Conceptual Association for Compound Noun Analysis

CONCEPTUAL ASSOCIATION FOR COMPOUND NOUN ANALYSIS Microsoft Institute 65 Epping Road North Ryde NSW 2113 (t-markl @ microsoft.corn) Mark Lauer AUSTRALIA Department of Computing Macquarie University NSW 2109 (mark @ macadam, mpce. mq.edu .au) Abstract This paper describes research toward the automatic interpretation of compound nouns using corpus statistics. An initial study aimed at syntactic disambiguation is presented. The approach presented bases associations upon thesaurus categories. Association data is gathered from unambiguous cases extracted from a corpus and is then applied to the analysis of ambiguous compound nouns. While the work presented is still in progress, a first attempt to syntactically analyse a test set of 244 examples shows 75% correctness. Future work is aimed at improving this accuracy and extending the technique to assign semantic role information, thus producing a complete interpretation. INTRODUCTION Compound Nouns: Compound nouns (CNs) are a commonly occurring construction in language consisting of a sequence of nouns, acting as a noun; pottery coffee mug, for example. For a detailed linguistic theory of compound noun syntax and semantics, see Levi (1978). Compound nouns are analysed syntactically by means of the rule N --¢ N N applied recursively. Compounds of more than two nouns are ambiguous in syntactic structure. A necessary part of producing an interpretation of a CN is an analysis of the attachments within the compound. Syntactic parsers cannot choose an appropriate analysis, because attachments are not syntactically governed. The current work presents a system for automatically deriving a syntactic analysis of arbitrary CNs in English using corpus statistics. Task description: The initial task can be formulated as choosing the most probable binary bracketing for a given noun sequence, known to form a compound noun, without knowledge of the context. E.G.: (pottery (coffee mug)); ((coffee mug) holder) Corpus Statistics: The need for wide ranging lexical-semantic knowledge to support NLP, commonly referred to as the ACQUISITION PROBLEM, has generated a great deal of research investigating automatic means of acquiring such knowledge. Much work has employed carefully constructed parsing systems to extract knowledge from machine readable dictionaries (e.g., Vanderwende, 1993). Other approaches have used rather simpler, statistical analyses of large corpora, as is done in this work. Hindle and Rooth (1993) used a rough parser to extract lexical preferences for prepositional phrase (PP) attachment. The system counted occurrences of unambiguously attached PPs and used these to define LEXICAL ASSOCIATION between prepositions and the nouns and verbs they modified. This association data was then used to choose an appropriate attachment for ambiguous cases. The counting of unambiguous cases in order to make inferences about ambiguous ones is adopted in the current work. An explicit assumption is made that lexical preferences are relatively independent of the presence of syntactic ambiguity. Subsequently, Hindle and Rooth's work has been extended by Resnik and Hearst (1993). Resnik and Hearst attempted to include information about typical prepositional objects in their association data. They introduced the notion of CONCEPTUAL ASSOCIATION in which associations are measured between groups of words considered to represent concepts, in …

Content truncated to 500 words