AMR Parsing as Sequence-to-Graph Transduction

被引：0

作者：

Zhang, Sheng ^{[1
]}

Ma, Xutai ^{[1
]}

Duh, Kevin ^{[1
]}

Van Durme, Benjamin ^{[1
]}

机构：

[1] Johns Hopkins Univ, Baltimore, MD 21218 USA

来源：

57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019) | 2019年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it can be effectively trained with limited amounts of labeled AMR data. Our experimental results outperform all previously reported SMATCH scores, on both AMR 2.0 (76.3% F1 on LDC2017T10) and AMR 1.0 (70.2% F1 on LDC2014T12).

引用

页码：80 / 94

页数：15

共 50 条

[21] A Graph-to-Sequence Model for AMR-to-Text Generation
Song, Linfeng
Zhang, Yue
Wang, Zhiguo
Gildea, Daniel
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, 2018, : 1616 - 1626
[22] From text to graph: a general transition-based AMR parsing using neural network
Min Gu
Yanhui Gu
Weilan Luo
Guandong Xu
Zhenglu Yang
Junsheng Zhou
Weiguang Qu
Neural Computing and Applications, 2021, 33 : 6009 - 6025
[23] SEQUENCE TRANSDUCTION WITH GRAPH-BASED SUPERVISION
Moritz, Niko
Hori, Takaaki
Watanabe, Shinji
Le Roux, Jonathan
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 7212 - 7216
[24] Improving AMR parsing by exploiting the dependency parsing as an auxiliary task
Wu, Taizhong
Zhou, Junsheng
Qu, Weiguang
Gu, Yanhui
Li, Bin
Zhong, Huilin
Long, Yunfei
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (20) : 30827 - 30838
[25] From text to graph: a general transition-based AMR parsing using neural network
Gu, Min
Gu, Yanhui
Luo, Weilan
Xu, Guandong
Yang, Zhenglu
Zhou, Junsheng
Qu, Weiguang
Neural Computing and Applications, 2021, 33 (11) : 6009 - 6025
[26] From text to graph: a general transition-based AMR parsing using neural network
Gu, Min
Gu, Yanhui
Luo, Weilan
Xu, Guandong
Yang, Zhenglu
Zhou, Junsheng
Qu, Weiguang
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (11): : 6009 - 6025
[27] AMR Parsing with Cache Transition Systems
Peng, Xiaochang
Gildea, Daniel
Satta, Giorgio
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 4897 - 4904
[28] Hierarchical Curriculum Learning for AMR Parsing
Wang, Peiyi
Chen, Liang
Liu, Tianyu
Dai, Damai
Cao, Yunbo
Chang, Baobao
Sui, Zhifang
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2, 2022, : 333 - 339
[29] Improving AMR parsing by exploiting the dependency parsing as an auxiliary task
Taizhong Wu
Junsheng Zhou
Weiguang Qu
Yanhui Gu
Bin Li
Huilin Zhong
Yunfei Long
Multimedia Tools and Applications, 2021, 80 : 30827 - 30838
[30] AMR Parsing with Latent Structural Information
Zhou, Qiji
Zhang, Yue
Ji, Donghong
Tang, Hao
58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 4306 - 4319

← 1 2 3 4 5 →