Systematic word meta-sense extension

Lei Yu

Submission Type: Regular Long Paper

Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Submission Track 2: Linguistic Theories, Cognitive Modeling, and Psycholinguistics

Keywords: lexical creativity, regular polysemy, systematicity, contextualized language model, analogical inference, figurative language processing

TL;DR: A computational framework of systematic word meaning extension and its application to figurative natural language inference

Abstract: The meaning of polysemous words often varies in a highly productive yet predictable way. Generalizing the regularity between conventional senses to derive novel word meaning is crucial for automated processing of non-literal language uses such as figurative expressions. We introduce a novel task called systematic word meta-sense extension (SWORME) to test and improve language models' ability to extend word meaning to denote new semantic domains (also called meta-senses) that bear regular semantic relations with existing senses. We found that language models prefer incremental lexical semantic change toward conceptually similar meta-senses such as logical metonymy, and are much worse at predicting highly non-literal meaning extensions such as metaphors. We propose a novel analogy-based method of word meaning extension, and show that it effectively improves language model systematicity in making both gradual and radical types of meta-sense extension. We further demonstrate that learning systematic meta-sense extensions benefits language models on multiple benchmarks of figurative language understanding.

Submission Number: 2017