Distilling state-of-the-art transformer models into lightweight student
...
Should sequences be modeled autoregressively—one symbol at a time? How m...
Query auto-completion is a search engine feature whereby the system sugg...
This paper addresses the problem of community membership detection using...
This paper addresses the problem of predicting duration of unplanned pow...
A context-aware language model uses location, user and/or domain metadat...
Increased adaptability of RNN language models leads to improved predicti...
The application of Deep Neural Networks for ranking in search engines ma...
Social media messages' brevity and unconventional spelling pose a challe...
The goal of this paper is to use multi-task learning to efficiently scal...
This paper addresses the question of how language use affects community
...
Usernames are ubiquitous on the Internet, and they are often suggestive ...
In applications involving conversational speech, data sparsity is a limi...