all AI news
The Branch Not Taken: Predicting Branching in Online Conversations
April 23, 2024, 4:43 a.m. | Shai Meital, Lior Rokach, Roman Vainshtein, Nir Grinberg
cs.LG updates on arXiv.org arxiv.org
Abstract: Multi-participant discussions tend to unfold in a tree structure rather than a chain structure. Branching may occur for multiple reasons -- from the asynchronous nature of online platforms to a conscious decision by an interlocutor to disengage with part of the conversation. Predicting branching and understanding the reasons for creating new branches is important for many downstream tasks such as summarization and thread disentanglement and may help develop online spaces that encourage users to engage …
abstract arxiv asynchronous conversation conversations cs.cl cs.lg decision discussions multiple nature online platforms part platforms the conversation tree type understanding
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
2 days, 10 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
2 days, 10 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
2 days, 10 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York