@inproceedings{p-v-s-meyer-2019-data,
title = "Data-efficient Neural Text Compression with Interactive Learning",
author = "P.V.S, Avinesh and
Meyer, Christian M.",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1262",
doi = "10.18653/v1/N19-1262",
pages = "2543--2554",
abstract = "Neural sequence-to-sequence models have been successfully applied to text compression. However, these models were trained on huge automatically induced parallel corpora, which are only available for a few domains and tasks. In this paper, we propose a novel interactive setup to neural text compression that enables transferring a model to new domains and compression tasks with minimal human supervision. This is achieved by employing active learning, which intelligently samples from a large pool of unlabeled data. Using this setup, we can successfully adapt a model trained on small data of 40k samples for a headline generation task to a general text compression dataset at an acceptable compression quality with just 500 sampled instances annotated by a human.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="p-v-s-meyer-2019-data">
<titleInfo>
<title>Data-efficient Neural Text Compression with Interactive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avinesh</namePart>
<namePart type="family">P.V.S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural sequence-to-sequence models have been successfully applied to text compression. However, these models were trained on huge automatically induced parallel corpora, which are only available for a few domains and tasks. In this paper, we propose a novel interactive setup to neural text compression that enables transferring a model to new domains and compression tasks with minimal human supervision. This is achieved by employing active learning, which intelligently samples from a large pool of unlabeled data. Using this setup, we can successfully adapt a model trained on small data of 40k samples for a headline generation task to a general text compression dataset at an acceptable compression quality with just 500 sampled instances annotated by a human.</abstract>
<identifier type="citekey">p-v-s-meyer-2019-data</identifier>
<identifier type="doi">10.18653/v1/N19-1262</identifier>
<location>
<url>https://aclanthology.org/N19-1262</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2543</start>
<end>2554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data-efficient Neural Text Compression with Interactive Learning
%A P.V.S, Avinesh
%A Meyer, Christian M.
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F p-v-s-meyer-2019-data
%X Neural sequence-to-sequence models have been successfully applied to text compression. However, these models were trained on huge automatically induced parallel corpora, which are only available for a few domains and tasks. In this paper, we propose a novel interactive setup to neural text compression that enables transferring a model to new domains and compression tasks with minimal human supervision. This is achieved by employing active learning, which intelligently samples from a large pool of unlabeled data. Using this setup, we can successfully adapt a model trained on small data of 40k samples for a headline generation task to a general text compression dataset at an acceptable compression quality with just 500 sampled instances annotated by a human.
%R 10.18653/v1/N19-1262
%U https://aclanthology.org/N19-1262
%U https://doi.org/10.18653/v1/N19-1262
%P 2543-2554
Markdown (Informal)
[Data-efficient Neural Text Compression with Interactive Learning](https://aclanthology.org/N19-1262) (P.V.S & Meyer, NAACL 2019)
ACL
- Avinesh P.V.S and Christian M. Meyer. 2019. Data-efficient Neural Text Compression with Interactive Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2543–2554, Minneapolis, Minnesota. Association for Computational Linguistics.