7k citations
- University of California, Santa BarbaraUS109 papers
- Microsoft Research (United Kingdom)GB50 papers
- ETH ZurichCH46 papers
- University of California, BerkeleyUS45 papers
- University of Maryland, College ParkUS43 papers
- Carnegie Mellon UniversityUS41 papers
- Stanford UniversityUS39 papers
- University of WashingtonUS37 papers
- Cornell UniversityUS32 papers
- Princeton UniversityUS32 papers
- California Institute of TechnologyUS28 papers
- Microsoft Research New York City (United States)25 papers
7 papers · 2 filters
A practical two-stage training strategy for multi-stream end-to-end speech recognition
Ruizhi Li, Gregory Sell, Xiaofei Wang +2
The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study o…
Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks
Igor Shalyminov, Sungjin Lee, Arash Eshghi +1
Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-drive…
Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation
Sungjin Lee, Igor Shalyminov
Neural dialog models often lack robustness to anomalous user input and produce inappropriate responses which leads to frustrating user experience. Although there are a set of prior…
Combining Sentiment Lexica with a Multi-View Variational Autoencoder
Alexander Hoyle, Lawrence Wolf-Sonkin, Hanna Wallach +2
When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, ann…
Topic-Guided Variational Autoencoders for Text Generation
Wenlin Wang, Zhe Gan, Hongteng Xu +5
We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Ga…
Multilingual Neural Machine Translation with Knowledge Distillation
Xu Tan, Yi Ren, Di He +3
Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving…