FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (2019-10-01T00:00:00.000000Z)

TL;DR

It is found that the state-of-the-art few-shot relation classification models struggle on these two aspects, and that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well.

Abstract

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? (2) Can they detect none-of-the-above (NOTA) relations? To construct FewRel 2.0, we build upon the FewRel dataset by adding a new test set in a quite different domain, and a NOTA relation choice. With the new dataset and extensive experimental analysis, we found (1) that the state-of-the-art few-shot relation classification models struggle on these two aspects, and (2) that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well. Our research calls for more attention and further efforts to these two real-world issues. All details and resources about the dataset and baselines are released at https://github.com/thunlp/fewrel.

Authors

Xu Han

16 papers

Zhiyuan Liu

34 papers

Maosong Sun

46 papers

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

TL;DR

Abstract

Authors

References22 items

Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification

Matching the Blanks: Distributional Similarity for Relation Learning

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

Adversarial Multi-lingual Neural Relation Extraction

Few-Shot Learning with Graph Neural Networks

Prototypical Networks for Few-shot Learning

Meta Networks

Optimization as a Model for Few-Shot Learning

Matching Networks for One Shot Learning

Domain-Adversarial Training of Neural Networks

Explaining and Harnessing Adversarial Examples

Wikidata

Unsupervised Visual Domain Adaptation Using Subspace Alignment

Unsupervised Domain Adaptation by Domain Invariant Projection

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals

Distant supervision for relation extraction without labeled data

Domain Adaptation via Transfer Component Analysis

Learning to Extract Relations from the Web using Minimal Supervision

Domain Adaptation with Structural Correspondence Learning

Robust Classification for Imprecise Environments

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Multi-way classification of semantic relations between pairs of nominals

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names