Verb Phrase Ellipsis detection using Automatically Parsed Text

Verb Phrase Ellipsis detection using Automatically Parsed Text Leif Arda Nielsen Department of Computer Science King’s College London nielsen@dcs.kcl.ac.uk Abstract This paper describes a Verb Phrase Ellipsis (VPE) detection system, built for robust- ness, accuracy and domain independence. The system is corpus-based, and uses a va- riety of machine learning techniques on free text that has been automatically parsed us- ing two different parsers. Tested on a mixed corpus comprising a range of genres, the sys- tem achieves a 72% F1-score. It is designed as the first stage of a complete VPE resolu- tion system that is input free text, detects VPEs, and proceeds to find the antecedents and resolve them. 1 Introduction Ellipsis is a linguistic phenomenon that has re- ceived considerable attention, mostly focusing on its interpretation. Most work on ellipsis (Fiengo and May, 1994; Lappin, 1993; Dalrym- ple et al., 1991; Kehler, 1993; Shieber et al., 1996) is aimed at discerning the procedures and the level of language processing at which ellipsis resolution takes place, or focuses on ambiguous and difficult cases. The detection of elliptical sentences or the identification of the antecedent and elided clauses within them are usually not dealt with, but taken as given. Noisy or miss- ing input, which is unavoidable in NLP applica- tions, is not dealt with, and neither is focusing on specific domains or applications. It therefore becomes clear that a robust, trainable approach is needed. An example of Verb Phrase Ellipsis (VPE), which is detected by the presence of an auxiliary verb without a verb phrase, is seen in example 1. VPE can also occur with semi-auxiliaries, as in example 2. (1) John3 {loves his3 wife}2. Bill3 does1 too. (2) But although he was terse, he didn’t {rage at me}2 the way I expected him to1. Several steps of work need to be done for el- lipsis resolution : 1. Detecting ellipsis occurrences. First, elided verbs need to be found. 2. Identifying antecedents. For most cases of ellipsis, copying of the antecedent clause is enough for resolution (Hardt, 1997). 3. Resolving ambiguities. For cases where ambiguity exists, a method for generating the full list of possible solutions, and sug- gesting the most likely one is needed. This paper describes the work done on the first stage, the detection of elliptical verbs. First, previous work done on tagged corpora will be summarised. Then, new work on parsed corpora will be presented, showing the gains possible through sentence-level features. Fi- nally, experiments using unannotated data that is parsed using an automatic parser are pre- sented, as our aim is to produce a stand-alone system. We have chosen to concentrate on VP ellipsis due to the fact that it is far more common than other forms of ellipsis, but pseudo-gapping, an example of which is seen in example 3, has also been included due to the similarity of its res- olution to VPE (Lappin, 1996). Do so/it/that and so doing anaphora are not handled, as their resolution is different from that of …

Content truncated to 500 words