@inproceedings{nangi-etal-2021-autosumm,
title = "{AUTOSUMM}: Automatic Model Creation for Text Summarization",
author = "Nangi, Sharmila Reddy and
Tyagi, Atharv and
Mundra, Jay and
Mukherjee, Sagnik and
Snehal, Raj and
Chhaya, Niyati and
Garimella, Aparna",
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.798",
doi = "10.18653/v1/2021.emnlp-main.798",
pages = "10162--10172",
abstract = "Recent efforts to develop deep learning models for text generation tasks such as extractive and abstractive summarization have resulted in state-of-the-art performances on various datasets. However, obtaining the best model configuration for a given dataset requires an extensive knowledge of deep learning specifics like model architecture, tuning parameters etc., and is often extremely challenging for a non-expert. In this paper, we propose methods to automatically create deep learning models for the tasks of extractive and abstractive text summarization. Based on the recent advances in Automated Machine Learning and the success of large language models such as BERT and GPT-2 in encoding knowledge, we use a combination of Neural Architecture Search (NAS) and Knowledge Distillation (KD) techniques to perform model search and compression using the vast knowledge provided by these language models to develop smaller, customized models for any given dataset. We present extensive empirical results to illustrate the effectiveness of our model creation methods in terms of inference time and model size, while achieving near state-of-the-art performances in terms of accuracy across a range of datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nangi-etal-2021-autosumm">
<titleInfo>
<title>AUTOSUMM: Automatic Model Creation for Text Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sharmila</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Nangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atharv</namePart>
<namePart type="family">Tyagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Mundra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sagnik</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Snehal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niyati</namePart>
<namePart type="family">Chhaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</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>Recent efforts to develop deep learning models for text generation tasks such as extractive and abstractive summarization have resulted in state-of-the-art performances on various datasets. However, obtaining the best model configuration for a given dataset requires an extensive knowledge of deep learning specifics like model architecture, tuning parameters etc., and is often extremely challenging for a non-expert. In this paper, we propose methods to automatically create deep learning models for the tasks of extractive and abstractive text summarization. Based on the recent advances in Automated Machine Learning and the success of large language models such as BERT and GPT-2 in encoding knowledge, we use a combination of Neural Architecture Search (NAS) and Knowledge Distillation (KD) techniques to perform model search and compression using the vast knowledge provided by these language models to develop smaller, customized models for any given dataset. We present extensive empirical results to illustrate the effectiveness of our model creation methods in terms of inference time and model size, while achieving near state-of-the-art performances in terms of accuracy across a range of datasets.</abstract>
<identifier type="citekey">nangi-etal-2021-autosumm</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.798</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.798</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>10162</start>
<end>10172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AUTOSUMM: Automatic Model Creation for Text Summarization
%A Nangi, Sharmila Reddy
%A Tyagi, Atharv
%A Mundra, Jay
%A Mukherjee, Sagnik
%A Snehal, Raj
%A Chhaya, Niyati
%A Garimella, Aparna
%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 nangi-etal-2021-autosumm
%X Recent efforts to develop deep learning models for text generation tasks such as extractive and abstractive summarization have resulted in state-of-the-art performances on various datasets. However, obtaining the best model configuration for a given dataset requires an extensive knowledge of deep learning specifics like model architecture, tuning parameters etc., and is often extremely challenging for a non-expert. In this paper, we propose methods to automatically create deep learning models for the tasks of extractive and abstractive text summarization. Based on the recent advances in Automated Machine Learning and the success of large language models such as BERT and GPT-2 in encoding knowledge, we use a combination of Neural Architecture Search (NAS) and Knowledge Distillation (KD) techniques to perform model search and compression using the vast knowledge provided by these language models to develop smaller, customized models for any given dataset. We present extensive empirical results to illustrate the effectiveness of our model creation methods in terms of inference time and model size, while achieving near state-of-the-art performances in terms of accuracy across a range of datasets.
%R 10.18653/v1/2021.emnlp-main.798
%U https://aclanthology.org/2021.emnlp-main.798
%U https://doi.org/10.18653/v1/2021.emnlp-main.798
%P 10162-10172
Markdown (Informal)
[AUTOSUMM: Automatic Model Creation for Text Summarization](https://aclanthology.org/2021.emnlp-main.798) (Nangi et al., EMNLP 2021)
ACL
- Sharmila Reddy Nangi, Atharv Tyagi, Jay Mundra, Sagnik Mukherjee, Raj Snehal, Niyati Chhaya, and Aparna Garimella. 2021. AUTOSUMM: Automatic Model Creation for Text Summarization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10162–10172, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.