Text Understanding with the Attention Sum Reader Network

Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, Jan Kleindienst
3/4/2016
cs.CL

Official code: rkadlec/asreader (98 stars, last commit 2016-09-09).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

rkadlec/asreaderOfficial100%

This is an implementation of the Attention Sum Reader model as presented in "Text Comprehension with the Attention Sum Reader Network" available at http://arxiv.org/abs/1603.01547.

9831Shell, PythonJun 6, 201610 years agoNOASSERTION

Similar Papers

SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

86% match1 repo1812017

Generator-Retriever-Generator Approach for Open-Domain Question Answering

84% match1 repo102023

Question Answering in Natural Language: the Special Case of Temporal Expressions

83% match2023

SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering

82% match1 repo1912018

BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering

82% match2026

Uncertainty Guided Global Memory Improves Multi-Hop Question Answering

82% match1 repo2023

Cite this paper

@article{kadlec2016text,
  title  = {Text Understanding with the Attention Sum Reader Network},
  author = {Rudolf Kadlec and Martin Schmid and Ondrej Bajgar and Jan Kleindienst},
  year   = {2016},
  eprint = {1603.01547},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1603.01547}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1603.01547.svg)](https://codeofpaper.com/paper/1603.01547)

Discussion