The effect of anaphor and ellipsis resolution on proximity searching in a text database

Abstract

So far, methods for ellipsis and anaphor resolution have been developed and the effects of anaphor resolution have been analyzed in the context of statistical information retrieval (IR) of scientific abstracts. No significant improvement has been observed. In this study, the effects of ellipsis and anaphor resolution on proximity searching in a full text database are analyzed. Anaphora and ellipses are classified on the basis of the type of their correlates/antecedents rather than, as traditional, on the basis of their own linguistic type. The classification differentiates proper names and common nouns of basic words, compound words, and phrases. The study was carried out in a newspaper article database containing 55,000 full text articles. A set of 154 keyword pairs in different categories was created. Human resolution of keyword ellipses and anaphora was performed to identify sentences and paragraphs which would match proximity searches after resolution. The findings indicate that ellipsis and anaphor resolution is most relevant for proper name phrases and only marginal in the other keyword categories. Therefore the recall effect of restricted resolution of proper name phrases only was analyzed for keyword pairs containing at least one proper name phrase. Our findings indicate a recall increase of 38.2% in sentence searches, and 28.8% in paragraph searches when proper name ellipses were resolved. The recall increase was 17.6% in sentence searches, and 10.8% in paragraph searches when proper name anaphora were resolved. This suggests that some simple and computationally justifiable resolution method might be developed only for proper name phrases to support keyword-based full-text IR. Elements of such a method are discussed.