@inproceedings{varanasi-etal-2020-copybert,
title = "{C}opy{BERT}: A Unified Approach to Question Generation with Self-Attention",
author = "Varanasi, Stalin and
Amin, Saadullah and
Neumann, Guenter",
editor = "Wen, Tsung-Hsien and
Celikyilmaz, Asli and
Yu, Zhou and
Papangelis, Alexandros and
Eric, Mihail and
Kumar, Anuj and
Casanueva, I{\~n}igo and
Shah, Rushin",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlp4convai-1.3",
doi = "10.18653/v1/2020.nlp4convai-1.3",
pages = "25--31",
abstract = "Contextualized word embeddings provide better initialization for neural networks that deal with various natural language understanding (NLU) tasks including Question Answering (QA) and more recently, Question Generation(QG). Apart from providing meaningful word representations, pre-trained transformer models (Vaswani et al., 2017), such as BERT (Devlin et al., 2019) also provide self-attentions which encode syntactic information that can be probed for dependency parsing (Hewitt and Manning, 2019) and POStagging (Coenen et al., 2019). In this paper, we show that the information from selfattentions of BERT are useful for language modeling of questions conditioned on paragraph and answer phrases. To control the attention span, we use semi-diagonal mask and utilize a shared model for encoding and decoding, unlike sequence-to-sequence. We further employ copy-mechanism over self-attentions to acheive state-of-the-art results for Question Generation on SQuAD v1.1 (Rajpurkar et al., 2016).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varanasi-etal-2020-copybert">
<titleInfo>
<title>CopyBERT: A Unified Approach to Question Generation with Self-Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stalin</namePart>
<namePart type="family">Varanasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saadullah</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guenter</namePart>
<namePart type="family">Neumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rushin</namePart>
<namePart type="family">Shah</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>Contextualized word embeddings provide better initialization for neural networks that deal with various natural language understanding (NLU) tasks including Question Answering (QA) and more recently, Question Generation(QG). Apart from providing meaningful word representations, pre-trained transformer models (Vaswani et al., 2017), such as BERT (Devlin et al., 2019) also provide self-attentions which encode syntactic information that can be probed for dependency parsing (Hewitt and Manning, 2019) and POStagging (Coenen et al., 2019). In this paper, we show that the information from selfattentions of BERT are useful for language modeling of questions conditioned on paragraph and answer phrases. To control the attention span, we use semi-diagonal mask and utilize a shared model for encoding and decoding, unlike sequence-to-sequence. We further employ copy-mechanism over self-attentions to acheive state-of-the-art results for Question Generation on SQuAD v1.1 (Rajpurkar et al., 2016).</abstract>
<identifier type="citekey">varanasi-etal-2020-copybert</identifier>
<identifier type="doi">10.18653/v1/2020.nlp4convai-1.3</identifier>
<location>
<url>https://aclanthology.org/2020.nlp4convai-1.3</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>25</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CopyBERT: A Unified Approach to Question Generation with Self-Attention
%A Varanasi, Stalin
%A Amin, Saadullah
%A Neumann, Guenter
%Y Wen, Tsung-Hsien
%Y Celikyilmaz, Asli
%Y Yu, Zhou
%Y Papangelis, Alexandros
%Y Eric, Mihail
%Y Kumar, Anuj
%Y Casanueva, Iñigo
%Y Shah, Rushin
%S Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F varanasi-etal-2020-copybert
%X Contextualized word embeddings provide better initialization for neural networks that deal with various natural language understanding (NLU) tasks including Question Answering (QA) and more recently, Question Generation(QG). Apart from providing meaningful word representations, pre-trained transformer models (Vaswani et al., 2017), such as BERT (Devlin et al., 2019) also provide self-attentions which encode syntactic information that can be probed for dependency parsing (Hewitt and Manning, 2019) and POStagging (Coenen et al., 2019). In this paper, we show that the information from selfattentions of BERT are useful for language modeling of questions conditioned on paragraph and answer phrases. To control the attention span, we use semi-diagonal mask and utilize a shared model for encoding and decoding, unlike sequence-to-sequence. We further employ copy-mechanism over self-attentions to acheive state-of-the-art results for Question Generation on SQuAD v1.1 (Rajpurkar et al., 2016).
%R 10.18653/v1/2020.nlp4convai-1.3
%U https://aclanthology.org/2020.nlp4convai-1.3
%U https://doi.org/10.18653/v1/2020.nlp4convai-1.3
%P 25-31
Markdown (Informal)
[CopyBERT: A Unified Approach to Question Generation with Self-Attention](https://aclanthology.org/2020.nlp4convai-1.3) (Varanasi et al., NLP4ConvAI 2020)
ACL