Third Workshop on Metaphor in Natural Language Processing

Страна: США

Город: Denver

Тезисы до: 04.03.2015

Даты: 05.06.15 — 05.06.15

Область наук: Филологические;

Е-мейл Оргкомитета:

Организаторы: University of California, Educational Testing Service, University of California


Metaphor processing is a rapidly growing area in NLP.  Characteristic to all areas of human activity (from poetic to ordinary to scientific) and, thus, to all types of discourse, metaphor becomes an important problem for NLP systems. Its ubiquity in language has been established in a number of corpus studies and the role it plays in human reasoning has been confirmed in psychological experiments. This makes metaphor an important research area for computational and cognitive linguistics, and its automatic identification and interpretation indispensable for any semantics-oriented NLP application.

The work on metaphor in NLP and AI started in the 1980s, providing us with a wealth of ideas on the structure and mechanisms of the phenomenon. The last decade witnessed a technological leap in natural language computation, whereby manually crafted rules gradually give way to more robust corpus-based statistical methods. This is also the case for metaphor research. In the recent years, the problem of metaphor modeling has been steadily gaining interest within the NLP community, with a growing number of approaches exploiting statistical techniques. Compared to more traditional approaches based on hand-coded knowledge, these more recent methods tend to have a wider coverage, as well as be more efficient, accurate and robust. However, even the statistical metaphor processing approaches so far often focused on a limited domain or a subset of phenomena. At the same time, recent work on computational lexical semantics and lexical acquisition techniques, as well as a wide range of NLP methods applying machine learning to open-domain semantic tasks, open many new avenues for creation of large-scale robust tools for recognition and interpretation of metaphor.

The aim of the workshop is to discuss issues in computational modeling of metaphor and methodologies for system evaluation, as well as to place the phenomenon within the wider scope of the work done by the NLP community and relate it to the most recent research trends. The main focus of the workshop will be on computational modeling of metaphor using state-of-the-art NLP techniques. However, papers on cognitive, linguistic, and applied aspects of metaphor are also of interest, provided that they are presented within a computational, a formal or a quantitative framework. We also encourage descriptions of proposals and data sets for shared tasks on metaphor processing. 

The workshop invites both full papers and short papers for either oral or poster presentation.

Topics will include, but will not be limited to, the following:

  Identification and interpretation of different levels and types of metaphor         Conceptual and linguistic metaphor         Lexical metaphor         Multiword metaphorical expressions         Extended metaphor / metaphor in discourse         Conventional / novel / deliberate metaphor

  Metaphor processing systems that incorporate state-of-the-art NLP methods 

        Statistical metaphor processing         The use of lexical resources for metaphor processing         The use of corpora for metaphor processing         Distributional methods for metaphor processing         Supervised and unsupervised learning for metaphor processing         Identification of conceptual and linguistic metaphor         Identification and interpretation of lexical metaphor / multiword metaphor / extended metaphor         Lexical metaphor interpretation vs. word sense disambiguation         Metaphor paraphrasing         Generation of metaphorical expressions         Metaphor translation and multilingual metaphor processing

   Metaphor resources and evaluation

        Metaphor annotation in corpora         Metaphor in lexical resources         Reliability of metaphor annotation         Datasets for evaluation of metaphor processing tools         Metaphor evaluation methodologies and frameworks         Descriptions of proposals for shared tasks on metaphor processing

   Metaphor processing for external NLP applications

        Metaphor in machine translation          Metaphor in opinion mining         Metaphor in information retrieval         Metaphor in educational applications         Metaphor in dialog systems         Metaphor in open-domain and domain-specific applications

  Metaphor and cognition 

        Computational approaches to metaphor inspired by cognitive evidence         Cognitive models of metaphor processing by the human brain         Models of metaphor across languages and cultures

   Metaphor interaction with other phenomena (within a computational, formal or quantitative framework)

        Metaphor and compositionality         Metaphor and abstractness / concreteness         Metaphor and persuasion         Metaphor and argumentation         Metaphor and metonymy         Metaphor and grammar      Metaphor and Sentiment         The use of metaphorical language to express stronger sentiment/evaluation         Sentiment processing systems that make use of metaphor as a feature         Sentiment processing systems that detect affect associated with metaphorical expressions        Metaphor and Social media         Processing of metaphoral language in blogging, twitter and other social media         How metaphorial language helps shape communication in social media         The influence of metaphor on social dynamics

Веб-сайт конференции: