@inproceedings{liu-etal-2019-reinforced,
title = "Reinforced Training Data Selection for Domain Adaptation",
author = "Liu, Miaofeng and
Song, Yan and
Zou, Hongbin and
Zhang, Tong",
editor = "Korhonen, Anna and
Traum, David and
M\`arquez, Llu\'\i s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1189/",
doi = "10.18653/v1/P19-1189",
pages = "1957--1968",
abstract = "Supervised models suffer from the problem of domain shifting where distribution mismatch in the data across domains greatly affect model performance. To solve the problem, training data selection (TDS) has been proven to be a prospective solution for domain adaptation in leveraging appropriate data. However, conventional TDS methods normally requires a predefined threshold which is neither easy to set nor can be applied across tasks, and models are trained separately with the TDS process. To make TDS self-adapted to data and task, and to combine it with model training, in this paper, we propose a reinforcement learning (RL) framework that synchronously searches for training instances relevant to the target domain and learns better representations for them. A selection distribution generator (SDG) is designed to perform the selection and is updated according to the rewards computed from the selected data, where a predictor is included in the framework to ensure a task-specific model can be trained on the selected data and provides feedback to rewards. Experimental results from part-of-speech tagging, dependency parsing, and sentiment analysis, as well as ablation studies, illustrate that the proposed framework is not only effective in data selection and representation, but also generalized to accommodate different NLP tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2019-reinforced">
<titleInfo>
<title>Reinforced Training Data Selection for Domain Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miaofeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluí</namePart>
<namePart type="given">s</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Supervised models suffer from the problem of domain shifting where distribution mismatch in the data across domains greatly affect model performance. To solve the problem, training data selection (TDS) has been proven to be a prospective solution for domain adaptation in leveraging appropriate data. However, conventional TDS methods normally requires a predefined threshold which is neither easy to set nor can be applied across tasks, and models are trained separately with the TDS process. To make TDS self-adapted to data and task, and to combine it with model training, in this paper, we propose a reinforcement learning (RL) framework that synchronously searches for training instances relevant to the target domain and learns better representations for them. A selection distribution generator (SDG) is designed to perform the selection and is updated according to the rewards computed from the selected data, where a predictor is included in the framework to ensure a task-specific model can be trained on the selected data and provides feedback to rewards. Experimental results from part-of-speech tagging, dependency parsing, and sentiment analysis, as well as ablation studies, illustrate that the proposed framework is not only effective in data selection and representation, but also generalized to accommodate different NLP tasks.</abstract>
<identifier type="citekey">liu-etal-2019-reinforced</identifier>
<identifier type="doi">10.18653/v1/P19-1189</identifier>
<location>
<url>https://aclanthology.org/P19-1189/</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>1957</start>
<end>1968</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reinforced Training Data Selection for Domain Adaptation
%A Liu, Miaofeng
%A Song, Yan
%A Zou, Hongbin
%A Zhang, Tong
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluí s.
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F liu-etal-2019-reinforced
%X Supervised models suffer from the problem of domain shifting where distribution mismatch in the data across domains greatly affect model performance. To solve the problem, training data selection (TDS) has been proven to be a prospective solution for domain adaptation in leveraging appropriate data. However, conventional TDS methods normally requires a predefined threshold which is neither easy to set nor can be applied across tasks, and models are trained separately with the TDS process. To make TDS self-adapted to data and task, and to combine it with model training, in this paper, we propose a reinforcement learning (RL) framework that synchronously searches for training instances relevant to the target domain and learns better representations for them. A selection distribution generator (SDG) is designed to perform the selection and is updated according to the rewards computed from the selected data, where a predictor is included in the framework to ensure a task-specific model can be trained on the selected data and provides feedback to rewards. Experimental results from part-of-speech tagging, dependency parsing, and sentiment analysis, as well as ablation studies, illustrate that the proposed framework is not only effective in data selection and representation, but also generalized to accommodate different NLP tasks.
%R 10.18653/v1/P19-1189
%U https://aclanthology.org/P19-1189/
%U https://doi.org/10.18653/v1/P19-1189
%P 1957-1968
Markdown (Informal)
[Reinforced Training Data Selection for Domain Adaptation](https://aclanthology.org/P19-1189/) (Liu et al., ACL 2019)
ACL
- Miaofeng Liu, Yan Song, Hongbin Zou, and Tong Zhang. 2019. Reinforced Training Data Selection for Domain Adaptation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1957–1968, Florence, Italy. Association for Computational Linguistics.