@inproceedings{mittal-etal-2021-distantly,
title = "Distantly Supervised Transformers For {E}-Commerce Product {QA}",
author = "Mittal, Happy and
Chakrabarti, Aniket and
Bayar, Belhassen and
Sharma, Animesh Anant and
Rasiwasia, Nikhil",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.315",
doi = "10.18653/v1/2021.naacl-main.315",
pages = "4008--4017",
abstract = "We propose a practical instant question answering (QA) system on product pages of e-commerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. User queries and CQA pairs differ significantly in language characteristics making relevance learning difficult. Our proposed transformer-based model learns a robust relevance function by jointly learning unified syntactic and semantic representations without the need for human labeled data. This is achieved by distantly supervising our model by distilling from predictions of a syntactic matching system on user queries and simultaneously training with CQA pairs. Training with CQA pairs helps our model learning semantic QA relevance and distant supervision enables learning of syntactic features as well as the nuances of user querying language. Additionally, our model encodes queries and candidate responses independently allowing offline candidate embedding generation thereby minimizing the need for real-time transformer model execution. Consequently, our framework is able to scale to large e-commerce QA traffic. Extensive evaluation on user queries shows that our framework significantly outperforms both syntactic and semantic baselines in offline as well as large scale online A/B setups of a popular e-commerce service.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mittal-etal-2021-distantly">
<titleInfo>
<title>Distantly Supervised Transformers For E-Commerce Product QA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Happy</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aniket</namePart>
<namePart type="family">Chakrabarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Belhassen</namePart>
<namePart type="family">Bayar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="given">Anant</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Rasiwasia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a practical instant question answering (QA) system on product pages of e-commerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. User queries and CQA pairs differ significantly in language characteristics making relevance learning difficult. Our proposed transformer-based model learns a robust relevance function by jointly learning unified syntactic and semantic representations without the need for human labeled data. This is achieved by distantly supervising our model by distilling from predictions of a syntactic matching system on user queries and simultaneously training with CQA pairs. Training with CQA pairs helps our model learning semantic QA relevance and distant supervision enables learning of syntactic features as well as the nuances of user querying language. Additionally, our model encodes queries and candidate responses independently allowing offline candidate embedding generation thereby minimizing the need for real-time transformer model execution. Consequently, our framework is able to scale to large e-commerce QA traffic. Extensive evaluation on user queries shows that our framework significantly outperforms both syntactic and semantic baselines in offline as well as large scale online A/B setups of a popular e-commerce service.</abstract>
<identifier type="citekey">mittal-etal-2021-distantly</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.315</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.315</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4008</start>
<end>4017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distantly Supervised Transformers For E-Commerce Product QA
%A Mittal, Happy
%A Chakrabarti, Aniket
%A Bayar, Belhassen
%A Sharma, Animesh Anant
%A Rasiwasia, Nikhil
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F mittal-etal-2021-distantly
%X We propose a practical instant question answering (QA) system on product pages of e-commerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. User queries and CQA pairs differ significantly in language characteristics making relevance learning difficult. Our proposed transformer-based model learns a robust relevance function by jointly learning unified syntactic and semantic representations without the need for human labeled data. This is achieved by distantly supervising our model by distilling from predictions of a syntactic matching system on user queries and simultaneously training with CQA pairs. Training with CQA pairs helps our model learning semantic QA relevance and distant supervision enables learning of syntactic features as well as the nuances of user querying language. Additionally, our model encodes queries and candidate responses independently allowing offline candidate embedding generation thereby minimizing the need for real-time transformer model execution. Consequently, our framework is able to scale to large e-commerce QA traffic. Extensive evaluation on user queries shows that our framework significantly outperforms both syntactic and semantic baselines in offline as well as large scale online A/B setups of a popular e-commerce service.
%R 10.18653/v1/2021.naacl-main.315
%U https://aclanthology.org/2021.naacl-main.315
%U https://doi.org/10.18653/v1/2021.naacl-main.315
%P 4008-4017
Markdown (Informal)
[Distantly Supervised Transformers For E-Commerce Product QA](https://aclanthology.org/2021.naacl-main.315) (Mittal et al., NAACL 2021)
ACL
- Happy Mittal, Aniket Chakrabarti, Belhassen Bayar, Animesh Anant Sharma, and Nikhil Rasiwasia. 2021. Distantly Supervised Transformers For E-Commerce Product QA. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4008–4017, Online. Association for Computational Linguistics.