Lexicon Acquisition: Learning from Corpus by Capitalizing on Lexical Categories

Text examples must be exploited in the acquisition of lexical structures. However, neither syntactic nor semantic features are provided by the text itself, and so acquisition must be aided by additional resources. We investigate the application of an existing resource, a set of lexical categories, as a prediction method. We present an algorithm that applies (a) top-down prediction based on lexical categories; (b) bottom-up validation by scanning text examples. Finally, we discuss the issue of semantic bootstrapping and identify its theoretical and practical limitations. 1 Introduction Existing programs frequently stumble when encountering a new word. Such lexical gaps diminish the utility of natural language technology. The problem is aggravated by the existence of entire unknown phrases composed of single well-known words: (1) John made a table from raw wood. (2) He made a widow happy. (3) He made a happy widow. (4) He made the widow a table. (5) He made her leave early. Each make phrase interacts with its arguments in its own idiosyncratic way. Example (1) presents the simple usage of make: make means generate. Examples (2) and (3), both taken from Love in the Time of Cholera [Marquez, 1986], are more intriguing since similar words combine in entirely different ways: in (2) she (the widow) becomes happy; in (3) he becomes a happy widow. Example (4) introduces the beneficiary interaction: he made it for her. And finally example (5) brings in the complement-taking form: he forced her to act. These examples illustrate how subtle differences in argument structure might impact the entire meaning. A lexicon therefore must account for all the variations such a verb can possibly assume. Idiomatic phrases are not confined to fine literature. The sample sentences next page are taken from the Dow-Jones newswire (July 7, 1988). A brief observation reveals the diversity of phrases used in this technical domain. Make a statement, make a plan, and make a decision fall into one category. Make final net $10,000 falls into a second category. Make it difficult, make it attractive, make it available fall into yet another category. This small collection of sentences illustrates (a) how extensive a lexicon should be to facilitate effective text processing, and (b), the wealth of raw information provided in the text for lexical acquisition purposes. A program processing such text cannot be provided with all these categories at the outset. Therefore, lexical knowledge must be acquired on demand: once …