My research interests include the following:
- Processing
of
Basque
- Combinations
of deep learning and knowledge-based techniques to learn representations
- Lexical
semantics and compositionality, including
relatedness/similarity among concepts, words, phrases and
sentences, as well as closely related Word Sense
Disambiguation and Named Entity Disambiguation
- Multi- and cross-lingual
semantic resources and their semi-automatic acquisition
- Domain adaptation of NLP tools
and resources
- Applications
of
semantic processing to IR, CLIR, QA and MT
Blog in Basque
and English
about my research group:
IXA NLP group.
You can check my list
of projects
and publications
(also in Google
Scholar) including a book on WSD:
|
Word
Sense Disambiguation: Algorithms and
applications (Springer)
Agirre, Eneko; Edmonds, Philip (Eds.) 2006 and 2007.
|
Recent
talks, awards and projects:
- Honourable mention paper award (top 1%) at EMNLP (details), 2020
- Outstanding Paper award (top 2%) at COLING (details), 2020
- Member of government evaluation body (ANEP area TIC), 2020
- Keynote talk on "Deploying Conversational Question Answering systems in new domains" (video) at the
EXPO DAQA workshop (IBM), NeurIPS conference, Dec. 2020
- Won a prize in White House promoted challenge related to COVID-19
(details) 2020
- Recipient of a 2019
Google Faculty Research Award for research on conversational QA (this is the third time)
- Part of the team which won the 2020 OpenCLIR Text Track Challenge
(organised by NIST and IARPA)
-
Keynote talk on "Cross-linguality and machine translation without bilingual data" (video) at the Applied Machine Learning Days (AMLD), EPFL, Laussane, Switzerland, Jan. 2020
-
Nomination for the best paper award at the Conference of the Association for Computational Linguistics, July, 2019.
-
Keynote talk at the Conference in Computational Collective Intelligence, Hendaye, Basque Country, September, 2019
-
Keynote talk at the conference of the Spanish NLP society (SEPLN), Bilbao, Basque Country, September, 2019
-
Invited talk at BCBL, Donostia, Basque Country, November, 2019
-
Invited talk at the Catholic University of Leuven, Belgium, May, 2019
-
Prestigious BBVA project, 2019-2021
- Three day crash course on
Deep Learning and NLP in English, UPV/EHU, San Sebastian, July 2019
- Recipient of a 2018
Best PhD thesis award to his PhD student Aitor Gonzalez-Agirre by the Spanish NLP society (SEPLN), September, 2019
- Recipient of a 2018
Google Faculty Research Award
- Invited tutorial on
Deep Learning for NLP, organized by the Italian Association of Computational Linguistics, Pavia, May 2019 (slides)
- Invited
talk on "Cross-linguality and machine translation without bilingual data" at FBK, Trento, May 2019 (slides)
- Best paper award at CoNLL 2018
- Course on
Deep Learning and NLP in Spanish, Universidad Carlos III, Madrid
- Invited talk
at 14th China Workshop on Machine Translation (CWMT), Wuyishan, China, October 2018
- Keynote
talk on "Cross-linguality and machine translation without bilingual data" at 3rd Swiss Text Analytics Conference, Winterthur June 2018 (video)
- Invited
talk on Cross-linguality and machine translation with monolingual data at BBVA Data and Analytics, Madrid 2018
- ICLR 2018 paper on Unsupervised Neural Machine Translation featured at Science magazine (Nov. 2017)
- PI of European project on learning to interact with humans
(LIHLITH 2018-2020)
- Invited
talk at the Institute for Natural Language Processing, Stuttgart 2018
- Visiting academic, CILVR lab at NYU
(Fall 2016)
Recent
activities:
PhD
students and alumni:
- Ander Salaberria (2020-)
- Jon Ander
Campos (2019-)
- Andoni
Azpeitia (2017-)
- Mikel
Artetxe (2016-)
- Iņigo
Lopez-Gazpio (2018, assistant professor at Deusto University)
-
Josu Goikoetxea (2017, assistant professor at University of the Basque Country)
-
Ander Barrena (2017, senior researcher at University of the Basque Country)
-
Aitor Gonzalez-Agirre (2017, senior researcher at BSC)
- Xabier
Saralegi (2017, senior researcher at Elhuyar Foundation)
- Nicolai
Erbs (2015,
Data Analyst at WordCloud Gmbh)
- Ander
Intxaurrondo (2015, senior
researcher at BSC)
- Aitziber
Atutxa (2014,
Associate Professor at the University of
the Basque Country)
- Arantxa
Otegi (2012,
senior researcher
at University of the Basque Country)
- Beņat
Zapirain (2011,
at
Department of Education, Basque Government)
- Oier
Lopez de Lacalle (2009,
senior
researcher at University of the Basque Country)
- Elisabete
Pociello (2008,
senior
researcher at Elhuyar Foundation)
- Mikel
Lersundi (2006,
Associate
Professor at the University of the Basque Country)
- David
Martinez (2004,
senior
researcher at IBM Watson)
Visiting
students and professors:
- 2020
Ahmed Sabir (from Universitat Politecnica de Catalunya in Barcelona)
- 2020
Jiawei Zhao (from Massey University in Auckland)
- 2019
Ivana Kvapilikova (from Charles University in Prague)
- 2018
Andrea Amelio Ravelli (from University of Florence)
- 2015
Roland Roller (from University of Sheffield)
- 2015
Marten Postma (from VUA)
- 2010
Wauter Bosma (from VUA)
- 2008
Pierpaolo Basile (from University of Bari)
- 2007
Mark Stevenson (from University of Sheffield)
- 2007
Alfio Gliozzo (from FBK, Trento)
Resources:
Past
activities, projects, awards, resources:
- Invited
talk at Annual
Meeting of the LCT master program (2016)
- Invited
speaker at the Internationa Conference on the
Computational Processing of Portuguese (PROPOR2016)
- Recipient of a 2015 Google
Research Award
- Guest
speaker at the Escuela de Otoņo, Mexico 2016
- Invited
talk at the UKP group at Darmstadt in 2015
- Invited talk at the Workshop
on
Semantic Annotation and Processing 2014
- European project on
multimodal processing (Muster
2015-2018)
- European project on
machine reading (Readers
2013-2016).
- European project on
semantics to improve Machine Translation (QTLeap
2013-2016).
- Double master
program on language processing awarded Erasmus Mundus
status (2014-).
- European project on
narratives for news (Newsreader
2013-2015).
- European project on
deploying semantic enrichment on digital libraries (LoCloud
2012-2014)
- Invited
to the Google Workshop on Natural Language Understanding at
Google Zurich 2014.
- Invited talk at JSSP
2013 (Understanding
text
with knowledge bases and random walks and STS
-
with Mona Diab).
- Invited talk at Mavir
Doctoral Consortium 2013 (slides)
- My research group was
awarded the Abbadia
2013
prize for advancing the normalization of Basque.
- Arantza Otegi (PhD
student) wins Koldo
Mitxelena
2013 prize for best technical PhD in Basque
- Local PI of CHIST-ERA
project READERS
on Machine Reading (2013-2015)
- Helped build Google's
dictionary
for entities and ideas
- Local PI of FP7
Project PATHS on
access to Cultural Heritage (2011-2013)
- Scholarpedia article
about Word
Sense
Disambiguation
- Co-organizer of a SemEval
2012 task on Semantic Textual Similarity
- General chair and
co-founder (with Mona Diab and Johan Bos) of a new conference
on semantics *SEM
2012
- Invited course on the
winter school on language and specch technologies WSLST
2012
- Area chair on Ontology
and Lexicon for ACL 2012
- Tutorial chair for EACL 2012
- Co-organizer of TPDL
2012 workshop on Supporting
Users' Exploration of Digital Libraries
- Invited talk at the Mavir
meeting, Madrid, 2011 (slides)
- Seminar
at SRI, Menlo Park, 2011
- Visiting associate
professor, Stanford NLP
group (Summer 2011)
- PI of the co-ordinated
KNOW2 project (intranet)
(2010-2012)
- Participant in the Europeana
version
1.0 project (euskaraz)
(2010-2012)
- Participant in EC FP7
Project KYOTO (intranet)
(2008-2011)
- Area chair for
semantics in EMNLP 2010
- Area chair for
semantics in ACL-IJCNLP 2010
- Secretary of SIGLEX
(2007-2010)
- Panelist on the future
of Semeval, ACL 2010, Uppsala, Sweden
- 5-day Seminar on “Semantic
processing
of text”, 2010, Bari, Italy (Links)
- Organizer
of SemEval
2010 task WSD
on a Specific Domain
- Co-editor
of LRE journal special
issue
on Computational Semantic Analysis of Language (2010)
- Visiting associate
professor, Stanford NLP group, 2009
- Invited talk at
Google, Mountain View, 2009 (slides)
- Organizer
of the Robust WSD
task @ CLEF 2009
- Area
co-chair for semantics in ACL-IJCNLP
2009
- Co-chair
of HLT-NAACL workshop on Semantic Evaluations (SEW-2009)
- Area chair for word
senses in EMNLP
2008.
- Organizer of CLEF 2008
tasks on QAWSD
and CLIRWSD.
- Co-chair of SemEval-2007
(formerly Senseval).
- Coordination of two
tasks in SemEval-2007: WSD/CLIR
interaction and WS
induction.
- Australian HCSNet
visiting scholar in 2007. Check the seminars
and video.
- PI of the co-ordinated
KNOW project (intranet)
funded by the Education Ministry (2007-2009)
- WSD
demo for Basque
- ML
features for all content words with more than
10 occurrences in SemCor 1.6. More details here.
The senses can be easily mapped to other WN versions here.
- Lexico-semantic
relations for Basque headwords.
- GWN tutorial on Automatic
WordNet construction (slides)
- Conceptual Density in Perl (tar file)
- Project related data: CESS-ECE
project, MEANING
project
A
cartoon (by Olariaga in berria.eus)
in Basque about WSD : "- Where the heck is ...? - What?
Does not the tree allow you to see the baso"
Where baso
is ambiguous between glass and wood

by
Olariaga in berria.eus
|
|