Polyglot Semantic Parsing in APIs

TL;DR

This paper introduces a unified polyglot semantic parsing model that handles multiple natural and programming languages simultaneously, using a novel graph-based decoding framework to improve performance across diverse datasets.

Contribution

It presents a new graph-based decoding approach enabling a single model to perform semantic parsing across multiple languages and datasets, advancing the flexibility of semantic parsing systems.

Findings

Achieved state-of-the-art results on software component datasets

Demonstrated effectiveness on two additional benchmark semantic parsing tasks

Unified model handles multiple natural and programming languages

Abstract

Traditional approaches to semantic parsing (SP) work by training individual models for each available parallel dataset of text-meaning pairs. In this paper, we explore the idea of polyglot semantic translation, or learning semantic parsing models that are trained on multiple datasets and natural languages. In particular, we focus on translating text to code signature representations using the software component datasets of Richardson and Kuhn (2017a,b). The advantage of such models is that they can be used for parsing a wide variety of input natural languages and output programming languages, or mixed input languages, using a single unified model. To facilitate modeling of this type, we develop a novel graph-based decoding framework that achieves state-of-the-art performance on the above datasets, and apply this method to two other benchmark SP tasks.