Towards a Seamless Integration of Word Senses into Downstream NLP Applications

TL;DR

This paper presents a method to incorporate word sense disambiguation into NLP applications, demonstrating improved performance in classification tasks and emphasizing the importance of in vivo evaluations for sense representations.

Contribution

Introduces a novel disambiguation algorithm integrated into a classification model, enhancing sense-level information use in downstream NLP tasks.

Findings

Disambiguation improves classification accuracy.

Granularity of sense inventory affects performance.

In vivo evaluations are crucial for sense representation research.

Abstract

Lexical ambiguity can impede NLP systems from accurate understanding of semantics. Despite its potential benefits, the integration of sense-level information into NLP systems has remained understudied. By incorporating a novel disambiguation algorithm into a state-of-the-art classification model, we create a pipeline to integrate sense-level information into downstream NLP applications. We show that a simple disambiguation of the input text can lead to consistent performance improvement on multiple topic categorization and polarity detection datasets, particularly when the fine granularity of the underlying sense inventory is reduced and the document is sufficiently large. Our results also point to the need for sense representation research to focus more on in vivo evaluations which target the performance in downstream NLP applications rather than artificial benchmarks.