Packed Levitated Marker for Entity and Relation Extraction

• DOI: 10.18653/v1/2022.acl-long.337
• Publication Date: 2022-06-03T01:34:53Z
• Authors: Deming Ye; Yankai Lin; Peng Li; Maosong Sun
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; 01 natural sciences; Computation and Language (cs.CL); 0105 earth and related environmental sciences

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.<br/>Accepted to ACL 2022. The code and models are available at https://github.com/thunlp/PL-Marker<br/>