A Transition-Based Directed Acyclic Graph Parser for UCCA

04/03/2017
by   Daniel Hershcovich, et al.
0

We present the first parser for UCCA, a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. To our knowledge, the conjunction of these formal properties is not supported by any existing parser. Our transition-based parser, which uses a novel transition set and features based on bidirectional LSTMs, has value not just for UCCA parsing: its ability to handle more general graph structures can inform the development of parsers for other semantic DAG structures, and in languages that frequently use discontinuous structures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/06/2019

SemEval 2019 Task 1: Cross-lingual Semantic Parsing with UCCA

We present the SemEval 2019 shared task on UCCA parsing in English, Germ...
research
07/13/2017

Parsing with Traces: An O(n^4) Algorithm and a Structural Representation

General treebank analyses are graph structured, but parsers are typicall...
research
05/31/2018

SemEval 2019 Shared Task: Cross-lingual Semantic Parsing with UCCA - Call for Participation

We announce a shared task on UCCA parsing in English, German and French,...
research
02/13/2019

Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling

We investigate the problem of parsing conversational data of morphologic...
research
08/31/2022

GRILLBot: An Assistant for Real-World Tasks with Neural Semantic Parsing and Graph-Based Representations

GRILLBot is the winning system in the 2022 Alexa Prize TaskBot Challenge...
research
02/24/2019

Unlexicalized Transition-based Discontinuous Constituency Parsing

Lexicalized parsing models are based on the assumptions that (i) constit...
research
10/05/2018

TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

We present TRANX, a transition-based neural semantic parser that maps na...

Please sign up or login with your details

Forgot password? Click here to reset