Conversation Disentanglement

4 papers with code • 3 benchmarks • 1 datasets

Automatic disentanglement could be used to provide more interpretable results when searching over chat logs, and to help users understand what is happening when they join a channel.

Source: Kummerfeld et al.

Most implemented papers

A Large-Scale Corpus for Conversation Disentanglement

jkkummerfeld/irc-disentanglement ACL 2019

Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets.

DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement

TeddLi/Disentangle 8 Apr 2020

Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to.

Unsupervised Conversation Disentanglement through Co-Training

layneins/unsupervised_dialo_disentanglement EMNLP 2021

For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier.

Dramatic Conversation Disentanglement

kentchang/dramatic-conversation-disentanglement 26 May 2023

We present a new dataset for studying conversation disentanglement in movies and TV series.