@inproceedings{parvez-etal-2023-retrieval,
title = "Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies",
author = "Parvez, Md Rizwan and
Chi, Jianfeng and
Ahmad, Wasi Uddin and
Tian, Yuan and
Chang, Kai-Wei",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.16",
doi = "10.18653/v1/2023.eacl-main.16",
pages = "201--210",
abstract = "Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user query. Existing labeled datasets are heavily imbalanced (only a few relevant segments), limiting the QA performance in this domain. In this paper, we develop a data augmentation framework based on ensembling retriever models that captures the relevant text segments from unlabeled policy documents and expand the positive examples in the training set. In addition, to improve the diversity and quality of the augmented data, we leverage multiple pre-trained language models (LMs) and cascaded them with noise reduction oracles. Using our augmented data on the PrivacyQA benchmark, we elevate the existing baseline by a large margin (10{\%} F1) and achieve a new state-of-the-art F1 score of 50{\%}. Our ablation studies provide further insights into the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parvez-etal-2023-retrieval">
<titleInfo>
<title>Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Chi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wasi</namePart>
<namePart type="given">Uddin</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user query. Existing labeled datasets are heavily imbalanced (only a few relevant segments), limiting the QA performance in this domain. In this paper, we develop a data augmentation framework based on ensembling retriever models that captures the relevant text segments from unlabeled policy documents and expand the positive examples in the training set. In addition, to improve the diversity and quality of the augmented data, we leverage multiple pre-trained language models (LMs) and cascaded them with noise reduction oracles. Using our augmented data on the PrivacyQA benchmark, we elevate the existing baseline by a large margin (10% F1) and achieve a new state-of-the-art F1 score of 50%. Our ablation studies provide further insights into the effectiveness of our approach.</abstract>
<identifier type="citekey">parvez-etal-2023-retrieval</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.16</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.16</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>201</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies
%A Parvez, Md Rizwan
%A Chi, Jianfeng
%A Ahmad, Wasi Uddin
%A Tian, Yuan
%A Chang, Kai-Wei
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F parvez-etal-2023-retrieval
%X Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user query. Existing labeled datasets are heavily imbalanced (only a few relevant segments), limiting the QA performance in this domain. In this paper, we develop a data augmentation framework based on ensembling retriever models that captures the relevant text segments from unlabeled policy documents and expand the positive examples in the training set. In addition, to improve the diversity and quality of the augmented data, we leverage multiple pre-trained language models (LMs) and cascaded them with noise reduction oracles. Using our augmented data on the PrivacyQA benchmark, we elevate the existing baseline by a large margin (10% F1) and achieve a new state-of-the-art F1 score of 50%. Our ablation studies provide further insights into the effectiveness of our approach.
%R 10.18653/v1/2023.eacl-main.16
%U https://aclanthology.org/2023.eacl-main.16
%U https://doi.org/10.18653/v1/2023.eacl-main.16
%P 201-210
Markdown (Informal)
[Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies](https://aclanthology.org/2023.eacl-main.16) (Parvez et al., EACL 2023)
ACL