Relationship Extraction

Relationship extraction is the task of extracting semantic relationships from a text. Extracted relationships usually occur between two or more entities of a certain type (e.g. Person, Organisation, Location) and fall into a number of semantic categories (e.g. married to, employed by, lives in).

New York Times Corpus

The standard corpus for distantly supervised relationship extraction is the New York Times (NYT) corpus, published in Riedel et al, 2010.

This contains text from the New York Times Annotated Corpus with named entities extracted from the text using the Stanford NER system and automatically linked to entities in the Freebase knowledge base. Pairs of named entities are labelled with relationship types by aligning them against facts in the Freebase knowledge base. (The process of using a separate database to provide label is known as 'distant supervision')


Elevation Partners, the $1.9 billion private equity group that was founded by Roger McNamee

(founded_by, Elevation_Partners, Roger_McNamee)

Different papers have reported various metrics since the release of the dataset, making it difficult to compare systems directly. The main metrics used are either precision at N results or plots of the precision-recall. The range of recall has increased over the years as systems improve, with earlier systems having very low precision at 30% recall.

Model P@10% P@30% Paper / Source Code
HRERE (Xu et al., 2019) 84.9 72.8 Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction HRERE
PCNN+noise_convert+cond_opt (Wu et al., 2019) 81.7 61.8 Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
Intra- and Inter-Bag (Ye and Ling, 2019) 78.9 62.4 Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions Code
RESIDE (Vashishth et al., 2018) 73.6 59.5 RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information RESIDE
PCNN+ATT (Lin et al., 2016) 69.4 51.8 Neural Relation Extraction with Selective Attention over Instances OpenNRE
MIML-RE (Surdeneau et al., 2012) 60.7+ - Multi-instance Multi-label Learning for Relation Extraction Mimlre
MultiR (Hoffman et al., 2011) 60.9+ - Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations MultiR
(Mintz et al., 2009) 39.9+ - Distant supervision for relation extraction without labeled data

(+) Obtained from results in the paper "Neural Relation Extraction with Selective Attention over Instances"

SemEval-2010 Task 8

SemEval-2010 introduced 'Task 8 - Multi-Way Classification of Semantic Relations Between Pairs of Nominals'. The task is, given a sentence and two tagged nominals, to predict the relation between those nominals and the direction of the relation. The dataset contains nine general semantic relations together with a tenth 'OTHER' relation.


There were apples, pears and oranges in the bowl.

(content-container, pears, bowl)

The main evaluation metric used is macro-averaged F1, averaged across the nine proper relationships (i.e. excluding the OTHER relation), taking directionality of the relation into account.

Several papers have used additional data (e.g. pre-trained word embeddings, WordNet) to improve performance. The figures reported here are the highest achieved by the model using any external resources.

End-to-End Models

Model F1 Paper / Source Code
BERT-based Models
R-BERT (Wu et al. 2019) 89.25 Enriching Pre-trained Language Model with Entity Information for Relation Classification
CNN-based Models
Multi-Attention CNN (Wang et al. 2016) 88.0 Relation Classification via Multi-Level Attention CNNs lawlietAi's Reimplementation
Attention CNN (Huang and Y Shen, 2016) 84.3
Attention-Based Convolutional Neural Network for Semantic Relation Extraction
CR-CNN (dos Santos et al., 2015) 84.1 Classifying Relations by Ranking with Convolutional Neural Network pratapbhanu's Reimplementation
CNN (Zeng et al., 2014) 82.7 Relation Classification via Convolutional Deep Neural Network roomylee's Reimplementation
RNN-based Models
Entity Attention Bi-LSTM (Lee et al., 2019) 85.2 Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing Official
Hierarchical Attention Bi-LSTM (Xiao and C Liu, 2016) 84.3 Semantic Relation Classification via Hierarchical Recurrent Neural Network with Attention
Attention Bi-LSTM (Zhou et al., 2016) 84.0 Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification SeoSangwoo's Reimplementation
Bi-LSTM (Zhang et al., 2015) 82.7
Bidirectional long short-term memory networks for relation classification

*: It uses external lexical resources, such as WordNet, part-of-speech tags, dependency tags, and named entity tags.

Dependency Models

Model F1 Paper / Source Code
BRCNN (Cai et al., 2016) 86.3 Bidirectional Recurrent Convolutional Neural Network for Relation Classification
DRNNs (Xu et al., 2016) 86.1 Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation
depLCNN + NS (Xu et al., 2015a) 85.6 Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
SDP-LSTM (Xu et al., 2015b) 83.7 Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path Sshanu's Reimplementation
DepNN (Liu et al., 2015) 83.6 A Dependency-Based Neural Network for Relation Classification
FCN (Yu et al., 2014) 83.0 Factor-based compositional embedding models
MVRNN (Socher et al., 2012) 82.4 Semantic Compositionality through Recursive Matrix-Vector Spaces pratapbhanu's Reimplementation


TACRED is a large-scale relation extraction dataset with 106,264 examples built over newswire and web text from the corpus used in the yearly TAC Knowledge Base Population (TAC KBP) challenges. Examples in TACRED cover 41 relation types as used in the TAC KBP challenges (e.g., _per:schoolsattended and org:members) or are labeled as _norelation if no defined relation is held. These examples are created by combining available human annotations from the TAC KBP challenges and crowdsourcing.


Billy Mays, the bearded, boisterious pitchman who, as the undisputed king of TV yell and sell, became an inlikely pop culture icon, died at his home in Tampa, Fla, on Sunday.

(per:city_of_death, Billy Mays, Tampa)

The main evaluation metric used is micro-averaged F1 over instances with proper relationships (i.e. excluding the _norelation type).

Model F1 Paper / Source Code
C-GCN + PA-LSTM (Zhang et al. 2018) 68.2 Graph Convolution over Pruned Dependency Trees Improves Relation Extraction Offical
PA-LSTM (Zhang et al, 2017) 65.1 Position-aware Attention and Supervised Data Improve Slot Filling Official


The Few-Shot Relation Classification Dataset (FewRel) is a different setting from the previous datasets. This dataset consists of 70K sentences expressing 100 relations annotated by crowdworkers on Wikipedia corpus. The few-shot learning task follows the N-way K-shot meta learning setting. It is both the largest supervised relation classification dataset as well as the largest few-shot learning dataset till now.

The public leaderboard is available on the FewRel website.

Go back to the README