tailieunhanh - Báo cáo khoa học: "Improving Parsing and PP attachment Performance with Sense Information"

To date, parsers have made limited use of semantic information, but there is evidence to suggest that semantic features can enhance parse disambiguation. This paper shows that semantic classes help to obtain significant improvement in both parsing and PP attachment tasks. We devise a gold-standard sense- and parse tree-annotated dataset based on the intersection of the Penn Treebank and SemCor, and experiment with different approaches to both semantic representation and disambiguation. For the Bikel parser, we achieved a maximal error reduction rate over the baseline parser of and , for parsing and PP-attachment respectively, using an unsupervised WSD. | Improving Parsing and PP attachment Performance with Sense Information Eneko Agirre IXA NLP Group University of the Basque Country Donostia Basque Country Timothy Baldwin LT Group CSSE University of Melbourne Victoria 3010 Australia tim@ David Martinez LT Group CSSE University of Melbourne Victoria 3010 Australia davidm@ Abstract To date parsers have made limited use of semantic information but there is evidence to suggest that semantic features can enhance parse disambiguation. This paper shows that semantic classes help to obtain significant improvement in both parsing and PP attachment tasks. We devise a gold-standard sense- and parse tree-annotated dataset based on the intersection of the Penn Treebank and SemCor and experiment with different approaches to both semantic representation and disambiguation. For the Bikel parser we achieved a maximal error reduction rate over the baseline parser of and for parsing and PP-attachment respectively using an unsupervised WSD strategy. This demonstrates that word sense information can indeed enhance the performance of syntactic disambiguation. 1 Introduction Traditionally parse disambiguation has relied on structural features extracted from syntactic parse trees and made only limited use of semantic information. There is both empirical evidence and linguistic intuition to indicate that semantic features can enhance parse disambiguation performance however. For example a number of different parsers have been shown to benefit from lexicalisa-tion that is the conditioning of structural features on the lexical head of the given constituent Mager-man 1995 Collins 1996 Charniak 1997 Char-niak 2000 Collins 2003 . As an example of lexi-calisation we may observe in our training data that knife often occurs as the manner adjunct of open in prepositional phrases headed by with . open with a knife which would provide strong evidence for with a knife attaching to open