@inproceedings{aharoni-goldberg-2018-split,
title = "Split and Rephrase: Better Evaluation and Stronger Baselines",
author = "Aharoni, Roee and
Goldberg, Yoav",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2114",
doi = "10.18653/v1/P18-2114",
pages = "719--724",
abstract = "Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017), they suffer from memorization of the training set which contains more than 89{\%} of the unique simple sentences from the validation and test sets. To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8.68 BLEU and fostering further progress on the task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aharoni-goldberg-2018-split">
<titleInfo>
<title>Split and Rephrase: Better Evaluation and Stronger Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roee</namePart>
<namePart type="family">Aharoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017), they suffer from memorization of the training set which contains more than 89% of the unique simple sentences from the validation and test sets. To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8.68 BLEU and fostering further progress on the task.</abstract>
<identifier type="citekey">aharoni-goldberg-2018-split</identifier>
<identifier type="doi">10.18653/v1/P18-2114</identifier>
<location>
<url>https://aclanthology.org/P18-2114</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>719</start>
<end>724</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Split and Rephrase: Better Evaluation and Stronger Baselines
%A Aharoni, Roee
%A Goldberg, Yoav
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F aharoni-goldberg-2018-split
%X Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017), they suffer from memorization of the training set which contains more than 89% of the unique simple sentences from the validation and test sets. To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8.68 BLEU and fostering further progress on the task.
%R 10.18653/v1/P18-2114
%U https://aclanthology.org/P18-2114
%U https://doi.org/10.18653/v1/P18-2114
%P 719-724
Markdown (Informal)
[Split and Rephrase: Better Evaluation and Stronger Baselines](https://aclanthology.org/P18-2114) (Aharoni & Goldberg, ACL 2018)
ACL