End-to-end Graph-based TAG Parsing with Neural Networks
This work addresses parsing challenges in natural language processing for tasks requiring rich structural analysis, offering a novel integration of graph-based and neural methods.
The paper tackles the problem of Tree Adjoining Grammar (TAG) parsing by developing an end-to-end graph-based parser using neural networks, which outperforms previous best results by over 2.2 LAS and UAS points and achieves state-of-the-art performance in downstream tasks like PETE and Unbounded Dependency Recovery.
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.