@inproceedings{petrovski-etal-2018-embedding,
title = "Embedding Individual Table Columns for Resilient {SQL} Chatbots",
author = "Petrovski, Bojan and
Aguado, Ignacio and
Hossmann, Andreea and
Baeriswyl, Michael and
Musat, Claudiu",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop {SCAI}: The 2nd International Workshop on Search-Oriented Conversational {AI}",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5710",
doi = "10.18653/v1/W18-5710",
pages = "67--73",
abstract = "Most of the world{'}s data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language Processing (NLP) aims to alleviate this problem by automatically translating natural language questions into SQL queries. While the proposed solutions are a great start, they lack robustness and do not easily generalize: the methods require high quality descriptions of the database table columns, and the most widely used training dataset, WikiSQL, is heavily biased towards using those descriptions as part of the questions. In this work, we propose solutions to both problems: we entirely eliminate the need for column descriptions, by relying solely on their contents, and we augment the WikiSQL dataset by paraphrasing column names to reduce bias. We show that the accuracy of existing methods drops when trained on our augmented, column-agnostic dataset, and that our own method reaches state of the art accuracy, while relying on column contents only.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrovski-etal-2018-embedding">
<titleInfo>
<title>Embedding Individual Table Columns for Resilient SQL Chatbots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bojan</namePart>
<namePart type="family">Petrovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Aguado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreea</namePart>
<namePart type="family">Hossmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Baeriswyl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudiu</namePart>
<namePart type="family">Musat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most of the world’s data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language Processing (NLP) aims to alleviate this problem by automatically translating natural language questions into SQL queries. While the proposed solutions are a great start, they lack robustness and do not easily generalize: the methods require high quality descriptions of the database table columns, and the most widely used training dataset, WikiSQL, is heavily biased towards using those descriptions as part of the questions. In this work, we propose solutions to both problems: we entirely eliminate the need for column descriptions, by relying solely on their contents, and we augment the WikiSQL dataset by paraphrasing column names to reduce bias. We show that the accuracy of existing methods drops when trained on our augmented, column-agnostic dataset, and that our own method reaches state of the art accuracy, while relying on column contents only.</abstract>
<identifier type="citekey">petrovski-etal-2018-embedding</identifier>
<identifier type="doi">10.18653/v1/W18-5710</identifier>
<location>
<url>https://aclanthology.org/W18-5710</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>67</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Embedding Individual Table Columns for Resilient SQL Chatbots
%A Petrovski, Bojan
%A Aguado, Ignacio
%A Hossmann, Andreea
%A Baeriswyl, Michael
%A Musat, Claudiu
%S Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Brussels, Belgium
%F petrovski-etal-2018-embedding
%X Most of the world’s data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language Processing (NLP) aims to alleviate this problem by automatically translating natural language questions into SQL queries. While the proposed solutions are a great start, they lack robustness and do not easily generalize: the methods require high quality descriptions of the database table columns, and the most widely used training dataset, WikiSQL, is heavily biased towards using those descriptions as part of the questions. In this work, we propose solutions to both problems: we entirely eliminate the need for column descriptions, by relying solely on their contents, and we augment the WikiSQL dataset by paraphrasing column names to reduce bias. We show that the accuracy of existing methods drops when trained on our augmented, column-agnostic dataset, and that our own method reaches state of the art accuracy, while relying on column contents only.
%R 10.18653/v1/W18-5710
%U https://aclanthology.org/W18-5710
%U https://doi.org/10.18653/v1/W18-5710
%P 67-73
Markdown (Informal)
[Embedding Individual Table Columns for Resilient SQL Chatbots](https://aclanthology.org/W18-5710) (Petrovski et al., 2018)
ACL
- Bojan Petrovski, Ignacio Aguado, Andreea Hossmann, Michael Baeriswyl, and Claudiu Musat. 2018. Embedding Individual Table Columns for Resilient SQL Chatbots. In Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 67–73, Brussels, Belgium. Association for Computational Linguistics.