Výsledky vyhledávání - "Arnold, Josh"

Report

LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing

Autor: Li, Yu, Arnold, Josh, Yan, Feifan, Shi, Weiyan, Yu, Zhou

We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible

Externí odkaz: http://arxiv.org/abs/2105.01992

Zobrazit plný text záznamu

Report

Revealing Persona Biases in Dialogue Systems

Autor: Sheng, Emily, Arnold, Josh, Yu, Zhou, Chang, Kai-Wei, Peng, Nanyun

Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. Modern dialogue systems may consider adopting anthropomorphic personas, mimicking societal demographic groups to appear more appro

Externí odkaz: http://arxiv.org/abs/2104.08728

Zobrazit plný text záznamu

Report

Gunrock 2.0: A User Adaptive Social Conversational System

Autor: Liang, Kaihui, Chau, Austin, Li, Yu, Lu, Xueyuan, Yu, Dian, Zhou, Mingyang, Jain, Ishan, Davidson, Sam, Arnold, Josh, Nguyen, Minh, Yu, Zhou

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understandin

Externí odkaz: http://arxiv.org/abs/2011.08906

Zobrazit plný text záznamu

Report

Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation

Autor: Zhou, Mingyang, Arnold, Josh, Yu, Zhou

Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the outp

Externí odkaz: http://arxiv.org/abs/1909.05365

Zobrazit plný text záznamu