Paper

Modeling morphosyntactic agreement as neural search: a case study of Hindi-Urdu

---

Abstract

Agreement is central to the morphosyntax of  many natural languages. Within contemporary linguistic theory, agreement relations have often been analyzed as the result of a structure-sensitive search operation. Neural language models, which lack an explicit bias for this type of operation, have shown mixed success at capturing morphosyntactic agreement phenomena. This paper develops an alternative neural model that formalizes the search operation in a fully differentiable way using gradient neural attention, and evaluates the model's ability to learn the complex agreement system of Hindi-Urdu from a large-scale dependency treebank and smaller synthetic datasets. We find that this model outperforms standard architectures at generalizing agreement patterns to held-out examples and structures.

Keywords: agreement, morphosyntax, computational modeling, neural networks, Hindi-Urdu

How to Cite:

Zhou, A. & Wilson, C., (2024) “Modeling morphosyntactic agreement as neural search: a case study of Hindi-Urdu”, Society for Computation in Linguistics 7(1), 227–239. doi: https://doi.org/10.7275/scil.2148