Towards Coinductive Models for Natural Language Understanding. Bringing together Deep Learning and Deep Semantics

TL;DR

This paper proposes integrating coinduction with traditional inductive methods to develop more realistic, scalable models for natural language understanding, addressing limitations of current bottom-up approaches.

Contribution

It introduces a formal framework combining coinduction and induction for natural language understanding, highlighting their joint potential and formalizing their use in NLP.

Findings

Coinduction can enhance the modeling of long sentences and dialogues.

Induction and coinduction can coexist and complement each other.

Formalizations demonstrate the joint application in NLP tasks.

Abstract

This article contains a proposal to add coinduction to the computational apparatus of natural language understanding. This, we argue, will provide a basis for more realistic, computationally sound, and scalable models of natural language dialogue, syntax and semantics. Given that the bottom up, inductively constructed, semantic and syntactic structures are brittle, and seemingly incapable of adequately representing the meaning of longer sentences or realistic dialogues, natural language understanding is in need of a new foundation. Coinduction, which uses top down constraints, has been successfully used in the design of operating systems and programming languages. Moreover, implicitly it has been present in text mining, machine translation, and in some attempts to model intensionality and modalities, which provides evidence that it works. This article shows high level formalizations of some of such uses. Since coinduction and induction can coexist, they can provide a common language and a conceptual model for research in natural language understanding. In particular, such an opportunity seems to be emerging in research on compositionality. This article shows several examples of the joint appearance of induction and coinduction in natural language processing. We argue that the known individual limitations of induction and coinduction can be overcome in empirical settings by a combination of the the two methods. We see an open problem in providing a theory of their joint use.