@inproceedings{ma-etal-2019-domain,
title = "Domain Adaptation with {BERT}-based Domain Classification and Data Selection",
author = "Ma, Xiaofei and
Xu, Peng and
Wang, Zhiguo and
Nallapati, Ramesh and
Xiang, Bing",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6109",
doi = "10.18653/v1/D19-6109",
pages = "76--83",
abstract = "The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data. For example, the pre-trained BERT model can be easily fine-tuned with just one additional output layer to create a state-of-the-art model for a wide range of tasks. However, the fine-tuned BERT model suffers considerably at zero-shot when applied to a different domain. In this paper, we present a novel two-step domain adaptation framework based on curriculum learning and domain-discriminative data selection. The domain adaptation is conducted in a mostly unsupervised manner using a small target domain validation set for hyper-parameter tuning. We tested the framework on four large public datasets with different domain similarities and task types. Our framework outperforms a popular discrepancy-based domain adaptation method on most transfer tasks while consuming only a fraction of the training budget.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2019-domain">
<titleInfo>
<title>Domain Adaptation with BERT-based Domain Classification and Data Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaofei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Xu</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>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data. For example, the pre-trained BERT model can be easily fine-tuned with just one additional output layer to create a state-of-the-art model for a wide range of tasks. However, the fine-tuned BERT model suffers considerably at zero-shot when applied to a different domain. In this paper, we present a novel two-step domain adaptation framework based on curriculum learning and domain-discriminative data selection. The domain adaptation is conducted in a mostly unsupervised manner using a small target domain validation set for hyper-parameter tuning. We tested the framework on four large public datasets with different domain similarities and task types. Our framework outperforms a popular discrepancy-based domain adaptation method on most transfer tasks while consuming only a fraction of the training budget.</abstract>
<identifier type="citekey">ma-etal-2019-domain</identifier>
<identifier type="doi">10.18653/v1/D19-6109</identifier>
<location>
<url>https://aclanthology.org/D19-6109</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>76</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain Adaptation with BERT-based Domain Classification and Data Selection
%A Ma, Xiaofei
%A Xu, Peng
%A Wang, Zhiguo
%A Nallapati, Ramesh
%A Xiang, Bing
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ma-etal-2019-domain
%X The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data. For example, the pre-trained BERT model can be easily fine-tuned with just one additional output layer to create a state-of-the-art model for a wide range of tasks. However, the fine-tuned BERT model suffers considerably at zero-shot when applied to a different domain. In this paper, we present a novel two-step domain adaptation framework based on curriculum learning and domain-discriminative data selection. The domain adaptation is conducted in a mostly unsupervised manner using a small target domain validation set for hyper-parameter tuning. We tested the framework on four large public datasets with different domain similarities and task types. Our framework outperforms a popular discrepancy-based domain adaptation method on most transfer tasks while consuming only a fraction of the training budget.
%R 10.18653/v1/D19-6109
%U https://aclanthology.org/D19-6109
%U https://doi.org/10.18653/v1/D19-6109
%P 76-83
Markdown (Informal)
[Domain Adaptation with BERT-based Domain Classification and Data Selection](https://aclanthology.org/D19-6109) (Ma et al., 2019)
ACL