2016/03/04 by Rudolf Kadlec, Kadlec, Rudolf, Martin Schmid +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL
paper · pdf · doi:10.48550/arxiv.1603.01547
Presented at ACL 2016
arxiv created 2016/06/24 · arxiv updated 2016/06/27
Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches. We present a new, simple model that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models. This makes the model particularly suitable for question-answering problems where the answer is a single word from the document. Ensemble of our models sets new state of the art on all evaluated datasets.