Noun2Verb: Probabilistic frame semantics for word class conversion

TL;DR

This paper introduces Noun2Verb, a probabilistic frame semantics framework that models how humans interpret and generate novel denominal verbs across languages, improving NLP understanding of word class conversion.

Contribution

It presents a new formalism for modeling denominal verb usage through shared semantic frames, outperforming existing models in interpreting and generating novel word class conversions.

Findings

Probabilistic models better explain denominal verb usage than state-of-the-art language models.

The framework applies across English, Mandarin Chinese, and historical English.

Shared knowledge in semantic frames enhances understanding of lexical creativity.

Abstract

Humans can flexibly extend word usages across different grammatical classes, a phenomenon known as word class conversion. Noun-to-verb conversion, or denominal verb (e.g., to Google a cheap flight), is one of the most prevalent forms of word class conversion. However, existing natural language processing systems are impoverished in interpreting and generating novel denominal verb usages. Previous work has suggested that novel denominal verb usages are comprehensible if the listener can compute the intended meaning based on shared knowledge with the speaker. Here we explore a computational formalism for this proposal couched in frame semantics. We present a formal framework, Noun2Verb, that simulates the production and comprehension of novel denominal verb usages by modeling shared knowledge of speaker and listener in semantic frames. We evaluate an incremental set of probabilistic models that learn to interpret and generate novel denominal verb usages via paraphrasing. We show that a model where the speaker and listener cooperatively learn the joint distribution over semantic frame elements better explains the empirical denominal verb usages than state-of-the-art language models, evaluated against data from 1) contemporary English in both adult and child speech, 2) contemporary Mandarin Chinese, and 3) the historical development of English. Our work grounds word class conversion in probabilistic frame semantics and bridges the gap between natural language processing systems and humans in lexical creativity.