This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-...
Factoid questions often contain one or more assertions (facts) about their answers. However, existing question-answering (QA) systems have not investigated how the multiple facts ...
—Computational performance increasingly depends on parallelism, and many systems rely on heterogeneous resources such as GPUs and FPGAs to accelerate computationally intensive ap...
Marcin Bogdanski, Peter R. Lewis, Tobias Becker, X...
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
—For the description of reactive systems, there is a large number of languages and formalisms, and depending on a particular application or design phase, one of them may be bette...
Jens Brandt, Mike Gemunde, Klaus Schneider, Sandee...