Few-Shot Relation Classification
10 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
Latest papers
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning
In this paper, we introduce a novel approach to enhance information extraction combining multiple sentence representations and contrastive learning.
CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation
To evaluate the performance of state-of-the-art RC models on the CORE dataset, we conduct experiments in the few-shot domain adaptation setting.
Few-Shot Document-Level Relation Extraction
We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark.
Meta-Information Guided Meta-Learning for Few-Shot Relation Classification
Few-shot classification requires classifiers to adapt to new classes with only a few training instances.
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
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?
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification.
Matching the Blanks: Distributional Similarity for Relation Learning
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
The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.