I am a member of the Language in the Information Society (LYS) research group of the University of A Coruña. LYS is an interdisciplinary research group formed by professors and researchers from the fields of Computer Science and Linguistics who have long been working in the area known as Computational Linguistics, Natural Language Processing and Language Engineering.

I was also a member of the founding committee of the Spanish Society for Information Retrieval (SERI) until 2014.

My research interests are in the application of Natural Language Processing techniques to improve Text Mining systems, including Information Retrieval/Extraction and Sentiment Analysis tasks. More specifically, my research work includes:
  • lexical analysis (e.g. tokenization);
  • morphological analysis;
  • (shallow) parsing;
  • information retrieval;
  • cross-language information retrieval;
  • character n-gram level processing;
  • machine translation;
  • microtext processing (e.g. tweets);
  • Spanish and Galician language NLP.

My (dear old) PhD. Thesis

I defended my PhD thesis in the Department of Computer Science of the University of A Coruña in 2005. My dissertation was about the Application of Natural Language Processing techniques in Spanish Information Retrieval. For this work I was awarded a PhD degree with highest honors (sobresaliente cum laude & premio extraordinario) and European Doctorate mention. You can find it here.

Research Publications

For your convenience, I have moved them into Publications.

Projects & Networks

Next, I list the projects and research networks I have been involved in throughout my career:

  1. Language technologies for opinion analysis in social networks: From text to microtext
    Funded by Ministry of Economy and Competitiveness (FFI2014-51978-C2-2-R) from 2015 to 2017.
  2. ESF Research Network: Evaluating Information Access Systems (ELIAS) <as local co-ordinator>
    Funded by European Science Foundation (ESF) through its Research Networking Programmes from 2011 to 2016.
  3. Galician Network for Language Processing and Information Retrieval (RedPLIR)
    Funded by Xunta de Galicia from 2006 to 2010 (2006/23 and 2009/061), 2012 to 2013 (CN 2012/319) and 2014 to 2015 (CN2014/034).
  4. Spanish Network on Multilingual and Multimodal Information Processing (TIMM) <from 2012>
    Funded by Ministry of Economy and Competitiveness (TIN2011-13070-E) from 2012 to 2014.
  5. Grant for consolidating and structuring competitive research units: Groups with potential for growth
    Funded by Xunta de Galicia (CN2012/008) from 2012 to 2014.
  6. Text analysis and information retrieval for opinion mining: Sentence analysis and relation extraction
    Funded by Ministry of Science and Innovation (TIN2010-18552-C03-02) from 2011 to 2014.
  7. Galician network on linguistic resources for a knowledge society (ReLiSCo)
    Funded by Xunta de Galicia (CN2011/006) from 2011 to 2012.
  8. Grant for consolidating and structuring competitive research units
    Funded by Xunta de Galicia in 2007 (INCITE07PXI104119ES), 2008 (INCITE08E1R104022ES), 2009 (INCITE09E2R104007ES) and 2010 (IN845B-2010/101).
  9. Galician Network for Corpus Linguistics (Rede_Corpus)
    Funded by Xunta de Galicia from 2009 to 2010.
  10. Improving news retrieval and financial information access: Text retrieval on document databases of news agencies
    Funded by Xunta de Galicia (PGIDIT07SIN005206PR) from 2007 to 2010.
  11. Extraction of multilingual economic information (ETIMON)
    Funded by Xunta de Galicia (PGIDIT05PXIC30501PN) from 2005 to 2008.
  12. Robust parsing for question answering
    Funded by Ministry of Education and Science (HUM2007-66607-C04-03) from 2007 to 2010.
  13. Information retrieval for question-answering in economic texts
    Funded by Ministry of Science and Technology (TIN2004-07246-C03-02) from 2004 to 2007.
  14. Generating, extracting and structuring legal information by means of artificial intelligence techniques <as principal investigator>
    Funded by Telémaco with a grant of Xunta de Galicia (PGIDIT05SIN044E) from 2005 to 2006.
  15. Application of Artificial Intelligence for extracting cognitive and qualitative information from financial markets
    Funded by 3.14 Financial Contents from 2002 to 2005 with a grant of Xunta de Galicia (PGIDIT02SIN01E).
  16. Enabling Eclipse to Visually Impaired People
    Funded by IBM (Eclipse Innovation Grants) in 2004.
  17. Tabular analyzers for natural languages 2
    Funded by Spanish (HF2002-0081) and French Governments from 2003 to 2004.
  18. Interactive evaluation of relevance in automatic information retrieval environments
    Funded by Xunta de Galicia (PGIDIT02PXIB30501PR) from 2002 to 2004.
  19. Application of Language Engineering to Collaborative Systems and Desktop Publishing
    Funded by University of A Coruña in 2003.
  20. Robust Parsing of Portuguese, Galician and Spanish.
    Funded by Spanish (HP2001-0044) and Portuguese Governments from 2002 to 2003.
  21. Galician Network of Parallel, Distributed, and GRID Computing Technologies
    Funded by Xunta de Galicia (PGIDT-PR426A-02/4) from 2002 to 2003.
  22. Extracting information from stock exchange news to assess market attitude
    Funded by University of A Coruña in 2002.
  23. Natural Language Information Retrieval Systems for Cognitive Evaluations of Information.
    Funded by FEUGA from Oct. 2001 to Feb. 2002 through a Smart Tulip project within the Innovation program of the European Union.
  24. Cluster of 30 nodes with architecture x86.
    Funded by Xunta de Galicia (Infraestructure Grant PGIDT01PXI0501IF) in 2001.
  25. Information Retrieval and Extraction Applying Linguistic Knowledge <as researcher, 2001>
    Funded by FEDER of European Union (1FD97-0047-C04-02) from Oct. 1998 to Sep. 2001.
  26. Automatic Analysis of Verbal Constructions in Spanish <as assistant scholar, 1999>
    Funded by Xunta de Galicia (XUGA 20402B97) from 1997 to 1999.

Personal Research Initiatives

  • Text Mining on Egyptian Hieroglyphic texts: I have participated as advisor in the development of HieroFinder, a text retrieval system designed to operate on Middle Egyptian hieroglyphic texts. I expect to continue working on this non-mainstream field in the mid-term. In the meantime, HieroFinder homepage can be found here.
  • Application of NLP to computer games accesibility: As many other computer scientist of our generation we, the youngest members of our research group, have grown playing computer games. Moreover, we knew about the limitations of visually-impaired people for playing computer games. The result of all this has been to propose a small personal initiative we have named TOP PLAYER LYS. Its objective is the development of computer games accessible to visually-impaired users by applying NLP techniques. These games are developed within the framework of final-year projects for Computer Science Degree students. So far we have focused on roguelike-genre games. You can find more information about it in this site [in English] [in Spanish].

Other Research Activities