Papers › A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

7 Sep 2019ACL 2020 6arXiv:1909.03227archive 2025-07-28

Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang

Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction. However, few existing works excel in solving the overlapping triple problem where multiple relational triples in the same sentence share the same entities. In this work, we introduce a fresh perspective to revisit the relational triple extraction task and propose a novel cascade binary tagging framework (CasRel) derived from a principled problem formulation. Instead of treating relations as discrete labels as in previous works, our new framework models relations as functions that map subjects to objects in a sentence, which naturally handles the overlapping problem. Experiments show that the CasRel framework already outperforms state-of-the-art methods even when its encoder module uses a randomly initialized BERT encoder, showing the power of the new tagging framework. It enjoys further performance boost when employing a pre-trained BERT encoder, outperforming the strongest baseline by 17.5 and 30.2 absolute gain in F1-score on two public datasets NYT and WebNLG, respectively. In-depth analysis on different scenarios of overlapping triples shows that the method delivers consistent performance gain across all these scenarios. The source code and data are released online.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

weizhepei/CasRel officialmentioned in papermentioned on GitHubtf report
LitianD/Joint_RE mentioned on GitHubpytorch report
Sherlock-coder/CasRel mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Relation ExtractionSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction NYT10-HRL CasRel (exact) F1 70.11 #7 of 10 Archive leaderboard report
Relation Extraction NYT11-HRL CasRel F1 53.9 #5 of 12 Archive leaderboard report
Relation Extraction NYT11-HRL CasRel (exact) F1 51.25 #9 of 12 Archive leaderboard report
Relation Extraction WebNLG HBT (CasRel) F1 91.8 #7 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections