[PDF][PDF] Who Says What to Whom: A Survey of Multi-Party Conversations.
Multi-party conversations (MPCs) are a more practical and challenging scenario involving
more than two interlocutors. This research topic has drawn significant attention from both …
more than two interlocutors. This research topic has drawn significant attention from both …
Response selection for multi-party conversations with dynamic topic tracking
While participants in a multi-party multi-turn conversation simultaneously engage in multiple
conversation topics, existing response selection methods are developed mainly focusing on …
conversation topics, existing response selection methods are developed mainly focusing on …
Online conversation disentanglement with pointer networks
T Yu, S Joty - arXiv preprint arXiv:2010.11080, 2020 - arxiv.org
Huge amounts of textual conversations occur online every day, where multiple
conversations take place concurrently. Interleaved conversations lead to difficulties in not …
conversations take place concurrently. Interleaved conversations lead to difficulties in not …
Unsupervised conversation disentanglement through co-training
Conversation disentanglement aims to separate intermingled messages into detached
sessions, which is a fundamental task in understanding multi-party conversations. Existing …
sessions, which is a fundamental task in understanding multi-party conversations. Existing …
Structured dialogue discourse parsing
TC Chi, AI Rudnicky - arXiv preprint arXiv:2306.15103, 2023 - arxiv.org
Dialogue discourse parsing aims to uncover the internal structure of a multi-participant
conversation by finding all the discourse~\emph {links} and corresponding~\emph …
conversation by finding all the discourse~\emph {links} and corresponding~\emph …
Automating discussion structure re-organization for GitHub issues
S Bai, L Liu, C Meng, H Liu - Expert Systems with Applications, 2023 - Elsevier
As a popular social code hosting platform, GitHub encourages developers to discuss and
leave opinions on issues. However, the linear format of GitHub issue discussions makes …
leave opinions on issues. However, the linear format of GitHub issue discussions makes …
Core-sets for fair and diverse data summarization
S Mahabadi, S Trajanovski - Advances in Neural …, 2024 - proceedings.neurips.cc
We study core-set construction algorithms for the task of Diversity Maximization under
fairness/partition constraint. Given a set of points $ P $ in a metric space partitioned into $ m …
fairness/partition constraint. Given a set of points $ P $ in a metric space partitioned into $ m …
Mmpose: Movie-induced multi-label positive emotion classification through eeg signals
Emotional information plays an important role in various multimedia applications. Movies, as
a widely available form of multimedia content, can induce multiple positive emotions and …
a widely available form of multimedia content, can induce multiple positive emotions and …
Conversation disentanglement with bi-level contrastive learning
Conversation disentanglement aims to group utterances into detached sessions, which is a
fundamental task in processing multi-party conversations. Existing methods have two main …
fundamental task in processing multi-party conversations. Existing methods have two main …
Dialbert: A hierarchical pre-trained model for conversation disentanglement
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 …
simultaneously, and the listener should decide which utterance is part of the conversation he …