@inproceedings{jun-etal-2022-anna,
title = "{ANNA}: Enhanced Language Representation for Question Answering",
author = "Jun, Changwook and
Jang, Hansol and
Sim, Myoseop and
Kim, Hyun and
Choi, Jooyoung and
Min, Kyungkoo and
Bae, Kyunghoon",
booktitle = "Proceedings of the 7th Workshop on Representation Learning for NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.repl4nlp-1.13",
doi = "10.18653/v1/2022.repl4nlp-1.13",
pages = "121--132",
abstract = "Pre-trained language models have brought significant improvements in performance in a variety of natural language processing tasks. Most existing models performing state-of-the-art results have shown their approaches in the separate perspectives of data processing, pre-training tasks, neural network modeling, or fine-tuning. In this paper, we demonstrate how the approaches affect performance individually, and that the language model performs the best results on a specific question answering task when those approaches are jointly considered in pre-training models. In particular, we propose an extended pre-training task, and a new neighbor-aware mechanism that attends neighboring tokens more to capture the richness of context for pre-training language modeling. Our best model achieves new state-of-the-art results of 95.7{\%} F1 and 90.6{\%} EM on SQuAD 1.1 and also outperforms existing pre-trained language models such as RoBERTa, ALBERT, ELECTRA, and XLNet on the SQuAD 2.0 benchmark.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jun-etal-2022-anna">
<titleInfo>
<title>ANNA: Enhanced Language Representation for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Changwook</namePart>
<namePart type="family">Jun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansol</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myoseop</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jooyoung</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungkoo</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghoon</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Representation Learning for NLP</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models have brought significant improvements in performance in a variety of natural language processing tasks. Most existing models performing state-of-the-art results have shown their approaches in the separate perspectives of data processing, pre-training tasks, neural network modeling, or fine-tuning. In this paper, we demonstrate how the approaches affect performance individually, and that the language model performs the best results on a specific question answering task when those approaches are jointly considered in pre-training models. In particular, we propose an extended pre-training task, and a new neighbor-aware mechanism that attends neighboring tokens more to capture the richness of context for pre-training language modeling. Our best model achieves new state-of-the-art results of 95.7% F1 and 90.6% EM on SQuAD 1.1 and also outperforms existing pre-trained language models such as RoBERTa, ALBERT, ELECTRA, and XLNet on the SQuAD 2.0 benchmark.</abstract>
<identifier type="citekey">jun-etal-2022-anna</identifier>
<identifier type="doi">10.18653/v1/2022.repl4nlp-1.13</identifier>
<location>
<url>https://aclanthology.org/2022.repl4nlp-1.13</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>121</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ANNA: Enhanced Language Representation for Question Answering
%A Jun, Changwook
%A Jang, Hansol
%A Sim, Myoseop
%A Kim, Hyun
%A Choi, Jooyoung
%A Min, Kyungkoo
%A Bae, Kyunghoon
%S Proceedings of the 7th Workshop on Representation Learning for NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F jun-etal-2022-anna
%X Pre-trained language models have brought significant improvements in performance in a variety of natural language processing tasks. Most existing models performing state-of-the-art results have shown their approaches in the separate perspectives of data processing, pre-training tasks, neural network modeling, or fine-tuning. In this paper, we demonstrate how the approaches affect performance individually, and that the language model performs the best results on a specific question answering task when those approaches are jointly considered in pre-training models. In particular, we propose an extended pre-training task, and a new neighbor-aware mechanism that attends neighboring tokens more to capture the richness of context for pre-training language modeling. Our best model achieves new state-of-the-art results of 95.7% F1 and 90.6% EM on SQuAD 1.1 and also outperforms existing pre-trained language models such as RoBERTa, ALBERT, ELECTRA, and XLNet on the SQuAD 2.0 benchmark.
%R 10.18653/v1/2022.repl4nlp-1.13
%U https://aclanthology.org/2022.repl4nlp-1.13
%U https://doi.org/10.18653/v1/2022.repl4nlp-1.13
%P 121-132
Markdown (Informal)
[ANNA: Enhanced Language Representation for Question Answering](https://aclanthology.org/2022.repl4nlp-1.13) (Jun et al., RepL4NLP 2022)
ACL
- Changwook Jun, Hansol Jang, Myoseop Sim, Hyun Kim, Jooyoung Choi, Kyungkoo Min, and Kyunghoon Bae. 2022. ANNA: Enhanced Language Representation for Question Answering. In Proceedings of the 7th Workshop on Representation Learning for NLP, pages 121–132, Dublin, Ireland. Association for Computational Linguistics.