@inproceedings{moon-okazaki-2020-patchbert,
title = "{P}atch{BERT}: Just-in-Time, Out-of-Vocabulary Patching",
author = "Moon, Sangwhan and
Okazaki, Naoaki",
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.631",
doi = "10.18653/v1/2020.emnlp-main.631",
pages = "7846--7852",
abstract = "Large scale pre-trained language models have shown groundbreaking performance improvements for transfer learning in the domain of natural language processing. In our paper, we study a pre-trained multilingual BERT model and analyze the OOV rate on downstream tasks, how it introduces information loss, and as a side-effect, obstructs the potential of the underlying model. We then propose multiple approaches for mitigation and demonstrate that it improves performance with the same parameter count when combined with fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moon-okazaki-2020-patchbert">
<titleInfo>
<title>PatchBERT: Just-in-Time, Out-of-Vocabulary Patching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sangwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>Large scale pre-trained language models have shown groundbreaking performance improvements for transfer learning in the domain of natural language processing. In our paper, we study a pre-trained multilingual BERT model and analyze the OOV rate on downstream tasks, how it introduces information loss, and as a side-effect, obstructs the potential of the underlying model. We then propose multiple approaches for mitigation and demonstrate that it improves performance with the same parameter count when combined with fine-tuning.</abstract>
<identifier type="citekey">moon-okazaki-2020-patchbert</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.631</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.631</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>7846</start>
<end>7852</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PatchBERT: Just-in-Time, Out-of-Vocabulary Patching
%A Moon, Sangwhan
%A Okazaki, Naoaki
%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 moon-okazaki-2020-patchbert
%X Large scale pre-trained language models have shown groundbreaking performance improvements for transfer learning in the domain of natural language processing. In our paper, we study a pre-trained multilingual BERT model and analyze the OOV rate on downstream tasks, how it introduces information loss, and as a side-effect, obstructs the potential of the underlying model. We then propose multiple approaches for mitigation and demonstrate that it improves performance with the same parameter count when combined with fine-tuning.
%R 10.18653/v1/2020.emnlp-main.631
%U https://aclanthology.org/2020.emnlp-main.631
%U https://doi.org/10.18653/v1/2020.emnlp-main.631
%P 7846-7852
Markdown (Informal)
[PatchBERT: Just-in-Time, Out-of-Vocabulary Patching](https://aclanthology.org/2020.emnlp-main.631) (Moon & Okazaki, EMNLP 2020)
ACL
- Sangwhan Moon and Naoaki Okazaki. 2020. PatchBERT: Just-in-Time, Out-of-Vocabulary Patching. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7846–7852, Online. Association for Computational Linguistics.