Abstract
We introduce an extension to CCG that allows form and function to be represented simultaneously, reducing the proliferation of modifier categories seen in standard CCG analyses. We can then remove the non-combinatory rules CCGbank uses to address this problem, producing a grammar that is fully lexicalised and far less ambiguous. There are intrinsic benefits to full lexicalisation, such as semantic transparency and simpler domain adaptation. The clearest advantage is a 52-88% improvement in parse speeds, which comes with only a small reduction in accuracy. © 2009 ACL and AFNLP.
Cite
CITATION STYLE
Honnibal, M., & Curran, J. R. (2009). Fully lexicalising CCGbank with hat categories. In EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009 (pp. 1212–1221). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1699648.1699667
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
