Lune

EMNLP Findings2024

Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach

Mayank Singh, Eduardo Blanco

Abstract

We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction cites CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation ExtractionAunabil Chakma, Mihai Surdeanu, Eduardo BlancoACL 2026 · 1 citation

Builds on5

  1. Lessons Learned from the Chameleon TestbedKate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau et al.USENIX ATC 2020 · 398 citations
  2. CodeT5+: Open Code Large Language Models for Code Understanding and GenerationYue Wang, Hung Le, Akhilesh Gotmare, Nghi D. Q. Bui et al.EMNLP 2023 · 339 citations
  3. Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation ExtractionTapas Nayak, Hwee Tou NgAAAI 2020 · 272 citations
  4. Re-TACRED: Addressing Shortcomings of the TACRED DatasetGeorge Stoica, Emmanouil Antonios Platanios, Barnabás PóczosAAAI 2021 · 146 citations
  5. Relation Classification with Entity Type RestrictionShengfei Lyu, Huanhuan ChenACL Findings 2021 · 59 citations

Related papers

  1. Label Verbalization and Entailment for Effective Zero and Few-Shot Relation ExtractionOscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena et al.EMNLP 2021 · 94 citations
  2. Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural NetworksChengyue Jiang, Yinggong Zhao, Shanbo Chu, Libin Shen et al.EMNLP 2020 · 23 citations
  3. Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence ClassificationPrithviraj Sen, Marina Danilevsky, Yunyao Li, Siddhartha Brahma et al.EMNLP 2020 · 12 citations
  4. Revisiting Relation Extraction in the era of Large Language ModelsSomin Wadhwa, Silvio Amir, Byron C. WallaceACL 2023 · 145 citations
  5. Large Language Models are Interpretable LearnersRuochen Wang, Si Si, Felix X. Yu, Dorothea Wiesmann Rothuizen et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines