@inproceedings{kuzin-etal-2022-query,
title = "Query Processing and Optimization for a Custom Retrieval Language",
author = "Kuzin, Yakov and
Smirnova, Anna and
Slobodkin, Evgeniy and
Chernishev, George",
editor = "Chiticariu, Laura and
Goldberg, Yoav and
Hahn-Powell, Gus and
Morrison, Clayton T. and
Naik, Aakanksha and
Sharp, Rebecca and
Surdeanu, Mihai and
Valenzuela-Esc{\'a}rcega, Marco and
Noriega-Atala, Enrique",
booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.pandl-1.8",
pages = "61--70",
abstract = "Data annotation has been a pressing issue ever since the rise of machine learning and associated areas. It is well-known that obtaining high-quality annotated data incurs high costs, be they financial or time-related. In our previous work, we have proposed a custom, SQL-like retrieval language used to query collections of short documents, such as chat transcripts or tweets. Its main purpose is enabling a human annotator to select {``}situations{''} from such collections, i.e. subsets of documents that are related both thematically and temporally. This language, named Matcher, was prototyped in our custom annotation tool. Entering the next stage of development of the tool, we have tested the prototype implementation. Given the language{'}s rich semantics, many possible execution options with various costs arise. We have found out we could provide tangible improvement in terms of speed and memory consumption by carefully selecting the execution strategy in each particular case. In this work, we present the improved algorithms and proposed optimization methods, as well as a benchmark suite whose results show the significance of the presented techniques. While this is an initial work and not a full-fledged optimization framework, it nevertheless yields good results, providing up to tenfold improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuzin-etal-2022-query">
<titleInfo>
<title>Query Processing and Optimization for a Custom Retrieval Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yakov</namePart>
<namePart type="family">Kuzin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Smirnova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgeniy</namePart>
<namePart type="family">Slobodkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Chernishev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Chiticariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clayton</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Morrison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valenzuela-Escárcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data annotation has been a pressing issue ever since the rise of machine learning and associated areas. It is well-known that obtaining high-quality annotated data incurs high costs, be they financial or time-related. In our previous work, we have proposed a custom, SQL-like retrieval language used to query collections of short documents, such as chat transcripts or tweets. Its main purpose is enabling a human annotator to select “situations” from such collections, i.e. subsets of documents that are related both thematically and temporally. This language, named Matcher, was prototyped in our custom annotation tool. Entering the next stage of development of the tool, we have tested the prototype implementation. Given the language’s rich semantics, many possible execution options with various costs arise. We have found out we could provide tangible improvement in terms of speed and memory consumption by carefully selecting the execution strategy in each particular case. In this work, we present the improved algorithms and proposed optimization methods, as well as a benchmark suite whose results show the significance of the presented techniques. While this is an initial work and not a full-fledged optimization framework, it nevertheless yields good results, providing up to tenfold improvement.</abstract>
<identifier type="citekey">kuzin-etal-2022-query</identifier>
<location>
<url>https://aclanthology.org/2022.pandl-1.8</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>61</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Query Processing and Optimization for a Custom Retrieval Language
%A Kuzin, Yakov
%A Smirnova, Anna
%A Slobodkin, Evgeniy
%A Chernishev, George
%Y Chiticariu, Laura
%Y Goldberg, Yoav
%Y Hahn-Powell, Gus
%Y Morrison, Clayton T.
%Y Naik, Aakanksha
%Y Sharp, Rebecca
%Y Surdeanu, Mihai
%Y Valenzuela-Escárcega, Marco
%Y Noriega-Atala, Enrique
%S Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F kuzin-etal-2022-query
%X Data annotation has been a pressing issue ever since the rise of machine learning and associated areas. It is well-known that obtaining high-quality annotated data incurs high costs, be they financial or time-related. In our previous work, we have proposed a custom, SQL-like retrieval language used to query collections of short documents, such as chat transcripts or tweets. Its main purpose is enabling a human annotator to select “situations” from such collections, i.e. subsets of documents that are related both thematically and temporally. This language, named Matcher, was prototyped in our custom annotation tool. Entering the next stage of development of the tool, we have tested the prototype implementation. Given the language’s rich semantics, many possible execution options with various costs arise. We have found out we could provide tangible improvement in terms of speed and memory consumption by carefully selecting the execution strategy in each particular case. In this work, we present the improved algorithms and proposed optimization methods, as well as a benchmark suite whose results show the significance of the presented techniques. While this is an initial work and not a full-fledged optimization framework, it nevertheless yields good results, providing up to tenfold improvement.
%U https://aclanthology.org/2022.pandl-1.8
%P 61-70
Markdown (Informal)
[Query Processing and Optimization for a Custom Retrieval Language](https://aclanthology.org/2022.pandl-1.8) (Kuzin et al., PANDL 2022)
ACL
- Yakov Kuzin, Anna Smirnova, Evgeniy Slobodkin, and George Chernishev. 2022. Query Processing and Optimization for a Custom Retrieval Language. In Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning, pages 61–70, Gyeongju, Republic of Korea. International Conference on Computational Linguistics.