Work

AMR Parsing with an Incremental Joint Model

Year: 2016

Type: conference-paper

Abstract: To alleviate the error propagation in the traditional pipelined models for Abstract Meaning Representation (AMR) parsing, we formulate AMR parsing as a joint task that performs the two subtasks: concept identification and relation identification simultaneously.To this end, we first develop a novel componentwise beam search algorithm for relation identification in an incremental fashion, and then incorporate the decoder into a unified framework based on multiple-beam search, which allows for the bi-directional information flow between the two subtasks in a single incremental model.Experiments on the public datasets demonstrate that our joint model significantly outperforms the previous pipelined counterparts, and also achieves better or comparable performance than other approaches to AMR parsing, without utilizing external semantic resources.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d16-1065

Authors: Junsheng Zhou, Feiyu Xu, Hans Uszkoreit, Weiguang QU, Ran Li, Yanhui Gu

Institutions: Nanjing Normal University, German Research Centre for Artificial Intelligence

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Bundesministerium für Bildung und Forschung, Banting and Best Diabetes Centre, University of Toronto, Natural Science Research of Jiangsu Higher Education Institutions of China