Work

A Graph-to-Sequence Model for AMR-to-Text Generation

Year: 2018

Type: conference-paper

Abstract: The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph.The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure.Although it is able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus faces challenges with large graphs, which result in long sequences.We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics.On a standard benchmark, our model shows superior results to existing methods in the literature.

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

DOI: 10.18653/v1/p18-1150

Authors: Linfeng Song, Yue Zhang, Zhiguo Wang, Daniel Gildea

Institutions: University of Rochester, Singapore University of Technology and Design, IBM (United States), IBM Research - Thomas J. Watson Research Center

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: University of Rochester, Centre International de Recherche sur le Cancer

OpenAlex ID: W2963374482