Few-Shot Relation Classification

8 papers with code • 4 benchmarks • 6 datasets

Few-Shot Relation Classification is a particular relation classification task under minimum annotated data, where a model is required to classify a new incoming query instance given only few support instances (e.g., 1 or 5) during testing.

Source: MICK: A Meta-Learning Framework for Few-shot Relation Classification with Little Training Data

Most implemented papers

Matching the Blanks: Distributional Similarity for Relation Learning

plkmo/BERT-Relation-Extraction ACL 2019

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction.

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

ProKil/FewRel EMNLP 2018

The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.

Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

ZhixiuYe/MLMAN ACL 2019

This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification.

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

thunlp/fewrel IJCNLP 2019

We present FewRel 2. 0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances?

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification

thunlp/miml COLING 2020

Few-shot classification requires classifiers to adapt to new classes with only a few training instances.

Few-Shot Document-Level Relation Extraction

nicpopovic/fredo NAACL 2022

We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark.