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.

natural-language-processing-7

Dialog Relation Extraction

3260 papers • 126 benchmarks • 313 datasets

Dialog Relation Extraction is the task of predicting the relation type between entities mentioned in dialogue. It uses multiple tokens to capture possible relations between pairs of entities in the dialogue. The popular benchmark for this task is the DialogRE dataset. The models are typically evaluated with the metric of F1 Score for both standard-setting and conversational settings.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in dialog-relation-extraction-7

Trend

Dataset

Best Model

Actions

DialogRE

DialogRE

DDRel

DDRel

Libraries

i

Use these libraries to find dialog-relation-extraction-7 models and implementations

Datasets

DialogRE

DDRel

Subtasks

No subtasks available.

Most implemented papers

Dialogue-Based Relation Extraction

Dong Yu, Kai Sun, Dian Yu, Claire Cardie•Thu Apr 16 2020

It is argued that speaker-related information plays a critical role in the proposed task, based on an analysis of similarities and differences between dialogue-based and traditional RE tasks, and a new metric to evaluate the performance of RE methods in a conversational setting is designed.

142

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Aixin Sun, E. Chng, Fuzhao Xue, Hao Zhang•Fri Dec 11 2020

This paper proposes to construct a latent multi-view graph to capture various possible relationships among tokens and refined this graph to select important words for relation prediction, and shows that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence- level RE.

90 0

DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues

Qi Jia, Hongru Huang, Kenny Q. Zhu•Thu Dec 03 2020

This paper crawled movie scripts from IMSDb, and annotated the relation label for each session according to 13 pre-defined relationships, and constructed session-level and pair-level relation classification tasks with widely-accepted baselines.

22 0

Dialogue Relation Extraction with Document-Level Heterogeneous Graph Attention Networks

Soujanya Poria, Navonil Majumder, Pengfei Hong, Hui Chen, Wei Han•Wed Sep 09 2020

An attention-based heterogeneous graph network is presented to deal with the dialogue relation extraction task in an inductive manner and shows superior performance on the benchmark dataset DialogRE.

47 0

An Embarrassingly Simple Model for Dialogue Relation Extraction

Aixin Sun, E. Chng, Fuzhao Xue, Hao Zhang•Sat Dec 26 2020

A simple yet effective model named SimpleRE is proposed for the RE task, which captures the interrelations among multiple relations in a dialogue through a novel input format named BERT Relation Token Sequence.

32 0

KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

Luo Si, Ningyu Zhang, Shumin Deng, Xiang Chen, Chuanqi Tan, Fei Huang, Huajun Chen, Yunzhi Yao, Ningyu Zhang, Xin Xie•Wed Apr 14 2021

A Knowledge-aware Prompt-tuning approach with synergistic optimization (KnowPrompt) that injects latent knowledge contained in relation labels into prompt construction with learnable virtual type words and answer words.

467 0

Semantic Representation for Dialogue Modeling

Yulong Chen, Xuefeng Bai, Yue Zhang, Linfeng Song•Thu May 20 2021

To the knowledge, this work is the first to leverage a formal semantic representation into neural dialogue modeling, and compares with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity.

56 0

Graph Based Network with Contextualized Representations of Turns in Dialogue

Y. Choi, Bongseok Lee•Wed Sep 08 2021

This paper proposes the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues, and proposes a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE.

78 0

D-REX: Dialogue Relation Extraction with Explanations

Alon Albalak, L. Getoor, W. Wang, Varun R. Embar, Yi-Lin Tuan•Thu Sep 09 2021

This work proposes a model-agnostic framework, D-REX, a policy-guided semi-supervised algorithm that optimizes for explanation quality and relation extraction simultaneously, and frames relation extraction as a re-ranking task and includes relation- and entity-specific explanations as an intermediate step of the inference process.

10 0

Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction

Wei Lu, Guoshun Nan, Sicong Leng, Guoqing Luo•Fri Sep 10 2021

This work introduces SOLS, a novel model which can explicitly induce speaker-oriented latent structures for better DiaRE, and learns latent structures to capture the relationships among tokens beyond the utterance boundaries, alleviating the entangled logic issue.

8 0

Adding a benchmark result helps the community track progress.

Dialog Relation Extraction | State-of-the-Art