Papers › Joint entity recognition and relation extraction as a multi-head selection problem
Joint entity recognition and relation extraction as a multi-head selection problem
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder
State-of-the-art models for joint entity recognition and relation extraction strongly rely on external natural language processing (NLP) tools such as POS (part-of-speech) taggers and dependency parsers. Thus, the performance of such joint models depends on the quality of the features obtained from these NLP tools. However, these features are not always accurate for various languages and contexts. In this paper, we propose a joint neural model which performs entity recognition and relation extraction simultaneously, without the need of any manually extracted features or the use of any external tool. Specifically, we model the entity recognition task using a CRF (Conditional Random Fields) layer and the relation extraction task as a multi-head selection problem (i.e., potentially identify multiple relations for each entity). We present an extensive experimental setup, to demonstrate the effectiveness of our method using datasets from various contexts (i.e., news, biomedical, real estate) and languages (i.e., English, Dutch). Our model outperforms the previous neural models that use automatically extracted features, while it performs within a reasonable margin of feature-based neural models, or even beats them.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Relation Extraction | ACE 2004 | multi-head | Cross Sentence | No | #8 of 11 | Archive leaderboard | report |
| Relation Extraction | ACE 2004 | multi-head | NER Micro F1 | 81.16 | #8 of 11 | Archive leaderboard | report |
| Relation Extraction | ACE 2004 | multi-head | RE+ Micro F1 | 47.14 | #8 of 11 | Archive leaderboard | report |
| Relation Extraction | Adverse Drug Events (ADE) Corpus | multi-head | NER Macro F1 | 86.40 | #15 of 15 | Archive leaderboard | report |
| Relation Extraction | Adverse Drug Events (ADE) Corpus | multi-head | RE+ Macro F1 | 74.58 | #15 of 15 | Archive leaderboard | report |
| Relation Extraction | CoNLL04 | multi-head | NER Macro F1 | 83.9 | #7 of 16 | Archive leaderboard | report |
| Relation Extraction | CoNLL04 | multi-head | RE+ Macro F1 | 62.04 | #7 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.
Methods
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