Papers › Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning

Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning

2 Sep 2021CoNLL (EMNLP) 2021 11arXiv:2109.00840archive 2025-07-28

Christos Theodoropoulos, James Henderson, Andrei C. Coman, Marie-Francine Moens

Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token-level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al.,2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.

PaperPDFConference PDFCode

Code

christos42/CLDR_CLNER_models officialmentioned 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

Contrastive LearningLanguage ModelingLanguage ModellingNamed Entity RecognitionNamed Entity Recognition (NER)Relation ExtractionSentenceSentence Embeddingsnamed-entity-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction Adverse Drug Events (ADE) Corpus CLDR + CLNER NER Macro F1 88.3 #10 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus CLDR + CLNER RE+ Macro F1 79.97 #10 of 15 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

CharacterBERTContrastive LearningGCNSupervised Contrastive Loss

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