We do research on different aspects of Natural Language Processing such as

  • Computational Lexicology,
  • Language-oriented Machine Learning,
  • Knowledge Extraction,
  • Multilingual Natural Language Generation,
  • Text simplification,
  • Summarization, and
  • Speech Prosody.

Special focus is put on application-oriented NLP and synergies with other fields of Computer Science and Artificial Intelligence.

The TALN group, Tractament Automàtic del Llenguatge Natural (Natural Language Processing) is part of the Department of Information and Communication Technologies, at Pompeu Fabra University, in Barcelona.

News News


José Camacho-Collados talk on semantic representations

José Camacho-Collados talk on semantic representations

The talk will take place in room 55.410 at 12:30h. Please find below title, bio and abstract of the presentation.


The talk will take place in room 55.410 at 12:30h. Please find below title, bio and abstract of the presentation.

Title: Semantic Representations of Word Senses, Concepts and Entities and their Applications

Abstract: A considerable amount of research has lately been conducted on developing neural architectures for learning vector representations of word forms (i.e., word embeddings). However, they have clear limitations when it comes to deep language understanding as they conflate different meanings of a word into a single representation and consequently are unable to accurately model semantics of individual word senses. In order to deal with these issues, a field of research has tried to address the issue with word representations by breaking them into those of their individual meanings. In this presentation I will give an overview of this kind of representations with a special emphasis on NASARI, our recently developed multilingual representation of concepts and entities. Finally, I will briefly present some of its most successful applications to date, namely semantic similarity, word sense disambiguation, sense clustering and domain adaptation.

Bio: Jose Camacho Collados is a Google Doctoral Fellow and PhD student at Sapienza University of Rome (http://wwwusers.di.uniroma1.it/~collados). His research focuses on Natural Language Processing and on the area of lexical semantics in particular. He has developed NASARI, a novel semantic vector representation for concepts and named entities (NAACL 2015, http://lcl.uniroma1.it/nasari/). This work was later extended to a fully multilingual approach (ACL 2015) and then refined and applied into various NLP tasks (AIJ 2016). Jose co-presented a tutorial on “Semantic Representations of Word Senses and Concepts” at ACL 2016 and will co-organize a SemEval 2017 task on multilingual and cross-lingual semantic similarity. His background education includes an Erasmus Mundus Master in Natural Language Processing and Human Language Technology and a 5-year BSc degree in Mathematics.


Department of Information and Communication Technologies

Tànger building (Comunication-Poblenou campus)
Tànger, 122-140
08018 Barcelona

+34 93.542.2241

taln.dtic at upf.edu