@inproceedings{shakeri-etal-2020-end,
title = "End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems",
author = "Shakeri, Siamak and
Nogueira dos Santos, Cicero and
Zhu, Henghui and
Ng, Patrick and
Nan, Feng and
Wang, Zhiguo and
Nallapati, Ramesh and
Xiang, Bing",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.439/",
doi = "10.18653/v1/2020.emnlp-main.439",
pages = "5445--5460",
abstract = "We propose an end-to-end approach for synthetic QA data generation. Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate both answers and questions. In a nutshell, we feed a passage to the encoder and ask the decoder to generate a question and an answer token-by-token. The likelihood produced in the generation process is used as a filtering score, which avoids the need for a separate filtering model. Our generator is trained by fine-tuning a pretrained LM using maximum likelihood estimation. The experimental results indicate significant improvements in the domain adaptation of QA models outperforming current state-of-the-art methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shakeri-etal-2020-end">
<titleInfo>
<title>End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siamak</namePart>
<namePart type="family">Shakeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cicero</namePart>
<namePart type="family">Nogueira dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henghui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Nan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiguo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramesh</namePart>
<namePart type="family">Nallapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose an end-to-end approach for synthetic QA data generation. Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate both answers and questions. In a nutshell, we feed a passage to the encoder and ask the decoder to generate a question and an answer token-by-token. The likelihood produced in the generation process is used as a filtering score, which avoids the need for a separate filtering model. Our generator is trained by fine-tuning a pretrained LM using maximum likelihood estimation. The experimental results indicate significant improvements in the domain adaptation of QA models outperforming current state-of-the-art methods.</abstract>
<identifier type="citekey">shakeri-etal-2020-end</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.439</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.439/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5445</start>
<end>5460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems
%A Shakeri, Siamak
%A Nogueira dos Santos, Cicero
%A Zhu, Henghui
%A Ng, Patrick
%A Nan, Feng
%A Wang, Zhiguo
%A Nallapati, Ramesh
%A Xiang, Bing
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F shakeri-etal-2020-end
%X We propose an end-to-end approach for synthetic QA data generation. Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate both answers and questions. In a nutshell, we feed a passage to the encoder and ask the decoder to generate a question and an answer token-by-token. The likelihood produced in the generation process is used as a filtering score, which avoids the need for a separate filtering model. Our generator is trained by fine-tuning a pretrained LM using maximum likelihood estimation. The experimental results indicate significant improvements in the domain adaptation of QA models outperforming current state-of-the-art methods.
%R 10.18653/v1/2020.emnlp-main.439
%U https://aclanthology.org/2020.emnlp-main.439/
%U https://doi.org/10.18653/v1/2020.emnlp-main.439
%P 5445-5460
Markdown (Informal)
[End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems](https://aclanthology.org/2020.emnlp-main.439/) (Shakeri et al., EMNLP 2020)
ACL