Relation Classification

120 papers with code • 8 benchmarks • 19 datasets

Relation Classification is the task of identifying the semantic relation holding between two nominal entities in text.

Source: Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text

Most implemented papers

Large-scale Exploration of Neural Relation Classification Architectures

aidantee/MASS EMNLP 2018

Experimental performance on the task of relation classification has generally improved using deep neural network architectures.

Few-shot Text Classification with Distributional Signatures

YujiaBao/Distributional-Signatures ICLR 2020

In this paper, we explore meta-learning for few-shot text classification.

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

markus-eberts/spert 17 Sep 2019

The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass.

Relation Transformer Network

rajatkoner08/rtn 13 Apr 2020

In this work, we propose a novel transformer formulation for scene graph generation and relation prediction.

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction

declare-lab/relationprompt Findings (ACL) 2022

We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods.

Experiments with Three Approaches to Recognizing Lexical Entailment

context-mover/HypEval 31 Jan 2014

Two general strategies for RLE have been proposed: One strategy is to manually construct an asymmetric similarity measure for context vectors (directional similarity) and another is to treat RLE as a problem of learning to recognize semantic relations using supervised machine learning techniques (relation classification).

Improved Relation Extraction with Feature-Rich Compositional Embedding Models

mgormley/pacaya EMNLP 2015

We propose a Feature-rich Compositional Embedding Model (FCM) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement.

Relation Classification via Recurrent Neural Network

DavidMortensen/Bachelor-readinglist 5 Aug 2015

Deep learning has gained much success in sentence-level relation classification.

A Latent Variable Recurrent Neural Network for Discourse Relation Language Models

jiyfeng/drlm 7 Mar 2016

This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.