In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
We consider a model for which it is important, early in processing, to estimate some variables with high precision, but perhaps at relatively low recall. If some variables can be ...
Gary B. Huang, Andrew Kae, Carl Doersch, Erik G. L...
Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experienc...
Architectural description languages are a useful tool for modeling complex systems at a high level of abstraction. If based on formal methods, they can also serve for enabling the...
Language and image understanding are two major goals of artificial intelligence which can both be conceptually formulated in terms of parsing the input signal into a hierarchical ...
Leo Zhu, Yuanhao Chen, Yuan Lin, Chenxi Lin, Alan ...