Andreas Vlachos

E-mail: a.vlachos AT cs.ucl.ac.uk.

Short Bio:

Since January 2014 I am a postdoc at Machine Reading group in the UCL Department of Computer Science working with Sebastian Riedel on automatic fact-checking in collaboration with the BBC research and development team. Until then I was at the Natural Language and Information Processing group at the University of Cambridge working with Stephen Clark on semantic parsing in the context of the SpaceBook project. Earlier I was a postdoc in the department of Biostatistics and Medical Informatics at the University of Wisconsin-Madison working with Mark Craven on information extraction from biomedical text. From October 2006 until December 2009, I was a PhD student at the NLIP group of the Computer Laboratory at the University of Cambridge under the supervision of Ted Briscoe, receiving further advice from Zoubin Ghahramani. My thesis explored ways of reducing the annotation cost for biomedical natural language processing and I was funded by a Gates award. Before that, from November 2004 until September 2006, I worked on the project: Integrating Literature, Experiments and Curation in Drosophila Genomics Research.

Full Curriculum Vitae

Research interests

Structured prediction, Semantic parsing, Information extraction, Clustering, Biomedical text mining, Active learning.

News

We are organizing the workshop Dialogue in Motion at EACL 2014, consider submitting/attending.

We are organizing the South England Statistical NLP Meetup, interested researchers are welcome to attend.

New paper: Gubbins, J., Vlachos, A. 2013. Dependency language models for sentence completion, in Proceedings of EMNLP (short papers), Seattle.

New paper: Andreas, J., Vlachos, A., Clark, S. 2013. Semantic Parsing as Machine Translation, in Proceedings of ACL (short papers), Sofia.

Selected publications (all publications or Google scholar)

Vlachos, A. 2012. An investigation of imitation learning algorithms for structured prediction, presented at the 10th European Workshop in Reinforcement Learning, JMLR W&C Proceedings, Vol. 24.

Vlachos, A., Craven, M. 2012. Biomedical event extraction from abstracts and full papers using search-based structured prediction, PDF, HTML in BMC Bioinformatics, Volume 13, Supplement 11.

Vlachos, A. 2011. Evaluating unsupervised learning for natural language processing tasks, in Proceedings of the EMNLP 2011 Workshop on Unsupervised Learning in NLP, Edinburgh.

Van Gael, J., Vlachos, A., Ghahramani, Z. 2009. The infinite HMM for unsupervised PoS tagging, in Proceedings of EMNLP, pages 678-687, Singapore.

Vlachos, A., Korhonen, A., Ghahramani, Z. 2009. Unsupervised and Constrained Dirichlet Process Mixture Models for Verb Clustering, in Proceedings of the workshop on GEometrical Models of Natural Language Semantics at EACL, Athens.

Vlachos, A. 2008. A stopping criterion for active learning, draft, publisher's website, in Computer, Speech and Language, Volume 22, Issue 3, July 2008, pages 295-312.

Software

Search-based Structured Prediction applied to Biomedical Event Extraction (email me for details)

Cost-sensitive classification with Adaptive Regularization of Weights

Other professional activities

Reviewer for: ACL, EMNLP, IJCAI, AAAI, CoNLL, EACL, BioNLP, Machine Learning, Computational Linguistics, Journal of Artificial Intelligence Research, ACM Transactions in Speech and Language Processing, Bioinformatics, Journal of Biomedical Informatics, Computer Speech and Language, Journal of Natural Language Engineering, Transactions of the Association for Computational Linguistics.

Consulting services in applications of natural language processing in various domains, including legal documents and biomedicine.

Non-Academic Interests

World music, photography, argentine tango, basketball, football.