Corpus-Based Learning for Noun Phrase Coreference Resolution

Corpus-Based Learning for Noun Phrase Coreference Resolution Wee Meng Soon Hwee Tou Ng Chung Yong Lim DSO National Laboratories 20 Science Park Drive, Singapore 118230 {sweemeng ,nhweetou, ichungyo}©dso, org. sg Abstract In this paper, we present a learning approach for coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task in- cludes resolving not just pronouns but rather general noun phrases. In contrast to previous work, we attempt to evaluate our approach on a common data set, the MUC-6 coreference cor- pus. We obtained encouraging results, indicat- ing that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to non-learning approaches. 1 Introduction Coreference resolution refers to the process of determining if two expressions in natural lan- guage refer to the same entity in the world. It is an important subtask in natural language processing systems. In particular, informa- tion extraction (IE) systems like those built in the DAI:tPA Message Understanding Confer- ences (Chinchor, 1998; Sundheim, 1995) have revealed that coreference resolution is such a critical component of IE systems that a sepa- rate coreference subtask has been defined and evaluated since MUC-6 (Committee, 1995). In this paper, we focus on the task of deter- mining coreference relations as defined in MUC- 6 (Committee, 1995). Specifically, a coreference relation denotes an identity of reference and holds between two textual elements known as markables, which are nouns, noun phrases, or pronouns. Thus, our coreference task resolves general noun phrases and not just pronouns, unlike in some previous work on anaphora res- olution. The ability to link co-referring noun phrases both within and across sentences is crit- ical to discourse analysis and language under- standing in general. 2 A Learning Approach for Coreference Resolution We adopt a corpus-based, learning approach for noun phrase coreference resolution. In this ap- proach, we need a relatively small corpus of training documents that have been annotated with coreference chains of noun phrases. All possible markables in a training document are determined by a pipeline of language process- ing modules, and training examples in the form of feature vectors are generated for appropri- ate pairs of markables. These training exam- ples are then given to a learning algorithm to build a classifier. To determine the coreference chains in a new document, all markables are determined and potential pairs of co-referring markables are presented to the classifier which will decide whether the two markables actually co-refer. We give the details of these steps in the following subsections. 2.1 Determination of Markables A pre-requisite for coreference resolution is to obtain most, if not all, of the possible mark- ables in a raw input text. To determine the markables, a pipeline of natural language pro- cessing (NLP) modules is used. They consist of sentence segmentation, tokenization, morpho- logical analysis, part-of-speech tagging, noun phrase identification, named entity recognition, and semantic class determination. As far as coreference resolution is concerned, the goal of these NLP modules …

Content truncated to 500 words