2007 CoordinateNPDisambigInAGenParsingModel

• (Hogan, 2007) ⇒ Deirdre Hogan. (2007). “Coordinate Noun Phrase Disambiguation in a Generative Parsing Model.” In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL-2007).

Subject Headings: Coordinate Noun Phrase Disambiguation, Noun Phrase Coordination, Coordinating Conjunction.

Notes

• It explores ways to improve Coordinating Conjunction attachment for Syntactic Parsing.

Cited By

~23 http://scholar.google.com/scholar?cites=13444114062689941359

Quotes

Abstract

• In this paper we present methods for improving the disambiguation of noun phrase (NP) coordination within the framework of a lexicalised history-based parsing model. As well as reducing noise in the data, we look at modelling two main sources of information for disambiguation: symmetry in conjunct structure, and the dependency between conjunct lexical heads. Our changes to the baseline model result in an increase in NP coordination dependency f-score from 69.9% to 73.8%, which represents a relative reduction in f-score error of 13%.

1. Introduction

• Coordination disambiguation is a relatively little studied area, yet the correct bracketing of coordination constructions is one of the most difficult problems for natural language parsers. In the Collins parser (Collins, 1999), for example, dependencies involving coordination achieve an f-score as low as 61.8%, by far the worst performance of all dependency types.
• Take the phrase busloads of executives and their wives (taken from the WSJ treebank). The coordinating conjunction (CC) and and the noun phrase their wives could attach to the noun phrase executives, as illustrated in Tree 1, Figure 1. Alternatively, their wives could be incorrectly conjoined to the noun phrase busloads of executives as in Tree 2, Figure 1.
• As with PP attachment, most previous attempts at tackling coordination as a subproblem of parsing have treated it as a separate task to parsing and it is not always obvious how to integrate the methods proposed for disambiguation into existing parsing models. We therefore approach coordination disambiguation, not as a separate task, but from within the framework of a generative parsing model.
• As noun phrase coordination accounts for over 50% of coordination dependency error in our baseline model we focus on NP coordination. Using a model based on the generative parsing model of (Collins, 1999) Model 1, we attempt to improve the ability of the parsing model to make the correct coordination decisions. This is done in the context of parse reranking, where the n-best parses output from Bikel’s parser (Bikel, 2004) are reranked according to a generative history-based model.
• In Section 2 we summarise previous work on coordination disambiguation. There is often a considerable bias toward symmetry in the syntactic structure of two conjuncts and in Section 3 we introduce new parameter classes to allow the model to prefer symmetry in conjunct structure. Section 4 is concerned with modelling the dependency between conjunct head words and begins by looking at how the different handling of coordination in noun phrases and base noun phrases (NPB) affects coordination disambiguation.1 We look at how we might improve the model’s handling of coordinate head-head dependencies by altering the model so that a common

8. Conclusion and Future Work

• This paper outlined a novel method for modelling symmetry in conjunct structure, for modelling the dependency between noun phrase conjunct head words and for incorporating a measure of word similarity in the estimation of a model parameter. We also demonstrated how simple pattern matching can be used to reduce noise in WSJ noun phrase coordination data. Combined, these techniques resulted in a statistically significant improvement in noun phrase coordination accuracy.
• Coordination disambiguation necessitates information from a variety of sources. Another information source important to NP coordinate disambiguation is the dependency between nonnominal modifiers and nouns which cross CCs in NPBs. For example, modelling this type of dependency could help the model learn that the phrase the cats and dogs should be bracketed flat, whereas the phrase the U.S. and Washington should be given structure.

References

---

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2007 CoordinateNPDisambigInAGenParsingModel	Deirdre Hogan			Coordinate Noun Phrase Disambiguation in a Generative Parsing Model			http://acl.ldc.upenn.edu/P/P07/P07-1086.pdf