@inproceedings{tambi-etal-2020-search,
title = "Search Query Language Identification Using Weak Labeling",
author = "Tambi, Ritiz and
Kale, Ajinkya and
King, Tracy Holloway",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.432",
pages = "3520--3527",
abstract = "Language identification is a well-known task for natural language documents. In this paper we explore search query language identification which is usually the first task before any other query understanding. Without loss of generalization, we run our experiments on the Adobe Stock search engine. Even though the domain is relatively generic because Adobe Stock queries cover a broad range of objects and concepts, out-of-the-box language identifiers do not perform well due to the extremely short text found in queries. Unlike other well-studied supervised approaches for this task, we examine a practical approach for the cold start problem for automatically getting large-scale query-language pairs for training. We describe the process of creating weak-labeled training data and then human-annotated evaluation data for the search query language identification task. The effectiveness of this technique is demonstrated by training a gradient boosting model for language classification given a query. We out-perform the open domain text model baselines by a large margin.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tambi-etal-2020-search">
<titleInfo>
<title>Search Query Language Identification Using Weak Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritiz</namePart>
<namePart type="family">Tambi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajinkya</namePart>
<namePart type="family">Kale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tracy</namePart>
<namePart type="given">Holloway</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Language identification is a well-known task for natural language documents. In this paper we explore search query language identification which is usually the first task before any other query understanding. Without loss of generalization, we run our experiments on the Adobe Stock search engine. Even though the domain is relatively generic because Adobe Stock queries cover a broad range of objects and concepts, out-of-the-box language identifiers do not perform well due to the extremely short text found in queries. Unlike other well-studied supervised approaches for this task, we examine a practical approach for the cold start problem for automatically getting large-scale query-language pairs for training. We describe the process of creating weak-labeled training data and then human-annotated evaluation data for the search query language identification task. The effectiveness of this technique is demonstrated by training a gradient boosting model for language classification given a query. We out-perform the open domain text model baselines by a large margin.</abstract>
<identifier type="citekey">tambi-etal-2020-search</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.432</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>3520</start>
<end>3527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Search Query Language Identification Using Weak Labeling
%A Tambi, Ritiz
%A Kale, Ajinkya
%A King, Tracy Holloway
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F tambi-etal-2020-search
%X Language identification is a well-known task for natural language documents. In this paper we explore search query language identification which is usually the first task before any other query understanding. Without loss of generalization, we run our experiments on the Adobe Stock search engine. Even though the domain is relatively generic because Adobe Stock queries cover a broad range of objects and concepts, out-of-the-box language identifiers do not perform well due to the extremely short text found in queries. Unlike other well-studied supervised approaches for this task, we examine a practical approach for the cold start problem for automatically getting large-scale query-language pairs for training. We describe the process of creating weak-labeled training data and then human-annotated evaluation data for the search query language identification task. The effectiveness of this technique is demonstrated by training a gradient boosting model for language classification given a query. We out-perform the open domain text model baselines by a large margin.
%U https://aclanthology.org/2020.lrec-1.432
%P 3520-3527
Markdown (Informal)
[Search Query Language Identification Using Weak Labeling](https://aclanthology.org/2020.lrec-1.432) (Tambi et al., LREC 2020)
ACL