185 citations · 552 across the 29 of their papers we have counts for
34 papers
Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play
Arkady Arkhangorodsky, Scot Fang, Victoria Knight +3
Task-oriented dialog systems are often trained on human/human dialogs, such as collected from Wizard-of-Oz interfaces. However, human/human corpora are frequently too small for sup…
MeetDot: Videoconferencing with Live Translation Captions
Arkady Arkhangorodsky, Christopher Chu, Scot Fang +5
We present MeetDot, a videoconferencing system with live translation captions overlaid on screen. The system aims to facilitate conversation between people who speak different lang…
Learning Mathematical Properties of Integers
Maria Ryskina, Kevin Knight
Embedding words in high-dimensional vector spaces has proven valuable in many natural language applications. In this work, we investigate whether similarly-trained embeddings of in…
A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
Boliang Zhang, Ying Lyu, Ning Ding +4
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the s…
Why Neural Machine Translation Prefers Empty Outputs
Xing Shi, Yijun Xiao, Kevin Knight
We investigate why neural machine translation (NMT) systems assign high probability to empty translations. We find two explanations. First, label smoothing makes correct-length tra…
MUSE: Textual Attributes Guided Portrait Painting Generation
Xiaodan Hu, Pengfei Yu, Kevin Knight +3
We propose a novel approach, MUSE, to illustrate textual attributes visually via portrait generation. MUSE takes a set of attributes written in text, in addition to facial features…