Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

relation-extraction

Temporal Relation Extraction

3260 papers • 126 benchmarks • 313 datasets

Temporal relation extraction systems aim to identify and classify the temporal relation between a pair of entities provided in a text. For instance, in the sentence "Bob sent a message to Alice while she was leaving her birthday party." one can infer that the actions "sent" and "leaving" entails a temporal relation that can be described as "simultaneous".

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in relation-extraction

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find relation-extraction models and implementations

ZHEvent/ZHEvent.github.io

2 papers 42

Datasets

2012 i2b2 Temporal Relations

2012 i2b2 Temporal Relations

French Timebank

French Timebank

Catalan TimeBank 1.0

Catalan TimeBank 1.0

Subtasks

Temporal Relation Classification

Most implemented papers

TempEval-3: Evaluating Events, Time Expressions, and Temporal Relations

N. UzZaman, H. Llorens, James F. Allen, Leon Derczynski, M. Verhagen, J. Pustejovsky•Thu Jun 21 2012

The TempEval-3 task is described, incorporating a three-part task structure covering event, temporal expression and temporal relation extraction; a larger dataset; and single overall task quality scores.

125

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

CATENA: CAusal and TEmporal relation extraction from NAtural language texts

Sara Tonelli, Paramita Mirza•Wed Nov 30 2016

CATENA, a sieve-based system to perform temporal and causal relation extraction and classification from English texts, exploiting the interaction between the temporal and the causal model is presented.

126 0

Structured Learning for Temporal Relation Extraction from Clinical Records

Marie-Francine Moens, A. Leeuwenberg•Sat Dec 31 2016

This study employs a structured perceptron together with integer linear programming constraints for document-level inference during training and prediction to exploit relational properties of temporality, together with global learning of the relations at the document level.

51 0

Effective Distant Supervision for Temporal Relation Extraction

Greg Durrett, Xinyu Zhao, Shih-Ting Lin•Fri Oct 23 2020

It is demonstrated that a pre-trained Transformer model is able to transfer from the weakly labeled examples to human-annotated benchmarks in both zero-shot and few-shot settings, and that the masking scheme is important in improving generalization.

22 0

Word-Level Loss Extensions for Neural Temporal Relation Classification

Marie-Francine Moens, A. Leeuwenberg•Tue Jul 31 2018

This work extends the classification model’s task loss with an unsupervised auxiliary loss on the word-embedding level of the model to ensure that the learned word representations contain both task-specific features and more general features learned from the unsuper supervised loss component.

7 0

Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference

Yu Yan, Kai-Wei Chang, Yizhou Sun, Rujun Han, Yichao Zhou, J. Caufield, P. Ping•Tue Dec 15 2020

A novel method, Clinical Temporal ReLation Exaction with Probabilistic Soft Logic Regularization and Global Inference (CTRL-PG) to tackle the problem at the document level, and significantly outperforms baseline methods for temporal relation extraction.

50 0

EventPlus: A Temporal Event Understanding Pipeline

Nanyun Peng, Jiao Sun, Mingyu Derek Ma, Shikhar Singh, Kung-Hsiang Huang, Nuan Wen, Rujun Han, Mu Yang•Tue Jan 12 2021

EventPlus as the first comprehensive temporal event understanding pipeline provides a convenient tool for users to quickly obtain annotations about events and their temporal information for any user-provided document.

33 0

Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction

Nanyun Peng, Rujun Han, Yichao Zhou•Mon Sep 14 2020

This work proposes a framework that enhances deep neural network with distributional constraints constructed by probabilistic domain knowledge and solves the constrained inference problem via Lagrangian Relaxation and applies it on end-to-end event temporal relation extraction tasks.

42 0

Deep Structured Neural Network for Event Temporal Relation Extraction

A. Galstyan, Nanyun Peng, Rujun Han, I-Hung Hsu, R. Weischedel, Mu Yang•Sat Sep 21 2019

Experimental results on three high-quality event temporal relation datasets demonstrate that incorporated with pre-trained contextualized embeddings, the proposed model achieves significantly better performances than the state-of-the-art methods on all three datasets.

66 0

Adding a benchmark result helps the community track progress.

Temporal Relation Extraction | State-of-the-Art