@inproceedings{kew-volk-2022-improving,
title = "Improving Specificity in Review Response Generation with Data-Driven Data Filtering",
author = "Kew, Tannon and
Volk, Martin",
booktitle = "Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ecnlp-1.15",
doi = "10.18653/v1/2022.ecnlp-1.15",
pages = "121--133",
abstract = "Responding to online customer reviews has become an essential part of successfully managing and growing a business both in e-commerce and the hospitality and tourism sectors. Recently, neural text generation methods intended to assist authors in composing responses have been shown to deliver highly fluent and natural looking texts. However, they also tend to learn a strong, undesirable bias towards generating overly generic, one-size-fits-all outputs to a wide range of inputs. While this often results in {`}safe{'}, high-probability responses, there are many practical settings in which greater specificity is preferable. In this work we examine the task of generating more specific responses for online reviews in the hospitality domain by identifying generic responses in the training data, filtering them and fine-tuning the generation model. We experiment with a range of data-driven filtering methods and show through automatic and human evaluation that, despite a 60{\%} reduction in the amount of training data, filtering helps to derive models that are capable of generating more specific, useful responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kew-volk-2022-improving">
<titleInfo>
<title>Improving Specificity in Review Response Generation with Data-Driven Data Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tannon</namePart>
<namePart type="family">Kew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Responding to online customer reviews has become an essential part of successfully managing and growing a business both in e-commerce and the hospitality and tourism sectors. Recently, neural text generation methods intended to assist authors in composing responses have been shown to deliver highly fluent and natural looking texts. However, they also tend to learn a strong, undesirable bias towards generating overly generic, one-size-fits-all outputs to a wide range of inputs. While this often results in ‘safe’, high-probability responses, there are many practical settings in which greater specificity is preferable. In this work we examine the task of generating more specific responses for online reviews in the hospitality domain by identifying generic responses in the training data, filtering them and fine-tuning the generation model. We experiment with a range of data-driven filtering methods and show through automatic and human evaluation that, despite a 60% reduction in the amount of training data, filtering helps to derive models that are capable of generating more specific, useful responses.</abstract>
<identifier type="citekey">kew-volk-2022-improving</identifier>
<identifier type="doi">10.18653/v1/2022.ecnlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.ecnlp-1.15</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>121</start>
<end>133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Specificity in Review Response Generation with Data-Driven Data Filtering
%A Kew, Tannon
%A Volk, Martin
%S Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kew-volk-2022-improving
%X Responding to online customer reviews has become an essential part of successfully managing and growing a business both in e-commerce and the hospitality and tourism sectors. Recently, neural text generation methods intended to assist authors in composing responses have been shown to deliver highly fluent and natural looking texts. However, they also tend to learn a strong, undesirable bias towards generating overly generic, one-size-fits-all outputs to a wide range of inputs. While this often results in ‘safe’, high-probability responses, there are many practical settings in which greater specificity is preferable. In this work we examine the task of generating more specific responses for online reviews in the hospitality domain by identifying generic responses in the training data, filtering them and fine-tuning the generation model. We experiment with a range of data-driven filtering methods and show through automatic and human evaluation that, despite a 60% reduction in the amount of training data, filtering helps to derive models that are capable of generating more specific, useful responses.
%R 10.18653/v1/2022.ecnlp-1.15
%U https://aclanthology.org/2022.ecnlp-1.15
%U https://doi.org/10.18653/v1/2022.ecnlp-1.15
%P 121-133
Markdown (Informal)
[Improving Specificity in Review Response Generation with Data-Driven Data Filtering](https://aclanthology.org/2022.ecnlp-1.15) (Kew & Volk, ECNLP 2022)
ACL