Adverbs Revisited: Enhancing WordNet Coverage of Adverbs with a Supersense Taxonomy

TL;DR

This paper develops a new supersense typology for adverbs to improve WordNet's semantic coverage, validated through annotation, enhancing NLP tasks like disambiguation and sentiment analysis.

Contribution

Introduces a linguistically grounded adverb supersense taxonomy, extending WordNet and enabling more accurate semantic classification of adverbs in NLP.

Findings

Categories cover broad adverb types in natural text

Annotations are reliable among human annotators

Typology improves WordNet's semantic coverage

Abstract

WordNet offers rich supersense hierarchies for nouns and verbs, yet adverbs remain underdeveloped, lacking a systematic semantic classification. We introduce a linguistically grounded supersense typology for adverbs, empirically validated through annotation, that captures major semantic domains including manner, temporal, frequency, degree, domain, speaker-oriented, and subject-oriented functions. Results from a pilot annotation study demonstrate that these categories provide broad coverage of adverbs in natural text and can be reliably assigned by human annotators. Incorporating this typology extends WordNet's coverage, aligns it more closely with linguistic theory, and facilitates downstream NLP applications such as word sense disambiguation, event extraction, sentiment analysis, and discourse modeling. We present the proposed supersense categories, annotation outcomes, and directions for future work.