@inproceedings{chen-yang-2021-simple,
title = "Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization",
author = "Chen, Jiaao and
Yang, Diyi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.530",
doi = "10.18653/v1/2021.emnlp-main.530",
pages = "6605--6616",
abstract = "Abstractive conversation summarization has received growing attention while most current state-of-the-art summarization models heavily rely on human-annotated summaries. To reduce the dependence on labeled summaries, in this work, we present a simple yet effective set of Conversational Data Augmentation (CODA) methods for semi-supervised abstractive conversation summarization, such as random swapping/deletion to perturb the discourse relations inside conversations, dialogue-acts-guided insertion to interrupt the development of conversations, and conditional-generation-based substitution to substitute utterances with their paraphrases generated based on the conversation context. To further utilize unlabeled conversations, we combine CODA with two-stage noisy self-training where we first pre-train the summarization model on unlabeled conversations with pseudo summaries and then fine-tune it on labeled conversations. Experiments conducted on the recent conversation summarization datasets demonstrate the effectiveness of our methods over several state-of-the-art data augmentation baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-yang-2021-simple">
<titleInfo>
<title>Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive conversation summarization has received growing attention while most current state-of-the-art summarization models heavily rely on human-annotated summaries. To reduce the dependence on labeled summaries, in this work, we present a simple yet effective set of Conversational Data Augmentation (CODA) methods for semi-supervised abstractive conversation summarization, such as random swapping/deletion to perturb the discourse relations inside conversations, dialogue-acts-guided insertion to interrupt the development of conversations, and conditional-generation-based substitution to substitute utterances with their paraphrases generated based on the conversation context. To further utilize unlabeled conversations, we combine CODA with two-stage noisy self-training where we first pre-train the summarization model on unlabeled conversations with pseudo summaries and then fine-tune it on labeled conversations. Experiments conducted on the recent conversation summarization datasets demonstrate the effectiveness of our methods over several state-of-the-art data augmentation baselines.</abstract>
<identifier type="citekey">chen-yang-2021-simple</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.530</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.530</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>6605</start>
<end>6616</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization
%A Chen, Jiaao
%A Yang, Diyi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F chen-yang-2021-simple
%X Abstractive conversation summarization has received growing attention while most current state-of-the-art summarization models heavily rely on human-annotated summaries. To reduce the dependence on labeled summaries, in this work, we present a simple yet effective set of Conversational Data Augmentation (CODA) methods for semi-supervised abstractive conversation summarization, such as random swapping/deletion to perturb the discourse relations inside conversations, dialogue-acts-guided insertion to interrupt the development of conversations, and conditional-generation-based substitution to substitute utterances with their paraphrases generated based on the conversation context. To further utilize unlabeled conversations, we combine CODA with two-stage noisy self-training where we first pre-train the summarization model on unlabeled conversations with pseudo summaries and then fine-tune it on labeled conversations. Experiments conducted on the recent conversation summarization datasets demonstrate the effectiveness of our methods over several state-of-the-art data augmentation baselines.
%R 10.18653/v1/2021.emnlp-main.530
%U https://aclanthology.org/2021.emnlp-main.530
%U https://doi.org/10.18653/v1/2021.emnlp-main.530
%P 6605-6616
Markdown (Informal)
[Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization](https://aclanthology.org/2021.emnlp-main.530) (Chen & Yang, EMNLP 2021)
ACL