A Probabilistic Generative Grammar for Semantic Parsing

TL;DR

This paper introduces a probabilistic generative grammar for semantic parsing that uses hierarchical Dirichlet processes, enabling domain-independent learning and improved generalization in natural language understanding systems.

Contribution

It presents a novel application of hierarchical Dirichlet processes for structured prediction in semantic parsing, with simplified algorithms and an extension to word morphology modeling.

Findings

Efficient algorithms for training, parsing, and sentence generation are derived.

The model generalizes well across domains without additional supervision.

Extended to incorporate morphological data from Wiktionary.

Abstract

Domain-general semantic parsing is a long-standing goal in natural language processing, where the semantic parser is capable of robustly parsing sentences from domains outside of which it was trained. Current approaches largely rely on additional supervision from new domains in order to generalize to those domains. We present a generative model of natural language utterances and logical forms and demonstrate its application to semantic parsing. Our approach relies on domain-independent supervision to generalize to new domains. We derive and implement efficient algorithms for training, parsing, and sentence generation. The work relies on a novel application of hierarchical Dirichlet processes (HDPs) for structured prediction, which we also present in this manuscript. This manuscript is an excerpt of chapter 4 from the Ph.D. thesis of Saparov (2022), where the model plays a central role in a larger natural language understanding system. This manuscript provides a new simplified and more complete presentation of the work first introduced in Saparov, Saraswat, and Mitchell (2017). The description and proofs of correctness of the training algorithm, parsing algorithm, and sentence generation algorithm are much simplified in this new presentation. We also describe the novel application of hierarchical Dirichlet processes for structured prediction. In addition, we extend the earlier work with a new model of word morphology, which utilizes the comprehensive morphological data from Wiktionary.