End-to-end Graph-based TAG Parsing with Neural Networks

TL;DR

This paper introduces a neural network-based graph parser for Tree Adjoining Grammar that jointly performs multiple linguistic tasks, achieving state-of-the-art results and demonstrating TAG's effectiveness for complex sentence analysis.

Contribution

The paper presents a novel end-to-end neural graph-based TAG parser that outperforms previous models and supports rich structural sentence analysis.

Findings

Outperforms previous best results by over 2.2 LAS and UAS points.

Achieves state-of-the-art in PETE and Unbounded Dependency Recovery.

Supports TAG as a viable formalism for complex linguistic analysis.

Abstract

We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.