Papers › ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning

ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning

10 Apr 2021NAACL 2021 4arXiv:2104.04697archive 2025-07-28

Chih-Yao Chen, Cheng-Te Li

While relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that cannot be observed at the training stage. In this paper, we formulate the zero-shot relation extraction problem by incorporating the text description of seen and unseen relations. We propose a novel multi-task learning model, zero-shot BERT (ZS-BERT), to directly predict unseen relations without hand-crafted attribute labeling and multiple pairwise classifications. Given training instances consisting of input sentences and the descriptions of their relations, ZS-BERT learns two functions that project sentences and relation descriptions into an embedding space by jointly minimizing the distances between them and classifying seen relations. By generating the embeddings of unseen relations and new-coming sentences based on such two functions, we use nearest neighbor search to obtain the prediction of unseen relations. Experiments conducted on two well-known datasets exhibit that ZS-BERT can outperform existing methods by at least 13.54\% improvement on F1 score.

PaperPDFConference PDFCode

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

Code

dinobby/ZS-BERT officialmentioned in paperpytorch 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

AttributeMulti-Task LearningRelation ExtractionRepresentation LearningZero-shot Relation Classification

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

Wiki-ZSL

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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