paper-with-me

홈 › Papers

MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations

2021-02-02 · Yao Dou, Maxwell Forbes, Ari Holtzman, Yejin Choi

We study conversational dialog in which there are many possible responses to a given history. We present the MultiTalk Dataset, a corpus of over 320,000 sentences of written conversational dialog that balances a high branching factor (10) with several conversation turns (6) through selective branch continuation. We make multiple contributions to study dialog generation in the highly branching setting. In order to evaluate a diverse set of generations, we propose a simple scoring algorithm, based on bipartite graph matching, to optimally incorporate a set of diverse references. We study multiple language generation tasks at different levels of predictive conversation depth, using textual attributes induced automatically from pretrained classifiers. Our culminating task is a challenging theory of mind problem, a controllable generation task which requires reasoning about the expected reaction of the listener.

📄 PDF Abstract BibTeX arXiv:2102.01263

Code (0)

등록된 구현이 없습니다.

Tasks

Graph MatchingText Generation

Similar Papers 제목 키워드 기반

DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue

2025-04-20 · Xiang Li, Duyi Pan, Hongru Xiao, Jiale Han 외

Speech synthesis is crucial for human-computer interaction, enabling natural and intuitive communication. However, existing datasets involve high construction costs due to manual annotation and suffer from limited charac…

DiversitySpeech Synthesis

Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games

2026-03-03 · Mark Goadrich, Achille Morenville, Éric Piette arxiv

AI algorithms for imperfect-information games are typically compared using performance metrics on individual games, making it difficult to assess robustness across game choices. Card games are a natural domain for imperf…

Speeding Up Mixed-Integer Programming Solvers with Sparse Learning for Branching

2026-03-31 · Selin Bayramoğlu, George L Nemhauser, Nikolaos V Sahinidis arxiv

Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datase…

Graph Neural NetworkSparse Learning

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

2026-08-15 · Varvara Arzt, Allan Hanbury, Terra Blevins arxiv

We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial languages, models exhibit a left-branching prefe…

GENEVA: GENErating and Visualizing branching narratives using LLMs

2023-11-15 · Jorge Leandro, Sudha Rao, Michael Xu, Weijia Xu 외

Dialogue-based Role Playing Games (RPGs) require powerful storytelling. The narratives of these may take years to write and typically involve a large creative team. In this work, we demonstrate the potential of large gen…

Language ModelingLanguage ModellingLarge Language Model