TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Question Answering	Children's Book Test	AS reader (greedy)	Accuracy-CN	67.5%	# 6
Question Answering	Children's Book Test	AS reader (greedy)	Accuracy-NE	71%	# 6
Question Answering	Children's Book Test	AS reader (avg)	Accuracy-CN	68.9%	# 5
Question Answering	Children's Book Test	AS reader (avg)	Accuracy-NE	70.6%	# 7
Question Answering	CNN / Daily Mail	AS Reader (ensemble model)	CNN	75.4	# 6
Question Answering	CNN / Daily Mail	AS Reader (ensemble model)	Daily Mail	77.7	# 4
Question Answering	CNN / Daily Mail	AS Reader (single model)	CNN	69.5	# 12
Question Answering	CNN / Daily Mail	AS Reader (single model)	Daily Mail	73.9	# 7
Open-Domain Question Answering	SearchQA	ASR	Unigram Acc	41.3	# 5
Open-Domain Question Answering	SearchQA	ASR	N-gram F1	22.8	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/text-understanding-with-the-attention-sum/question-answering-on-childrens-book-test)](https://paperswithcode.com/sota/question-answering-on-childrens-book-test?p=text-understanding-with-the-attention-sum)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/text-understanding-with-the-attention-sum/open-domain-question-answering-on-searchqa)](https://paperswithcode.com/sota/open-domain-question-answering-on-searchqa?p=text-understanding-with-the-attention-sum)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/text-understanding-with-the-attention-sum/question-answering-on-cnn-daily-mail)](https://paperswithcode.com/sota/question-answering-on-cnn-daily-mail?p=text-understanding-with-the-attention-sum)`

Text Understanding with the Attention Sum Reader Network

ACL 2016 · Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, Jan Kleindienst ·

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.

PDF Abstract ACL 2016 PDF ACL 2016 Abstract

Code

Add Remove Mark official

rkadlec/asreader official

libertatis/mrc-cbt

Tasks

Add Remove

Machine Reading Comprehension

Open-Domain Question Answering

Question Answering

Reading Comprehension

Datasets

CNN/Daily Mail

SearchQA

CBT Children's Book Test PTR_NETS

Results from the Paper

Edit

Ranked #5 on Open-Domain Question Answering on SearchQA (Unigram Acc metric)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Question Answering	Children's Book Test	AS reader (greedy)	Accuracy-CN	67.5%	# 6	Compare
Question Answering	Children's Book Test	AS reader (greedy)	Accuracy-NE	71%	# 6	Compare
Question Answering	Children's Book Test	AS reader (avg)	Accuracy-CN	68.9%	# 5	Compare
Question Answering	Children's Book Test	AS reader (avg)	Accuracy-NE	70.6%	# 7	Compare
Question Answering	CNN / Daily Mail	AS Reader (ensemble model)	CNN	75.4	# 6	Compare
Question Answering	CNN / Daily Mail	AS Reader (ensemble model)	Daily Mail	77.7	# 4	Compare
Question Answering	CNN / Daily Mail	AS Reader (single model)	CNN	69.5	# 12	Compare
Question Answering	CNN / Daily Mail	AS Reader (single model)	Daily Mail	73.9	# 7	Compare
Open-Domain Question Answering	SearchQA	ASR	Unigram Acc	41.3	# 5	Compare
Open-Domain Question Answering	SearchQA	ASR	N-gram F1	22.8	# 5	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Text Understanding with the Attention Sum Reader Network

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove