Bevan K. Jones

office 3.48 Informatics Forum 10 Crichton Street Edinburgh, EH8 9AB United Kingdom email b.k.jones (but don't forget to add the sms.ed.ac.uk preceded by the at thinger)

I am a third year PhD student pursuing a joint degree in Informatics at the University of Edinburgh and Computer Science at Macquarie University under advisors Sharon Goldwater and Mark Johnson. Previously, I was at Brown University (Cognitive Science) and San Jose State University (Computer Science).

My research interests center on grammar induction, with a particular focus on how an assumption that language has meaning might influence the kinds of structures learned. Currently, this means I do a lot of work in semantic parsing, attempting to learn a map from natural language sentence to a formal representation of its meaning. I also sometimes work on semantics-based statistical machine translation, and on word-segmentation, with an interest in how simultaneously learning word meanings might impact segmentation. I tend to use Bayesian inference techniques, applying them to models taken from formal language theory such as tree transducers and graph grammars, and prefer machine learning techniques that require little or no supervision.

Publications

David Chiang, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan Jones and Kevin Knight (2013). Parsing graphs with hyperedge replacement grammars. To appear at ACL 2013.

Bevan K. Jones^*, Jacob Andreas^*, Daniel Bauer^*, Karl Moritz Hermann^*, and Kevin Knight (2012). Semantics-Based Machine Translation with Hyperedge Replacement Grammars. In Proceedings of the 24th International Conference on Computational Linguistics (COLING2012). * All four first authors contributed equally. Their order is random.

Bevan K. Jones, Mark Johnson, and Sharon Goldwater (2012). Semantic Parsing with Bayesian Tree Transducers. In Proceedings of the 50th Annual Meeting of the Association of Computational Linguistics (ACL2012). (Data set.)

Bevan K. Jones, Mark Johnson, and Sharon Goldwater (2011). Formalizing Semantic Parsing with Tree Transducers. The 2011 Australasian Language Technology Workshop (ALTA2011).

Benjamin Börschinger, Bevan K. Jones, and Mark Johnson (2011). Reducing Grounded Learning Tasks To Grammatical Inference. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP2011), pages 1416-1425.

Mark Johnson, Katherine Demuth, Michael C. Frank, and Bevan K. Jones (2010). Synergies in learning words and their meanings. Neural Information Processing Systems (NIPS2010).

Bevan K. Jones (2010). A Distributional Account of Covariance Effects and Talker Adaptation in Infant and Adult Phonetic Category Recognition. In Proceedings of the 32nd Annual Meeting of the Cognitive Science Society.

Bevan K. Jones, Mark Johnson, and Michael C. Frank (2010). Learning Words and Their Meanings from Unsegmented Child-directed Speech. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL2010), pp. 501-509.

Talks etc.

Yet another tutorial on Variational Bayes. A talk delivered at the machine learning readings groups at the University of Edinburgh and Macquarie University.

Affiliations (Past & Present)

• Probabilistic Models of Language Group (ProbModels) @ the University of Edinburgh (current)
• Institute for Language, Cognition and Computation (ILCC) @ the University of Edinburgh (current)
• Centre for Language Technology @ Macquarie University (current)
• Natural Language Processing Group, ISI @ the University of Southern California (Summer 2012)
• Brown Lab for Linguistic Information Processing (BLLIP) @ Brown University (between 2008-2010)
• Computational Semantics Lab (Semlab) @ CSLI (between 2006-2008)