To access the content of digital texts efficiently, it is necessary to provide more sophisticated access than keyword based searching. Genescene provides biomedical researchers wi...
Gondy Leroy, Hsinchun Chen, Jesse D. Martinez, Sha...
This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential mean...
Exploiting unannotated natural language data is hard largely because unsupervised parameter estimation is hard. We describe deterministic annealing (Rose et al., 1990) as an appea...
We take a multi-pass approach to machine translation decoding when using synchronous context-free grammars as the translation model and n-gram language models: the first pass uses...
This paper proposes a speech comprehension computational model based on neurocognitiveresearches. The computational representation uses techniques as wavelets transform and connec...