Toward General-Purpose Learning for Information Extraction

Two trends are evident in the recent evolution of the field of information extraction: a preference for simple, often corpus-driven techniques over linguistically sophisticated ones; and a broadening of the central problem definition to include many non-traditional text domains. This development calls for information extraction systems which are as retctrgetable and general as possible. Here, we describe SRV, a learning architecture for information extraction which is designed for maximum generality and flexibility. SRV can exploit domain-specific information, including linguistic syntax and lexical information, in the form of features provided to the system explicitly as input for training. This process is illustrated using a domain created from Reuters corporate acquisitions articles. Features are derived from two general-purpose NLP systems, Sleator and Temperly's link grammar parser and Wordnet. Experiments compare the learner's performance with and without such linguistic information. Surprisingly, in many cases, the system performs as well without this information as with it. 1 I n t r o d u c t i o n The field of information extraction (IE) is concerned with using natural language processing (NLP) to extract essential details from text documents automatically. While the problems of retrieval, routing, and filtering have received considerable attention through the years, IE is only now coming into its own as an information management sub-discipline. Progress in the field of IE has been away from general NLP systems, that must be tuned to work ill a particular domain, toward faster systems that perform less linguistic processing of documents and can be more readily targeted at novel domains (e.g., (Appelt et al., 1993)). A natural part of this development has been the introduction of machine learning techniques to facilitate the domain engineering effort (Riloff, 1996; Soderland and Lehnert, 1994). Several researchers have reported IE systems which use machine learning at their core (Soderland, 1996; Califf and Mooney, 1997). Rather than spend human effort tuning a system for an IE domain, it becomes possible to conceive of training it on a document sample. Aside from the obvious savings in human development effort, this has significant implications for information extraction as a discipline: Retargetability Moving to a novel domain should no longer be a question of code modification; at most some feature engineering should be required. Gene ra l i t y It should be possible to handle a much wider range of domains than previously. In addition to domains characterized by grammatical prose, we should be able to perform information extraction in domains involving less traditional structure, such as netnews articles and Web pages. In this paper we describe a learning algorithm similar in spirit to FOIL (Quinlan, 1990), which takes as input a set of tagged documents, and a set of features that control generalization, and produces rules that describe how to extract information from novel documents. For this system, introducing linguistic or any other information particular to a domain is an exercise in feature definition, separate from the central algorithm, which is constant. We describe a set of experiments, involving a document collection of newswire articles, in which this learner is compared with simpler learning algorithms.