Paper: Robust Conversion of CCG Derivations to Phrase Structure Trees

ACL ID P12-2021
Title Robust Conversion of CCG Derivations to Phrase Structure Trees
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2012
Authors

We propose an improved, bottom-up method for converting CCG derivations into PTB-style phrase structure trees. In contrast with past work (Clark and Curran, 2009), which used simple transductions on category pairs, our ap- proach uses richer transductions attached to single categories. Our conversion preserves more sentences under round-trip conversion (51.1% vs. 39.6%) and is more robust. In par- ticular, unlike past methods, ours does not re- quire ad-hoc rules over non-local features, and so can be easily integrated into a parser.