Text Understanding with the Attention Sum Reader Network
This work addresses the need for efficient single-word answer extraction in large-scale QA datasets, representing an incremental improvement over existing attention-based methods.
The authors tackled the problem of text comprehension in cloze-style question-answering by introducing a new model that uses attention to directly select answers from context, achieving state-of-the-art results on datasets like CNN, Daily Mail, and the Children's Book Test.
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.