Towards Resolving Word Ambiguity with Word Embeddings

Bibliographic Details
Title: Towards Resolving Word Ambiguity with Word Embeddings
Authors: Thurnbauer, Matthias, Reisinger, Johannes, Goller, Christoph, Fischer, Andreas
Publication Year: 2023
Collection: Computer Science
Subject Terms: Computer Science - Computation and Language
More Details: Ambiguity is ubiquitous in natural language. Resolving ambiguous meanings is especially important in information retrieval tasks. While word embeddings carry semantic information, they fail to handle ambiguity well. Transformer models have been shown to handle word ambiguity for complex queries, but they cannot be used to identify ambiguous words, e.g. for a 1-word query. Furthermore, training these models is costly in terms of time, hardware resources, and training data, prohibiting their use in specialized environments with sensitive data. Word embeddings can be trained using moderate hardware resources. This paper shows that applying DBSCAN clustering to the latent space can identify ambiguous words and evaluate their level of ambiguity. An automatic DBSCAN parameter selection leads to high-quality clusters, which are semantically coherent and correspond well to the perceived meanings of a given word.
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2307.13417
Accession Number: edsarx.2307.13417
Database: arXiv
More Details
Description not available.