Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play

no code implementations • 20 Sep 2021 • Arkady Arkhangorodsky, Scot Fang, Victoria Knight, Ajay Nagesh, Maria Ryskina, Kevin Knight

Task-oriented dialog systems are often trained on human/human dialogs, such as collected from Wizard-of-Oz interfaces.

reinforcement-learning Reinforcement Learning (RL)

MeetDot: Videoconferencing with Live Translation Captions

no code implementations • EMNLP (ACL) 2021 • Arkady Arkhangorodsky, Christopher Chu, Scot Fang, Yiqi Huang, Denglin Jiang, Ajay Nagesh, Boliang Zhang, Kevin Knight

We use the re-translation strategy to translate the streamed speech, resulting in caption flicker.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training

1 code implementation • 9 Oct 2020 • Arkady Arkhangorodsky, Amittai Axelrod, Christopher Chu, Scot Fang, Yiqi Huang, Ajay Nagesh, Xing Shi, Boliang Zhang, Kevin Knight

We create a new task-oriented dialog platform (MEEP) where agents are given considerable freedom in terms of utterances and API calls, but are constrained to work within a push-button environment.

Learning to Pronounce Chinese Without a Pronunciation Dictionary

no code implementations • EMNLP 2020 • Christopher Chu, Scot Fang, Kevin Knight

We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary.