Computational Approaches to Figurative Language

Workshop in conjunction with HLT/NAACL 2007
To be held in Rochester, NY, April 26, 2007


Program     Registration   Workshop Description   Submissions    Important Dates   Organizers  Program Committee

Figurative language, such as metaphor, metonymy, idioms, personification, simile among others, is in abundance in natural discourse. It is an effective apparatus to heighten effect and convey various meanings, such as humor, irony, sarcasm, affection, etc. Figurative language can be found not only in fiction, but also in everyday speech, newspaper articles, research papers, and even technical reports. The recognition of figurative language use and the computation of figurative language meaning constitute one of the hardest problems for a variety of natural language processing tasks, such as machine translation, text summarization, information retrieval, and question answering. Resolution of this problem involves both a solid understanding of the distinction between literal and non-literal language and the development of effective computational models that can make the appropriate semantic interpretation automatically.

As natural language processing moves to an unprecedented new stage, it has become more urgent than ever to tackle the bottleneck presented by figurative language. There has been an increasing amount of work in this area in the past few years (e.g. theoretical semantic/pragmatic analyses of non-compositional phenomena, research on psychological/neuro-linguistic modeling of figurative language comprehension and production, research on the structure of the lexicon, knowledge representation and figurative language comprehension, domain-specific figurative language detection, computational corpus studies of figurative language), but much more work needs to be done (e.g. large-scale automatic figurative language detection, automatic extraction of idioms and non-compositional phrases from large corpora, automatic semantic interpretation of figurative language, automatic figurative language generation, machine translation of non-literal phenomena, etc.). The goal of this workshop is to provide a venue for researchers in this area to inform each other and the natural language processing community at large of the state of the art of current systems and to reach a better understanding of the new issues and challenges that need to be tackled.

The workshop is intended to be highly interdisciplinary. We encourage the participation of people whose research deals with figurative language from different perspectives, including (but not limited to) applied linguistics, psychology, corpus linguistics, human-computer interaction, natural language processing, etc.

Topics covered by the workshop include, but are not limited to:

(1) Computational models of figurative language processing, including
    - extracting idioms and non-compositional phrases from large corpora
    - classifying metaphoric/non-metaphoric and humorous/non-humorous language use
    - computing non-literal meaning
    - multilingual or cross-lingual processing of figurative language
    - computational modeling of human figurative language  comprehension and production

(2) Psychological models of figurative language processing, including
    - figurative language comprehension
    - figurative language production
    - figurative language acquisition
(3) Corpus-driven studies of figurative language, including
    - corpus-based studies of figurative aspects of any language
    - corpus-based studies of specific linguistic cues for figurative language
    - effects of domain and genre on studies of figurative language
    - annotation of non-literal phenomena in corpora

(4) Theoretical discussions on literal and non-literal language,  including discussions on
    - the distinction between literal and non-literal language
    - the distinction between different types of figurative language
    - cross-linguistic differences of figurative language

(5) Lexical and ontological resources for figurative language  processing, including
    - representation of non-literal meaning in lexicons and ontologies
    - development of new lexical resources for figurative language processing

(6) Evaluation of figurative language processing in large-scale NLP systems, such as machine translation, Computer-assisted Language Learning (CALL), question answering, dialogue systems, etc.

The emphasis of the workshop is on computational approaches  to figurative language. We particularly are interested in  submissions that deal with figurative language in the context  of Machine Translation, Word Sense Disambiguation, Information  Extraction, Document Retrieval, Dialogue Systems, Intelligent Tutoring systems, etc.

Workshop Home Page:

Conference Program:

Thursday, April 26, 2007  
(Room: Regency A)

Opening Remarks
"Lexical Influences on the Perception of Sarcasm", Roger Kreuz and Gina Caucci
"Corpus-driven Metaphor Harvesting", Astrid Reining and Birte L¨onneker-Rodman
"Hunting Elusive Metaphors Using Lexical Resources", Saisuresh Krishnakumaran and Xiaojin Zhu
10:30–11:00         Break
30         "Active Learning for the Identification of Nonliteral Language", Julia Birke and Anoop Sarkar
11:30–12:30         Invited Talk:
"The Language of Humor"
                                                                                            Rada Mihalcea:
                   Rada Mihalcea is an Assistant Professor of Computer Science at the
University of North Texas. Her research interests are in lexical
semantics, graph-based algorithms for natural language processing,
minimally supervised natural language learning, and multilingual natural
language processing. She is currently involved in a number of research
projects, including knowledge-based word sense disambiguation,
(non-traditional) methods for building annotated corpora with volunteer
contributions over the Web, graph-based algorithms for text processing,
opinion and sentiment analysis, and computational humour. She has
published a number of articles in books, journals, and proceedings, in
these and related areas. She is the president of the ACL Special Group on
the Lexicon (SIGLEX), and a board member for the ACL Special Group on
Natural Language Learning (SIGNLL). She serves on the editorial boards of
the journal of Computational Linguistics, the journal of Language
Resources and Evaluations, the Journal of Natural Language Engineering,
the Journal of Research on Language and Computation, and the recently
established journal of Interesting Negative Results in Natural Language
Processing and Machine Learning.

Paper Submission:

Submissions should describe original, unpublished work.  Papers are limited to 8 pages. Submissions should use the  style files available at  No author information should be included in the papers since reviewing  will be blind. Papers not conforming to these requirements are subject  to rejection without review. Papers should be submitted via START which is available here:

Important Dates:

Paper submission deadline                        January 18, 2007
Notification of acceptance for papers:       February 22, 2007
Camera ready papers due:                        March 1, 2007
Workshop Date:                                       April 26, 2007


Xiaofei Lu, Penn State University                                 xxl13  AT
Anna Feldman, Montclair State University                    feldmana AT

Program Committee:

Chris Brew, The Ohio State University
Afsaneh Fazly, University of Toronto, Canada
Eileen Fitzpatrick, Montclair State University
Sam Glucksberg, Princeton University
Sid Horton, Northwestern University
Diana Inkpen, University of Ottawa, Canada
Kevin Knight, USC/Information Sciences Institute
Mark Lee, The University of Birmingham, UK
Katja Markert,University of Leeds, UK
Detmar Meurers, The Ohio State University
Rada Mihalcea, University of North Texas
Andrew Ortony, Northwestern University
Wim Peters, University of Sheffield, UK
Vasile Rus, The University of Memphis
Richard Sproat, University of Illinois at Urbana-Champain
Suzanne Stevenson, University of Toronto, Canada
Carlo Strapparava, Istituto per la Ricerca Scientifica e Tecnologica, Trento, Italy