Logical Inferences with Comparatives and Generalized Quantifiers
This addresses the problem of improving logical inference accuracy for linguistically complex sentences in NLI, which is incremental as it builds on existing formal semantics and inference methods.
The paper tackled the challenge of handling comparative constructions in Natural Language Inference (NLI) by developing a compositional semantics system that maps comparatives to logical representations and integrates it with automated theorem proving. The result showed that the system outperformed previous logic-based and deep learning-based models on three NLI datasets containing complex logical inferences.
Comparative constructions pose a challenge in Natural Language Inference (NLI), which is the task of determining whether a text entails a hypothesis. Comparatives are structurally complex in that they interact with other linguistic phenomena such as quantifiers, numerals, and lexical antonyms. In formal semantics, there is a rich body of work on comparatives and gradable expressions using the notion of degree. However, a logical inference system for comparatives has not been sufficiently developed for use in the NLI task. In this paper, we present a compositional semantics that maps various comparative constructions in English to semantic representations via Combinatory Categorial Grammar (CCG) parsers and combine it with an inference system based on automated theorem proving. We evaluate our system on three NLI datasets that contain complex logical inferences with comparatives, generalized quantifiers, and numerals. We show that the system outperforms previous logic-based systems as well as recent deep learning-based models.