Oscar Sainz, Oier Lopez, Lacalle Gorka, Labaka Ander, Barrena Agirre
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 minutes 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 of 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, giving the best results to date on TACRED when fully trained. The analysis shows that our few-shot systems are especially effective when discriminating between relations, and that the performance difference in low data regimes comes mainly from identifying no-relation cases.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.03659")
get_code_for_paper("2109.03659")
have("2109.03659")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.03659.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.03659)
Connect an agent — have() is free.