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

[1] AMR Parsing via Graph⇆Sequence Iterative Inference
Cai, Deng
Lam, Wai
58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 1290 - 1301
[2] On the Complexity of Sequence-to-Graph Alignment
Jain, Chirag
Zhang, Haowen
Gao, Yu
Aluru, Srinivas
JOURNAL OF COMPUTATIONAL BIOLOGY, 2020, 27 (04) : 640 - 654
[3] Incorporating EDS Graph for AMR Parsing
Shou, Ziyi
Lin, Fangzhen
10TH CONFERENCE ON LEXICAL AND COMPUTATIONAL SEMANTICS (SEM 2021), 2021, : 202 - 211
[4] Ensembling Graph Predictions for AMR Parsing
Lam, Hoang Thanh
Picco, Gabriele
Hou, Yufang
Lee, Young-Suk
Nguyen, Lam M.
Phan, Dzung T.
Lopez, Vanessa
Astudillo, Ramon Fernandez
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[5] Bit-parallel sequence-to-graph alignment
Rautiainen, Mikko
Maekinen, Veli
Marschall, Tobias
BIOINFORMATICS, 2019, 35 (19) : 3599 - 3607
[6] GraphAligner: rapid and versatile sequence-to-graph alignment
Rautiainen, Mikko
Marschall, Tobias
GENOME BIOLOGY, 2020, 21 (01) : 253
[7] Guiding AMR Parsing with Reverse Graph Linearization
Gao, Bofei
Chen, Liang
Wang, Peiyi
Sui, Zhifang
Chang, Baobao
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 13 - 26
[8] Sequence-to-sequence AMR Parsing with Ancestor Information
Yu, Chen
Gildea, Daniel
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2, 2022, : 571 - 577
[9] AMR Parsing as Graph Prediction with Latent Alignment
Lyu, Chunchuan
Titov, Ivan
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, 2018, : 397 - 407
[10] Accelerating Sequence-to-Graph Alignment on Heterogeneous Processors
Feng, Zonghao
Luo, Qiong
50TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, 2021,

← 1 2 3 4 5 →