Abstract | ||
---|---|---|
Several large doze-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. |
Year | DOI | Venue |
---|---|---|
2016 | 10.18653/v1/P16-1086 | PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 |
DocType | Volume | Citations |
Conference | abs/1603.01547 | 83 |
PageRank | References | Authors |
3.18 | 13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rudolf Kadlec | 1 | 229 | 16.25 |
Martin Schmid | 2 | 86 | 5.64 |
Ondrej Bajgar | 3 | 110 | 5.45 |
Jan Kleindienst | 4 | 220 | 23.74 |