Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info


E-mail this page

Conference Information



Full Title: 13th Workshop on Multiword Expressions

      
Short Title: MWE 2017
Location: Valencia, Spain
Start Date: 03-Apr-2017 - 04-Apr-2017
Contact: Stella Markantonatou
Meeting Email: click here to access email
Meeting URL: http://multiword.sf.net/mwe2017
Meeting Description: Natural languages express complex human thoughts and ideas in many ways. They may exploit compositionality, i.e. concatenating simplex elements of language to yield a more complex meaning that can be computed from the meaning of the original parts and the way they are combined. However, non-compositional phrases are also frequent in human languages. These complex phrases, often called multiword expressions (MWEs), may be decomposed into single meaningful units, but the meaning of the whole phrase cannot (or can only partially) be computed from the meaning of its parts. MWEs display lexical, syntactic, semantic, pragmatic and/or statistical idiosyncrasies (Baldwin & Kim 2010). MWEs encompass idiomatic constructions and closely related linguistic constructs such as light verb constructions, rhetorical figures and institutionalized phrases/collocations (Sag et al. 2002). They pose problems for linguistic processing, especially in language learning and natural language processing (NLP), for instance, in machine translation, syntactic and semantic parsing, just to name a few applications.

Researchers from several disciplines such as computer science, linguistics and psychology have been jointly working on MWE modeling and processing. Designing guidelines for the annotation of MWEs in corpora and treebanks has been undertaken in various languages and linguistic frameworks (Rosén et al. 2015). Lexical resources with MWEs in dozens of languages have been/are developed (Losnegaard et al. 2016). Many papers describe methods to discover new MWEs in texts, applying a wide variety of tools and techniques such as association measures, distributional methods and machine learning. Interactions of MWE processing with deeper levels of linguistic analysis, notably parsing and semantic processing, are investigated (e.g. in SEMEVAL 2016 task 10 - DiMSUM). Special issues on MWEs have been published by leading journals (CSL in 2005, LR&E in 2010, ACM TSLP in 2013). Several funded projects on MWEs indicate the importance of the field within the NLP community. The EU H2020 program currently supports the COST Action PARSEME (2013-2017), that addresses the role of MWEs in parsing and gathers 200+ researchers from 33 countries covering 30 languages. PARSEME has inspired several national spin-off projects.

Many of these advances are described and published in the annual MWE workshop that attracts the attention of an ever-growing community working on a variety of languages and linguistic phenomena. The workshop has been held since 2001 in conjunction with major computational linguistics conferences (ACL, COLING, LREC, EACL). It represents an important venue for the community to interact, share resources and tools, and collaborate on efforts for advancing the computational treatment of MWEs.

Special Track: Shared task on automatic identification of verbal MWEs

This year, there will be an extension to the traditional workshop: a special track for shared task papers. The shared task will compare and evaluate systems for the automatic identification of verbal MWEs in sentences. Participants will have the opportunity to submit shared task system description papers and present their approach and results - see the separate call for the shared task: http://multiword.sourceforge.net/sharedtask2017/ .

A volume with selected papers from the workshop is planned within the book series Phraseology and MultiWord Expressions of Language Science Press.
Linguistic Subfield: Computational Linguistics; Lexicography; Semantics; Syntax; Text/Corpus Linguistics
LL Issue: 28.269


Back
Calls and Conferences main page