Unsupervised word sense disambiguation in dynamic semantic spaces.
In this paper, we are mainly concerned with the ability to quickly andautomatically distinguish word senses in dynamic semantic spaces in which newterms and new senses appear frequently. Such spaces are built '"on the fly"from constantly evolving data sets such as Wikipedia, repositories of patentgrants and applications, or large sets of legal documents for TechnologyAssisted Review and e-discovery. This immediacy rules out supervision as wellas the use of a priori training sets. We show that the various senses of a termcan be automatically made apparent with a simple clustering algorithm, eachsense being a vector in the semantic space. While we only consider heresemantic spaces build by using random vectors, this algorithm should work withany kind of embedding, provided meaningful similarities between terms can becomputed and do fulfill at least the two basic conditions that terms whichclose meanings have high similarities and terms with unrelated meanings havenear-zero similarities.
Continue reading and listening
Stay in the loop.
Subscribe to our newsletter for a weekly update on the latest podcast, news, events, and jobs postings.