* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *


LINGUIST List 24.917

Wed Feb 20 2013

Calls: Semantics, Computational Linguistics/France

Editor for this issue: Alison Zaharee <alisonlinguistlist.org>

Date: 20-Feb-2013
From: Nabil Hathout <Nabil.Hathoutuniv-tlse2.fr>
Subject: Current Issues in Distributional Semantics
E-mail this message to a friend

Full Title: Current Issues in Distributional Semantics
Short Title: SemDis 2013

Date: 21-Jun-2013 - 21-Jun-2013
Location: Sables d'Olonne, France
Contact Person: Cécile Fabre
Meeting Email: < click here to access email >
Web Site: http://www.taln2013.org/ateliers/appel-atelier-semantique-distributionnelle/

Linguistic Field(s): Computational Linguistics; Semantics

Call Deadline: 05-Apr-2013

Meeting Description:

SemDis 2013: Current Issues in Distributional Semantics
Workshop associated with the 20th TALN conference
June 21, 2013
Sables d’Olonne, France

In the course of the last two decades, significant progress has been made with regard to the automatic extraction of semantic knowledge from large-scale text corpora. Most work relies on Harris’ distributional hypothesis of meaning, which states that words that appear within the same contexts tend to be semantically related. This principle has inspired a substantial amount of research - mainly for English but also for other languages - and several survey articles have recently helped to consolidate the concepts and procedures used for distributional computations (Sahlgren, 2006; Turney and Pantel, 2010; Baroni and Lenci, 2010). In recent years, the distributional semantic approach has benefited from the availability of massive amounts of textual data and increased computational power, allowing for the application of these methods on a large scale. Still, a number of research topics remain open, with regard to the construction, the evaluation and the application of the semantic information that is induced by these methods.

Regarding the construction of distributional semantic resources, the nature of the corpus is a key issue, and its impact on the results requires further investigation. Today’s trend is to use massive corpora, moving away from Harris’ initial hypothesis which was based on the analysis of small, well-defined, and specialized corpora. A second important issue relates to the modeling of semantic compositionality within a distributional framework, such that not only individual words but also larger phrases can be taken into account (Mitchell et Lapata, 2008; Baroni & Zamparelli, 2010; Grefenstette & Sadrzadeh, 2011).

Relations between words tend to be very diverse. Regarding the evaluation of distributional models, we need a better understanding of the nature of semantic relations (synonymous, associative, analogous, etc.) induced by these models, and the impact of the distributional parameters on the induced relations (Sahlgren, 2006; Peirsman & Geeraerts, 2009). Secondly, large corpora generate resources so large that they are very difficult to explore and grasp. The manipulation of graphs within visualization systems suitable for their exploration can improve our knowledge on their content and structure.

Finally, distributional resources are useful for a large number of applications such as information retrieval, summarization, text segmentation, etc. Distributional features have been incorporated into a wide range of NLP tasks, such as named entity classification and paraphrasing (Kotlerman et al. 2010; Jonnalagadda et al. 2012). Linguists could equally benefit from these distributional approaches, as they provide a means to conduct large-scale studies of the semantic relations that may be discovered from large corpora.

Call for Papers:

We welcome papers that focus on any of the aforementioned topics, and in particular:

- The construction of distributional semantic resources
- The nature of corpora within distributional semantics
- Compositionality within a distributional framework
- The use of distributional resources for linguistic analysis
- The induction of specific semantic relations
- The use of distributional methods within NLP tasks
- Optimization techniques for distributional computations
- Visualization techniques for word spaces

Important Dates:

Paper submission: April 5, 2013
Acceptance notification: April 19, 2013
Final version: May 2, 2013

Papers should be submitted in PDF format through EasyChair:

https://www.easychair.org/conferences/?conf=semdis2013

Papers should be written in French or English, should count between 12 and 14 pages, and need to conform to the TALN style sheet, which is available on the conference website (http://www.taln2013.org/soumettre/). The selection criteria are those defined for the main conference.

Organizing Committee:

Cécile Fabre, CLLE, Toulouse, France
Nabil Hathout, CLLE, Toulouse, France
Philippe Muller, IRIT, Toulouse, France
Tim Van de Cruys, IRIT, Toulouse, France

Program Committee:

Stergos Afantenos, IRIT, Toulouse, France
Yves Bestgen, UCL/CECL, Louvain-La-Neuve, Belgium
Marie Candito, ALPAGE, Paris, France
Eric de la Clergerie, ALPAGE, Paris, France
Cécile Fabre, CLLE, Toulouse, France
Olivier Ferret, CEA-LIST, Fontenay-aux-Roses, France
Nabil Hathout, CLLE, Toulouse, France
Philippe Muller, IRIT, Toulouse, France
Adeline Nazarenko, LIPN, Paris, France
Pascale Sébillot, IRISA, Rennes, France
Ludovic Tanguy, CLLE, Toulouse, France
Agnès Tutin, LIDILEM, Grenoble, France
Tim Van de Cruys, IRIT, Toulouse, France
Virginie Zampa, LIDILEM, Grenoble, France

Contact: Cécile Fabre (cecile.fabreuniv-tlse2.fr) and Tim Van de Cruys (tim.vandecruysirit.fr)



Read more issues|LINGUIST home page|Top of issue



Page Updated: 20-Feb-2013

Supported in part by the National Science Foundation       About LINGUIST    |   Contact Us       ILIT Logo
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed on its pages, it cannot vouch for their contents.