@inproceedings{karn-etal-2021-shot,
title = "Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data",
author = {Karn, Sanjeev Kumar and
Chen, Francine and
Chen, Yan-Ying and
Waltinger, Ulli and
Sch{\"u}tze, Hinrich},
editor = "Ben-David, Eyal and
Cohen, Shay and
McDonald, Ryan and
Plank, Barbara and
Reichart, Roi and
Rotman, Guy and
Ziser, Yftah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.24/",
pages = "245--254",
abstract = "Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle the posts by threads and then extract summaries from those threads. A major issue with such systems is error propagation from the disentanglement component. While end-to-end trainable summarization system could obviate explicit disentanglement, such systems require a large amount of labeled data. To address this, we propose to pretrain an end-to-end trainable hierarchical encoder-decoder system using synthetic interleaved texts. We show that by fine-tuning on a real-world meeting dataset (AMI), such a system out-performs a traditional two-step system by 22{\%}. We also compare against transformer models and observed that pretraining with synthetic data both the encoder and decoder outperforms the BertSumExtAbs transformer model which pretrains only the encoder on a large dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karn-etal-2021-shot">
<titleInfo>
<title>Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Karn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francine</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan-Ying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulli</namePart>
<namePart type="family">Waltinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Ben-David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Rotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle the posts by threads and then extract summaries from those threads. A major issue with such systems is error propagation from the disentanglement component. While end-to-end trainable summarization system could obviate explicit disentanglement, such systems require a large amount of labeled data. To address this, we propose to pretrain an end-to-end trainable hierarchical encoder-decoder system using synthetic interleaved texts. We show that by fine-tuning on a real-world meeting dataset (AMI), such a system out-performs a traditional two-step system by 22%. We also compare against transformer models and observed that pretraining with synthetic data both the encoder and decoder outperforms the BertSumExtAbs transformer model which pretrains only the encoder on a large dataset.</abstract>
<identifier type="citekey">karn-etal-2021-shot</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.24/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>245</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data
%A Karn, Sanjeev Kumar
%A Chen, Francine
%A Chen, Yan-Ying
%A Waltinger, Ulli
%A Schütze, Hinrich
%Y Ben-David, Eyal
%Y Cohen, Shay
%Y McDonald, Ryan
%Y Plank, Barbara
%Y Reichart, Roi
%Y Rotman, Guy
%Y Ziser, Yftah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F karn-etal-2021-shot
%X Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle the posts by threads and then extract summaries from those threads. A major issue with such systems is error propagation from the disentanglement component. While end-to-end trainable summarization system could obviate explicit disentanglement, such systems require a large amount of labeled data. To address this, we propose to pretrain an end-to-end trainable hierarchical encoder-decoder system using synthetic interleaved texts. We show that by fine-tuning on a real-world meeting dataset (AMI), such a system out-performs a traditional two-step system by 22%. We also compare against transformer models and observed that pretraining with synthetic data both the encoder and decoder outperforms the BertSumExtAbs transformer model which pretrains only the encoder on a large dataset.
%U https://aclanthology.org/2021.adaptnlp-1.24/
%P 245-254
Markdown (Informal)
[Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data](https://aclanthology.org/2021.adaptnlp-1.24/) (Karn et al., AdaptNLP 2021)
ACL