Papers › Adversarial training for multi-context joint entity and relation extraction

Adversarial training for multi-context joint entity and relation extraction

21 Aug 2018EMNLP 2018 10arXiv:1808.06876archive 2025-07-28

Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and relation extraction. In particular, we demonstrate that applying AT to a general purpose baseline model for jointly extracting entities and relations, allows improving the state-of-the-art effectiveness on several datasets in different contexts (i.e., news, biomedical, and real estate data) and for different languages (English and Dutch).

PaperPDFConference PDFCode

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

Code

bekou/multihead_joint_entity_relation_extraction officialmentioned in papermentioned on GitHubtf 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

Joint Entity and Relation ExtractionRelation Extraction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction ACE 2004 multi-head + AT Cross Sentence No #7 of 11 Archive leaderboard report
Relation Extraction ACE 2004 multi-head + AT NER Micro F1 81.64 #7 of 11 Archive leaderboard report
Relation Extraction ACE 2004 multi-head + AT RE+ Micro F1 47.45 #7 of 11 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus multi-head + AT NER Macro F1 86.73 #14 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus multi-head + AT RE+ Macro F1 75.52 #14 of 15 Archive leaderboard report
Relation Extraction CoNLL04 multi-head + AT NER Macro F1 83.6 #8 of 16 Archive leaderboard report
Relation Extraction CoNLL04 multi-head + AT RE+ Macro F1 61.95 #8 of 16 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.

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