Work

Deep Multitask Learning for Semantic Dependency Parsing

Year: 2017

Type: conference-paper

Abstract: We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms.By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax.We then explore two multitask learning approaches-one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly.We find that both approaches improve performance across formalisms on average, achieving a new state of the art.Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p17-1186

Authors: Hao Peng, Sam Thomson, Noah A. Smith

Institutions: University of Washington, Carnegie Mellon University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Awards: G4713059963, G5432064702, RI: Medium: Broad-Coverage Semantic Parsing: Linguistic Representation Learning from Crowd-Scale Data