Papers › Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction

Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction

8 Sep 2021arXiv:2109.03659archive 2025-07-28

Oscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, Eneko Agirre

Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relations produced in less than 15 min per relation. The system relies on a pretrained textual entailment engine which is run as-is (no training examples, zero-shot) or further fine-tuned on labeled examples (few-shot or fully trained). In our experiments on TACRED we attain 63% F1 zero-shot, 69% with 16 examples per relation (17% points better than the best supervised system on the same conditions), and only 4 points short to the state-of-the-art (which uses 20 times more training data). We also show that the performance can be improved significantly with larger entailment models, up to 12 points in zero-shot, allowing to report the best results to date on TACRED when fully trained. The analysis shows that our few-shot systems are specially effective when discriminating between relations, and that the performance difference in low data regimes comes mainly from identifying no-relation cases.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

osainz59/Ask2Transformers officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations (arXiv:2203.13602; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Natural Language InferenceRelation Extraction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction TACRED NLI_DeBERTa F1 73.9 #11 of 40 Archive leaderboard report
Relation Extraction TACRED NLI_DeBERTa F1 (1% Few-Shot) 63.7 #11 of 40 Archive leaderboard report
Relation Extraction TACRED NLI_DeBERTa F1 (10% Few-Shot) 67.9 #11 of 40 Archive leaderboard report
Relation Extraction TACRED NLI_DeBERTa F1 (5% Few-Shot) 69.0 #11 of 40 Archive leaderboard report
Relation Extraction TACRED NLI_DeBERTa F1 (Zero-Shot) 62.8 #11 of 40 Archive leaderboard report
Relation Extraction TACRED NLI_RoBERTa F1 71.0 #21 of 40 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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