NAACL-2009 Workshop on Unsupervised and Minimally Supervised Learning of Lexical Semantics

June 5, 2009
Boulder, Colorado, USA

Announcements


  • - Workshop presentations are being made available here
  • - Workshop Proceedings are available in ACL Anthology
  • - Workshop poster has been published.
  • - Workshop schedule has been announced.
  • - SIGLEX Endorsement We are very pleased to announce that the workshop has been endorsed by SIGLEX. SIGLEX, a Special Interest Group on the Lexicon of the Association for Computational Linguistics, provides an umbrella for research interests on lexical issues ranging from lexicography and the use of online dictionaries to computational lexical semantics. SIGLEX is also the umbrella organization for the SemEval semantic evaluations and the SENSEVAL word-sense evaluation exercises.





Lexical semantics (the semantics of words) has become an important part of Natural Language Processing due to its practical application in a number of areas such as machine translation, web & enterprise search, ontology learning etc.

This fact can be observed by looking at the increasing interest in the field of learning of lexical semantics e.g. the last Semantic Evaluation Workshop (SemEval-2007) consisted of 18 tasks ranging from the traditional Word Sense Disambiguation (WSD)  task to the most recent of Word Sense Induction (WSI), web people search, metonymy resolution and others.


Given the wide variety of applications exploiting lexical semantics it is significant to focus on methods and techniques, which can overcome the "Knowledge Acquisition Bottleneck" and deal with the cost-prohibitive, error-prone and labor-intensive processes of creating hand-tagged training data.


The scope of this workshop is limited to topics that cover unsupervised and minimally supervised methods relevant to learning of lexical semantics. We particularly invite novel submissions which focus on issues related to feature selection for specific tasks such as WSD or WSI or multi-word items,  parameter tunning and unsupervised parameter estimation, learning and evaluating hyponymy relations, graph-based methods for learning lexical semantics, learning of bilingual lexicons. Other relevant topics are welcome.

The call for papers provides a more extensive list of topics.


Organizers:

Suresh Manandhar,
Department of Computer Science, University of York, UK, suresh@cs.york.ac.uk
Ioannis Klapaftis,  Department of Computer Science, University of York, UK, giannis@cs.york.ac.uk