Towards Resolving Word Ambiguity with Word Embeddings
This addresses ambiguity resolution for information retrieval tasks, particularly in specialized environments with sensitive data, but it is incremental as it builds on existing word embedding and clustering methods.
The paper tackles the problem of word ambiguity in natural language by using DBSCAN clustering on word embeddings to identify ambiguous words and evaluate their ambiguity levels, achieving high-quality, semantically coherent clusters.
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.