Natural Language Processing and Cognitive Science (NLPCS 2011)

Natural Language Processing and Cognitive Science (NLPCS 2011)

8th International Workshop on Natural Language Processing and Cognitive Science (NLPCS 2011)
Special Issue: Human-Machine Interaction in Translation
20-21 August, 2011 - Copenhagen, Denmark
 
The conference venue is Copenhagen Business School, Solbjerg Plads 3, 2000 Frederiksberg, auditorium SP.s13 (the Velux auditorium). Directions can be found under the item 'Getting here'.
In conjunction with

First Ph.D Course in Translation Processes Research (TPR)
15-19 August, 2011 - Copenhagen, Denmark
The course takes place at Dalgas Have 15, 2000 Frederiksberg.
 

The Department of International Language Studies and Computational Linguistics, Copenhagen Business School welcomes you to 8th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2011 - on Human-Machine Interaction in Translation.
 
Co-chairs of the workshop:
  • Bernadette Sharp, Staffordshire University, U.K.
  • Michael Zock, CNRS, LIF, Marseille, France
  • Arnt Lykke Jakobsen, CBS, Copenhagen, Denmark
  • Michael Carl, Copenhagen Business School, Denmark
Local organizers:
Workshop Program Committee
  • Aretoulaki, M. (Dialog Connection, UK)
  • Ball, J.T. (Air Force Research Laboratory, USA)
  • Barnden, J. (Birmingham University, UK)
  • Blanchon, H (IMAG, Grenoble, France)
  • Carl, M. (Copenhagen Business School, Denmark)
  • Casacuberta, F. (Universidad Politécnica de Valencia, Spain)
  • Cristea D. (University A.I. Cuza of Iasi, Romania)
  • Delmonte, R. (Ca' Foscari, Venezia, Italy)
  • Endres-Niggemeyer (Fachhochschule Hannover, Germany)
  • Ferret, O. (CEA, Fontenay-aux-Roses, France)
  • Fischer, I. ( University of Konstanz, Germany)
  • Hardt, D. (Copenhagen Business School, Denmark)
  • Higgins, C.A. (Nottingham Trent University, UK)
  • Higgins, S.J.B. (Nottingham Trent University, UK)
  • Jakobsen, A.L. (Copenhagen Business School, Denmark)
  • Keller, F. (University of Edinburgh, UK)
  • Koehn, P. (University of Edinburgh, UK)
  • Kutz, O. (University of Bremen, Germany)
  • Langlais, P. (University of Montreal, Canada)
  • Lapalme, G. (University of Montreal, Canada)
  • Lepage, Y. (Waseda University, Japan)
  • Macklovitch, E. (Bureau de la traduction, Canada)
  • Mladenic, D. (J. Stefan Institute, Slovenia)
  • Murray, W. E. (Boeing Research and Technology)
  • Neustein, A. (Journal of Speech Technology, USA)
  • Netter, K. (Consulting GmbH, Saarbrücken, Germany)
  • Rapp, R. (University of Leeds, UK)
  • Roche, C. (Université de Savoie, France)
  • Rosso, P. (Universidad Politécnica de Valencia, Spain)
  • Schwab, D. (LIG-GETALP, Grenoble, France)
  •  Sedes, F. (Université de Toulouse, France)
  • Simard, M. (NRC, Gatineau, Québec, Canada)
  • Thompson, G. (Liverpool University, UK)
  • Tiedmann, J. (Uppsala University, Sweden)
  • Tufis, D. (RACAI, Bucharest)
  • Rayson, P. (Lancaster University, UK)
  • Sharp, B. (Staffordshire University, UK)
  • Wandmacher, T. (Systran, Paris, France)
  • Zock, M. (LIF- CNRS, France)
 

Program

Saturday, august 20

8:30-9:15
Registration
9:15-9:30
Welcome to participants
9:30-10:15
 Sinha, RMK (invited talk)
 Man-Machine Integration in Translation Processes: an Indian Scenario
10:15-10:30
 coffee break
 
Machine Translation (idiomaticity, morphologically rich and resource-poor languages)
10:30-11:00
 Huet, S. & P. Langlais
 Identifying the translations of idiomatic expressions using TransSearch
11:00-11:30
 Ceausu, A. & D. Tufis
 Addressing SMT Data Sparseness when Translating into Morphologically-Rich Languages
11:30-12:00
Jaber, S., Tonelli, S. & R. Delmonte
 Venetan to English machine translation: issues and possible solutions
12:00-13:30
lunch break
 
Translation and Cognitive Processes
13:30-14:00
Jakobsen, A.L.
 First-ever PhD summer school on translation process research: observations and first conclusions
14:00-14:30
Teixeira, C.
 Knowledge of provenance and its effects on translation performance
14:30-15:0
Christensen, T. P. & A. Schjoldager
 The Impact of Translation-Memory (TM) Technology on Cognitive Processes: Student-Translators' Retrospective Comments in an Online Questionnaire
15:00-15:30
coffee break
 
15:30-16:15
Shukla, R. & RMK Sinha (invited talk)
 Divergence patterns for Urdu to English and English to Urdu Translation
 
Human Text Processing (reading, writing, translating)
16:15-16:45
Nilsson, M. & J. Nivre
 Entropy-Driven Evaluation of Models of Eye Movement Control in Reading
16:45-17:15
Carl, M.
 Patterns of shallow text production in translation
17:15-17:45
Alves, F., Pagano, A. & I. A. da Silva
 Modeling (Un)Packing of Meaning in Translation: Insights from Effortful Text Production
 
19:00-22:00
dinner in Tivoli

Sunday, august 21

9:00-9:45
Bhattacharyya, P. (invited talk)
 IndoWordNet and Multilingual Resource Conscious Word Sense Disambiguation
9:45-10:00
coffee break
 
Ontological, linguistic and interface issues
10:00-10:30
Glückstad, F. K.
 Application of Classical Psychological Theory to Terminological Ontology Alignment
10:30-11:00
 
Klein. A., Krenn, B. & H. Trost
 Functions of Explicit Negation in German News Textsn
11:00-11:30
Llopis, M. & A. Ferrandez
 {AskMe*}: Reducing the costs of adoption, portability and learning process in a natural language interface to query databases
11:30-12:00
Zhang, B., Wang, X. & G. Fang
 Evaluation on Lexical Category Acquisition
 
12:00-13:30
lunch break
 
Machine Translation and the human factor (interlingua, evaluation, post-editing)
13:30-14:00
Finch, A., Song, W., Tanaka-Ishii, K. & E. Sumita
 Source Language Generation from Pictures for Machine Translation on Mobile Devices
14:00-14:30
Starlander, M. & P. Estrella
 Looking for the best Evaluation Method for interlingua-based Spoken Language Translation in the medical domain
14:30-15:00
Carl, M., Dragsted, B., Elming, J., Hardt, D. & A. L. Jakobsen
 The Process of Post-Editing: A Pilot Study
15:00-15:30
Brkic, M., Seljan, S. & Matetić
 Machine Translation Evaluation for Croatian-English and English-Croatian Language Pairs
 
15:30-16:00
coffee break
 
NLP and Cognition (linguistic resources, reasoning, sentiments)
16:00-16:45
Zock, M. (invited talk)
 A semantic map and a lexical compass to help authors find the word they are searching for
16:45-17:15
Murray, W. & D. Jain
 Modeling Cognitive Frames for Situations with Markov Logic Networks
17:15-17:45
Petrakis, S. & M. Klenner
 Learning Theories for Noun-Phrase Sentiment Composition
17:45-18:15
Valitutti, A.
 How Many Jokes are Really Funny? A New Approach to the Evaluation of Computational Humour Generators
18:15-18:30
Wrap up discussion
 
19:00-22:00
Let's talk it over a drink: a glass of beer

First Keynote Speaker at NLPCS 2011

R.M.K. Sinha, IIT Kanpur, India

Man-Machine Integration in the Translation Process: An Indian Scenario Translating natural language text or speech from one language to another is a challenging task. The quality of machine translation is found to be inferior to that of translation produced by a human being. However, machines are good at providing rough translations which can be used by human translators. Thus integrating man with the machine in the translation process is one of the ways of making translation systems practical in real life. There can be a learning loop in this man-machine integration process. This paper is focused on examining these aspects with specific reference to the Indian scenario. The Indian translation scenario is complex with a multiplicity of languages and scripts. As compared to the EU scenario, besides multiplicity of scripts, Indian languages exhibit free word group order; are morphologically rich; have complex usage of predicate verbs; use various distinctive features such as replicative words, onomatopoeic combinations etc. These result in a large number of variations in semantically equivalent utterances or written forms. The translation industry is still in its infancy in terms of preparedness for technology absorption. Machine translation strategies employed are primarily rule-based

Dr. Sinha is a Professor of Computer Science & Engineering and Electrical Engineering at IIT Kanpur where he has been serving for more than three decades. Dr. Sinha's major research concentration has been in the areas of language technology and applied artificial intelligence. In the early 70s, he worked on Devanagari OCR and was the first person to work on the topic. In the late 70s and early 80s, he worked on Indian script enabling and their computer processing. He is the originator of the well-known multilingual GIST technology / IDC, ISCII coding, INSCRIPT keyboarding and several other Indian language technologies. Starting in the late 80s, he has been working on computer processing of Indian languages. He is the originator of AnglaBharati and AnuBharati technology for translation from English to Indian languages and vice-versa. He is a member of TDIL working group, National Translation Mission Advisory, Technical Advisory Committee of CDAC, Standardization committee, Associate UNESCO chair in ORBICOM. He is founding president of the Society for Machine Aids for Translation and Communication (SMATAC), Fellow IETE, and Senior Member of IEEE. He has been a visiting professor at Michigan State University, Wayne State University, INRS Quebec and Asian Institute of Technology.

Second Keynote Speaker at NLPCS 2011

V.N. Shukla, CDAC Noida, India

Divergence patterns for Urdu to English and English to Urdu Translation Translation divergence is said to occur when two languages differ in their grammars. Thus divergence would occur when a sentence in the source language translates to a sentence in the target language in a very different manner. Divergence for English to Urdu or Vice versa has not been explored so far barring an exception [Saboor et al, 2010] which has studied the divergence patterns for Urdu to English and not vice versa. Thus here we try to identify the various divergence patterns that exist for English to Urdu as well as Urdu to English

Prof. Vijendrakumar Narendraprasad Shukla is Associate Director and Professor in the C-DAC Noida and heads Speech & Natural Language Processing lab. Prior to joining current Organization, he served as Assistant Professor / Lecturer in various academic institutions linked with University of Pune, Marathwada University ,University of Bombay and I.I.T.Roorkee. Prof. Shukla started his career in teaching way back in 1982 and has a total experience of about 28 years. He received his M. Tech. (Computer Science & Technology) from University of Roorkee. He has a number of research publications at International and National level to his credit. He is a member of various professional bodies like IETE, IEEE, ISTE. He was Manager W3C India office. He worked as a Convener of the National Committee on Technology Development in Indian Languages (TDIL) set up by the Department of Information Technology, Government of India. He is consortia leader for English to Indian Language Machine Translation Project awarded by TDIL unit of Department of Information Technology, Govt. of India. He was conferred the 1st IETE-Brig M L Anand Award for his outstanding contribution in the field of I.T. His teaching and research subjects include Digital library and Archiving, Data Mining, Formal Computing, Software Engineering, Object Oriented Software Engineering, Multilingual Computing, Geomatics, e-governance & Open Source Technology. He is an initiator of the formulation of curriculum for M.Tech. Language Technology and M.Tech Linguistic Computing Programmes.

Third Keynote Speaker at NLPCS 2011

P. Bhattacharyya, IIT Bombay, India

Indowordnet and Multilingual Resource Conscious Word Sense Disambiguation Wordnets have become crucial resources for NLP. They are complex structures capturing various kinds of lexico semantic relations among words. In the first part of the talk we describe the principles and methodolgies followed in multilingual wordnet construction. We close this part of the discussion with a brief description of the Pan-Indian multilingual dictionary standard that IndoWordnet has given rise to and is the essential resource for multilingual WSD. In the second part of the presentation, we discuss ways of doing WSD under resource constraint. Next we describe how the corpus of one language can help WSD of another language, i.e., LANGUAGE ADAPTATION. The talk is presented in a multilingual setting of Indian languages. There are 22 official languages in India with strong requirements of machine translation and cross lingual search. Our languages of focus in this talk are Hindi and Marathi along with English and the domains of focus are Tourism and Health which are important to India.

Dr. Pushpak Bhattacharyya is a Professor of Computer Science and Engineering at IIT Bombay. He received his B.Tech from IIT Kharagpur, M.Tech from IIT Kanpur and PhD from IIT Bombay. He has held visiting postions at MIT, Cambridge, USA, Stanford University, USA and University Joseph Fourier, Grenoble, France.

Dr. Bhattacharyya's research interests include Natural Language Processing, Machine Translation and Machine Leaning. He has had more than 130 publications in top conferences and journals and has served as program chair, area chair, workshop chair and PC member of top fora like ACL, COLING, LREC, SIGIR, CIKM, NAACL, GWC and others. He has guided 7 PhDs and over 100 masters and undergraduate students in their thesis work. Dr. Bhattacharyya plays a leading role in India's large scale projects on Machine Translation, Cross Lingual Search, and Wordnet and Dictionary Development. Dr. Bhattacharyya received a number of prestigious awards including IBM Innovation Award, United Nations Faculty Research Award, MIcrosoft Research Grant Award, Yahoo faculty award, IIT Bombay's Patwardhan Award for Technology Development, and Ministry of IT and Digital India Foundation's Manthan Award. Recently he has been appointed Associate Editor of the prestigious journal, ACM Transactions on Asian Language Information Processing. Prof. Bhattacharyya is the organizing chair of COLING 2012 at IIT Bombay.

Fourth Keynote Speaker at NLPCS 2011

M. Zock, CNRS-LIF, Marseilles, France

A semantic map and a lexical compass to help people find the words they are searching for NLP has produced very few applications to support people in their quest to understand or produce language. Yet, such applications are not only badly needed, they are also possible. I will deal here only with one problem, word finding (lexical access or word retrieval), showing how electronic dictionaries could be improved to help language producers (speaker, writer) find the words they are looking for. Since finding supposes searching, I suggest to build similar tools to the ones we use elsewhere for this activity, namely, a map and a compass. While the 'semantic map' defines the territory within which search takes place, the 'lexical compass' guides the user, helping her or him to reach the goal (target word). I will discuss how such tools or resources can be built and how they can be used for search. After having completed a PhD in experimental psychology,

Dr. Zock was appointed by the CNRS to work at LIMSI, an AI-lab close to Paris (Orsay). Since 2006 he lives in Marseille (southern France), joining TALEP, the NLP group of the LIF (université de la Méditerranée). His research interests lie in language production by and large. Starting from user needs and empirical findings he tries to build tools helping people to acquire the skill of writing or speaking. His research foci comprise: (a) Message-planning: creation of a conceptual interface to help people compose their thoughts; (b) Outline-planning: help authors to perceive possible links between their ideas in order to produce coherent discourse; (c) Lexical access, i.e. help authors to find the word they are searching for (navigation in electronic dictionaries based on findings concerning the mental lexicon) (d) Acquisition of fluency in speaking, i.e. acquisition of the basic structures needed in order to survive in the new culture.

NLPCS 2011 -  Proceedings