureau of Lesser Used Languages working with projects in Siberia and Togo/Benin VOCALL (Vocationally oriented CALL) School of Computer Applications
• 9.
  Intelligence World WideMind project People: Dr M. Humphrys, R. Walshe. C. O’Leary, D. O’Connor Overview : This is a new idea for decentralising the work in AI by putting agent mind and worlds online as reusable servers This work proposes that the construction of advanced artificial minds may be too difficult for any single lab No easy system exists whereby a working mind can be made from the components of two or more labs O ur system aims to change this and accelerate the growth of AI School of Computer Applications
• 10.
  Intelligence Society ofMind constructed from Multiple servers 1. client talks to: 1. Mind M , which talks to: 1. Mind 2. Mind M , which talks to: 1. Mind 3. Mind AS , which talks to: 1. Mind 2. Mind M , which talks to: 1. Mind 3. Mind 2. World W , which talks to: 1. World School of Computer Applications
• 11.
  Language and IntelligenceWorld Wide Mind School of Computer Applications World (problem to solve) Client (do some task) Mind Server Mind Mind Mind Uses World Wide Web and cgi-bin/perl for communication State State Action Action Action State State Action
• 12.
  Language and IntelligenceDr D Fitzpatrick: Applications of Speech Technology and Multi-modal interfaces School of Computer Applications Map Information Analysis Force Feedback/ (Haptic) Device Purpose: to convey spatial information non-visually i.e. using sensors other than vision
• 13.
  Language and IntelligenceR. Walshe: Evolution of Early Language School of Computer Applications World Agent (Speaker, Hearer, Learner) Reinforcement Learning Network (Neural Network) State Action Agent (Speaker, Hearer, Learner) Reinforcement Learning Network (Neural Network) State of the world Action Unique features: No master No prior language knowledge Grrraahhh = ??? Go Left Grrraahhh
• 14.
  Language and IntelligenceJ. Kelleher: Natural Language interface to 3D world - Situated Language Interpreter School of Computer Applications Natural Language Understanding Natural Language Interface Visual Context
• 15.
  Language and IntelligenceJ. Hayes : Semantics - computational modelling of nominal compounds School of Computer Applications Linguistic Level Compounding Cognitive Process Concept Combination Computer Wizard Computer Wizard ? + Generate an Interpretation (form a meaning) Interpretation
• 16.
  Language and IntelligenceS. Harford: A Neural Network model of Melodic Memory School of Computer Applications Learning, Feedforward Feedback Processing Neural Networks Input Output