Improved Portability and Parsing Through Interactive Acquisition of Semantic Information

IMPROVED PORTABILITY AND PARSING THROUGH INTERACTIVE ACQUISITION OF SEMANTIC INFORMATION t Francois-Michel Lang and Lynette Hirschman Paoli Research Center, UNISYS P. O. Box 517, Paoli, PA 19301 ABSTRACT This paper presents SPQR (Selectional Pat- tern Queries and Responses), a module of the PUNDIT text-processing system designed to facili- tate the acquisition of domain-specific semantic information, and to improve the accuracy and efficiency of the parser. SPQR operates by interactively and incrementally collecting informa- tion about the semantic acceptability of certain lexical co-occurrence patterns (e.g., subject-verb- object) found in partially constructed parses. The module has proved to be a valuable tool for port- ing PUNDIT to new domains and acquiring essen- tial semantic information about the domains. Preliminary results also indicate that SPQR causes a threefold reduction in the number of parses found, and about a 40~ reduction in total parsing time. 1. INTRODUCTION A major concern in designing a natural- language system is portability: It is advantageous to design a system in such a way that it can be ported to new domains with a minimum of effort. The level of effort required for such a port is con- siderably simplified if the system features a high degree of modularity. For example, if the domain-independent and domain-specific com- ponents of a system are clearly factored, only the domain-specific knowledge bases need be changed when porting to a new domain. Even if a system demonstrates such separation, however, the prob- lem remains of acquiring this domain-specific tThis work has been supported in part by DARPA under contract N00014-85-C-0012, administered by the Office of Na- val Research, and in part by National Science Foundation contract DCR-85-02205, as well as by Independent R~D fund- ing from System Development Corporation, now part of Unisys Corporation. knowledge. One obvious benefit of acquiring domain- specific semantic information is rejecting parses generated by the syntactic component which are semantically anomalous. Using domain knowledge to rule out semantically anomalous parses is espe- cially important when parsing with large, broad- coverage grammars such as ours: Our Prolog implementation of Restriction Grammar ~-Iirschman1982,Hirschman1985] includes about 100 grammar rules and 75 restrictions, and is based on Sager's Linguistic String Grammar [Sager1981]. It also includes a full treatment of sentential fragments and telegraphic message style. As a result of this extended coverage, many sentences receive numerous syntactic analyses. A majority of these analyses, however, are incorrect because they violate some semantic constraint. Let us take as an example the sentence High lsbe oil temperatsre belle~ed contribstor to snlt failure. Two of the parses for this sentence could be paraphrased as: (1) The high lube oil temperature believed the contributor to the unit failure. (2) The high lube oil temperature was believed to be a contributor to the unit failure. but our knowledge of the domain (and common sense) tells us that the first parse is wrong, since temperatures cannot hold beliefs. It is only because of this semantic informa- tion that we know that parse (2) is correct, and that parse (1) …

Content truncated to 500 words