@inproceedings{brad-etal-2017-dataset,
title = "Dataset for a Neural Natural Language Interface for Databases ({NNLIDB})",
author = "Brad, Florin and
Iacob, Radu Cristian Alexandru and
Hosu, Ionel Alexandru and
Rebedea, Traian",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-1091",
pages = "906--914",
abstract = "Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouraging baseline results on a smaller manually annotated test corpus, obtained using an attention-based sequence-to-sequence neural network.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brad-etal-2017-dataset">
<titleInfo>
<title>Dataset for a Neural Natural Language Interface for Databases (NNLIDB)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florin</namePart>
<namePart type="family">Brad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="given">Cristian</namePart>
<namePart type="given">Alexandru</namePart>
<namePart type="family">Iacob</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ionel</namePart>
<namePart type="given">Alexandru</namePart>
<namePart type="family">Hosu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouraging baseline results on a smaller manually annotated test corpus, obtained using an attention-based sequence-to-sequence neural network.</abstract>
<identifier type="citekey">brad-etal-2017-dataset</identifier>
<location>
<url>https://aclanthology.org/I17-1091</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>906</start>
<end>914</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
%A Brad, Florin
%A Iacob, Radu Cristian Alexandru
%A Hosu, Ionel Alexandru
%A Rebedea, Traian
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F brad-etal-2017-dataset
%X Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouraging baseline results on a smaller manually annotated test corpus, obtained using an attention-based sequence-to-sequence neural network.
%U https://aclanthology.org/I17-1091
%P 906-914
Markdown (Informal)
[Dataset for a Neural Natural Language Interface for Databases (NNLIDB)](https://aclanthology.org/I17-1091) (Brad et al., IJCNLP 2017)
ACL
- Florin Brad, Radu Cristian Alexandru Iacob, Ionel Alexandru Hosu, and Traian Rebedea. 2017. Dataset for a Neural Natural Language Interface for Databases (NNLIDB). In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 906–914, Taipei, Taiwan. Asian Federation of Natural Language Processing.