Packed Levitated Marker for Entity and Relation Extraction

Deming Ye, Yankai Lin, Peng Li, Maosong Sun


Abstract
Recent entity and relation extraction works focus on investigating how to obtain a better span representation from the pre-trained encoder. However, a major limitation of existing works is that they ignore the interrelation between spans (pairs). In this work, we propose a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder. In particular, we propose a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information. Furthermore, for those more complicated span pair classification tasks, we design a subject-oriented packing strategy, which packs each subject and all its objects to model the interrelation between the same-subject span pairs. The experimental results show that, with the enhanced marker feature, our model advances baselines on six NER benchmarks, and obtains a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models on ACE04 and ACE05. Our code and models are publicly available at https://github.com/thunlp/PL-Marker
Anthology ID:
2022.acl-long.337
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4904–4917
Language:
URL:
https://aclanthology.org/2022.acl-long.337
DOI:
10.18653/v1/2022.acl-long.337
Bibkey:
Cite (ACL):
Deming Ye, Yankai Lin, Peng Li, and Maosong Sun. 2022. Packed Levitated Marker for Entity and Relation Extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4904–4917, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Packed Levitated Marker for Entity and Relation Extraction (Ye et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.337.pdf
Software:
 2022.acl-long.337.software.zip
Code
 thunlp/pl-marker
Data
ACE 2004ACE 2005CoNLL-2003Few-NERDOntoNotes 5.0SciERC