Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler
This work addresses the challenge of domain-specific dictionary creation for linguists and researchers, though it appears incremental as it builds on existing methods.
The paper tackles the problem of detecting characteristic vocabulary for specialized dictionaries by introducing a directed crawler and a distributional semantics package that eliminate the need for a background corpus, with both tools made available online.
Specialized dictionaries are used to understand concepts in specific domains, especially where those concepts are not part of the general vocabulary, or having meanings that differ from ordinary languages. The first step in creating a specialized dictionary involves detecting the characteristic vocabulary of the domain in question. Classical methods for detecting this vocabulary involve gathering a domain corpus, calculating statistics on the terms found there, and then comparing these statistics to a background or general language corpus. Terms which are found significantly more often in the specialized corpus than in the background corpus are candidates for the characteristic vocabulary of the domain. Here we present two tools, a directed crawler, and a distributional semantics package, that can be used together, circumventing the need of a background corpus. Both tools are available on the web.