Eneko Agirre has been awarded with a Google Research Award after its annual open call for proposals on computer science and related topics, including machine learning, speech recognition, natural language processing, and computational neuroscience. Google received 950 proposals covering 55 countries and over 350 universities, and decided to [...]]]>

Measuring the distance between word meanings

Eneko Agirre has been awarded with a Google Research Award after its annual open call for proposals on computer science and related topics, including machine learning, speech recognition, natural language processing, and computational neuroscience. Google received 950 proposals covering 55 countries and over 350 universities, and  decided to fund 151 projects, 10 of then related to Natural Language Processing.

Eneko will expend the $50.000 prize in research on “Learning Interlingual Representations of Words and Concepts.”. In the field of language processing Eneko is one of the 10 researchers awarded by Google. In addition to Eneko, also they have been awarded researchers at universities like Harvard, Berkeley, Edinburgh or Washington.

Eneko Agirre: “The goal of this basic research is the interlingual representation of the meaning of words, ie, knowing automatically when the meanings of two words are related in a language or in different languages. It would be like having a special dictionary to know which words have similar meanings. For example, knowing that the meaning of the word ‘banco‘ in Spanish is similar to ‘caja de ahorros‘ (‘savings bank’) and ‘silla‘ (chair’), depending on the word sense, but not to words like ‘cat‘ or ‘Monday‘. We visualize the distance between different senses of a word, and we can thus represent the senses of ‘banco‘, one that resembles ‘savings bank‘ and the other sense similar to ‘chair‘. Our proposal is able to represent the meanings of words from several languages in the same space, which allows us to know that a sense of ‘banco‘ is similar to ‘bank‘ and ‘kutxa‘ in English and Basque, respectively, and that the other sense of ‘banco’ is similar to ‘chair‘ and ‘aulki‘, but none of the two meanings are similar to ‘cat‘ or ‘katu‘”

Eneko Agirre from Ixa Group has been awarded with a Google Research Award (El Diario Vasco, 2015-03-18)

The methods that support this kind of research are taught in Eneko Agirre’s course in the Master “Language Analysis and Processing” at the Faculty of Informatics of the University of the Basque Country in Donostia.

CONGRATULATIONS Eneko!

http://player.vimeo.com/video/129409827?title=0&byline=0

ACL special interest groups SIGLEX and SIGSEM are organising a joint conference on Lexical and computational semantics: *SEM

Eneko Agirre from the Ixa Group is the general chair in this conference.

The main goal of *SEM is to provide a stable fo of rum for the growing number of NLP researchers working on different [...]]]>

ACL special interest groups SIGLEX and SIGSEM are organising a joint conference on Lexical and computational semantics: *SEM

Eneko Agirre from the Ixa Group is the general chair in this conference.

The main goal of *SEM is to provide a stable fo of rum for the growing number of NLP researchers working on different aspects of semantic processing, which has been scattered over a large array of small workshops and conferences.

The first edition of *SEM will be a two-day conference collocated with the North American Chapter of the Association for Computational Linguistics and Human Language Technologies 2012 conference (NAACL HLT), which will take place in Montreal, Canada.

Important dates:
 30 March 2012, Paper due date
 23 April 2012, Notification of acceptance
  4 May 2012, Camera-ready deadline
7-8 June 2012, Conference

For further information see *SEM