TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking

Extracting entities and relations from unstructured text has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in identifying overlapping relations with shared entities. Prior works show that joint learning can result in a noticeable performance gain. However, they usually involve sequential interrelated steps and suffer from the problem of exposure bias. At training time, they predict with the ground truth conditions while at inference it has to make extraction from scratch. This discrepancy leads to error accumulation. To mitigate the issue, we propose in this paper a one-stage joint extraction model, namely, TPLinker, which is capable of discovering overlapping relations sharing one or both entities while immune from the exposure bias. TPLinker formulates joint extraction as a token pair linking problem and introduces a novel handshaking tagging scheme that aligns the boundary tokens of entity pairs under each relation type. Experiment results show that TPLinker performs significantly better on overlapping and multiple relation extraction, and achieves state-of-the-art performance on two public datasets.

PDF Abstract COLING 2020 PDF COLING 2020 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction NYT10-HRL TPLinker F1 72.45 # 3
Relation Extraction NYT11-HRL TPLinker F1 55.67 # 2
Relation Extraction WebNLG TPLinker F1 91.9 # 6

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Relation Extraction NYT10-HRL TPLinker F1 71.93 # 5
Relation Extraction NYT11-HRL TPLinker F1 55.28 # 4

Methods


No methods listed for this paper. Add relevant methods here