TL;DR
This paper investigates how lexical ambiguity correlates with contextual informativeness across multiple languages, proposing measures based on WordNet and BERT, and finds that speakers tend to use more informative contexts to disambiguate ambiguous words.
Contribution
It introduces two novel measures of lexical ambiguity using WordNet and BERT, and empirically demonstrates their correlation with contextual informativeness across diverse languages.
Findings
Significant correlation between BERT-based ambiguity estimates and WordNet synonyms.
Lexical ambiguity negatively correlates with contextual uncertainty in 18 languages.
Speakers compensate for ambiguity by increasing contextual informativeness.
Abstract
Lexical ambiguity is widespread in language, allowing for the reuse of economical word forms and therefore making language more efficient. If ambiguous words cannot be disambiguated from context, however, this gain in efficiency might make language less clear -- resulting in frequent miscommunication. For a language to be clear and efficiently encoded, we posit that the lexical ambiguity of a word type should correlate with how much information context provides about it, on average. To investigate whether this is the case, we operationalise the lexical ambiguity of a word as the entropy of meanings it can take, and provide two ways to estimate this -- one which requires human annotation (using WordNet), and one which does not (using BERT), making it readily applicable to a large number of languages. We validate these measures by showing that, on six high-resource languages, there are…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
