Joint A* Syntactic and Semantic Parsing for CCG

Add to your list(s) Download to your calendar using vCal

• Mike Lewis, University of Washington
• Friday 25 September 2015, 12:00-13:00
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Tamara Polajnar.

Joint models of syntactic and semantic parsing have the potential to improve performance on both tasks—but to date, the best results have been achieved with pipelines. I will introduce a new joint model using CCG , which is motivated by the close link between CCG syntax and semantics. Semantic roles are recovered by labelling the deep dependency structures produced by the grammar. Furthermore, I will show how to exploit CCG ’s strong lexicalization to introduce a new A∗ parsing algorithm—-which finds optimal parses over 5 times faster than CKY parsing. Our joint model is the first to substantially improve both syntactic and semantic accuracy over a comparable pipeline, and also achieves state-of-the-art results for a non-ensemble semantic role labelling model.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Big Data
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Chris Davis' list
• Computer Laboratory talks
• FW26, Computer Laboratory
• Guy Emerson's list
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• rp587

Note that ex-directory lists are not shown.