Department of Computer Science and Technology

Technical reports

A shallow processing approach to anaphor resolution

David Maclean Carter

May 1986, 233 pages

This technical report is based on a dissertation submitted December 1985 by the author for the degree of Doctor of Philosophy to the University of Cambridge, King’s College.

DOI: 10.48456/tr-88

Abstract

The thesis describes an investigation of the faesibility of resolving anaphors in natural language texts by means of a “shallow processing” approach which exploits knowledge of syntax, semantics and local focussing as heavily as possible; it does not rely on the presence of large amounts of world or domain knowledge, which are notoriously hard to process accurately.

The ideas reported are implemented in a program called SPAR (Shallow Processing Anaphor Resolver), which resolves anaphoric and other linguistic ambiguities in simple English stories and generates sentence-by-sentence paraphrases that show what interpretations have been selected. Input to SPAR takes the form of semantic structures for single sentences constructed by Boguraev’s English analyser. These structures are integrated into a network-style text representation as processing proceeds. To achieve anaphor resolution, SPAR combines and develops several existing techniques, most notably Sidner’s theory of local focussing and Wilks’ “preference semantics” theory of semantics and common sense inference.

Consideration of the need to resolve several anaphors in the same sentence results in Sidner’s framework being modified and extended to allow focus-based processing to ineract more flexibly with processing based on other types of knowledge. Wilks’ treatment of common sense inference is extended to incorporate a wider range of types of inference without jeopardizing its uniformity and simplicity. Further his primitive-based formalism for word sense meanings is developed in the interests of economy, accuracy and ease of use.

Although SPAR is geared mainly towards resolving anaphors, the design of the system allows many non-anaphoric (lexical and structural) ambiguities that cannot be resloved during sentence analysis to be resolved as a by-product of anaphor resolution.

Full text

Only available on paper (could be scanned on request).

BibTeX record

@TechReport{UCAM-CL-TR-88,
  author =	 {Carter, David Maclean},
  title = 	 {{A shallow processing approach to anaphor resolution}},
  year = 	 1986,
  month = 	 may,
  institution =  {University of Cambridge, Computer Laboratory},
  address =	 {15 JJ Thomson Avenue, Cambridge CB3 0FD, United Kingdom,
          	  phone +44 1223 763500},
  doi = 	 {10.48456/tr-88},
  number = 	 {UCAM-CL-TR-88}
}