Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders

About

Named entity recognition and relation extraction are two important fundamental problems. Joint learning algorithms have been proposed to solve both tasks simultaneously, and many of them cast the joint task as a table-filling problem. However, they typically focused on learning a single encoder (usually learning representation in the form of a table) to capture information required for both tasks within the same space. We argue that it can be beneficial to design two distinct encoders to capture such two different types of information in the learning process. In this work, we propose the novel {\em table-sequence encoders} where two different encoders -- a table encoder and a sequence encoder are designed to help each other in the representation learning process. Our experiments confirm the advantages of having {\em two} encoders over {\em one} encoder. On several standard datasets, our model shows significant improvements over existing approaches.

Jue Wang, Wei Lu• 2020

Related benchmarks

TaskDatasetResultRank
Relation ExtractionACE05 (test)
F1 Score67.6
72
Named Entity RecognitionACE 2005 (test)
F1 Score89.5
58
Entity extractionACE05 (test)
F1 Score89.5
53
Relation ExtractionCONLL04
Relation Strict F173.6
43
Named Entity RecognitionACE04 (test)
F1 Score88.6
36
Relation ExtractionCoNLL04 (test)
F1 Score75.8
28
Joint Entity and Relation ExtractionADE--
26
Relation ExtractionACE04 (test)
F1 Score63.3
21
Relation ExtractionADE
Relation Strict F180.1
20
Entity extractionACE04 (test)
F1 Score88.6
19
Showing 10 of 24 rows

Other info

Code

Follow for update