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

04/18/2018
by   Jungo Kasai, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/20/2019

Global Greedy Dependency Parsing

Most syntactic dependency parsing models may fall into one of two catego...
research
05/01/2017

Dependency Parsing with Dilated Iterated Graph CNNs

Dependency parses are an effective way to inject linguistic knowledge in...
research
04/05/2016

A new TAG Formalism for Tamil and Parser Analytics

Tree adjoining grammar (TAG) is specifically suited for morph rich and a...
research
12/19/2014

Supertagging: Introduction, learning, and application

Supertagging is an approach originally developed by Bangalore and Joshi ...
research
08/20/2019

Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited

Transition-based and graph-based dependency parsers have previously been...
research
07/11/2018

UniParse: A universal graph-based parsing toolkit

This paper describes the design and use of the graph-based parsing frame...
research
12/22/2014

Joint RNN-Based Greedy Parsing and Word Composition

This paper introduces a greedy parser based on neural networks, which le...

Please sign up or login with your details

Forgot password? Click here to reset