Fully Lexicalising CCGbank with Hat Categories

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.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Matthew Honnibal, James R. Curran
• Keywords: EMNLP 2009, Modifier Categories, Natural Language Processing, Simpler Domain Adaptation, Standard Ccg Analyses