@inproceedings{wang-etal-2022-paratag,
title = "{P}ara{T}ag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, {NLG} Evaluation, and Data Augmentation",
author = "Wang, Shuohang and
Xu, Ruochen and
Liu, Yang and
Zhu, Chenguang and
Zeng, Michael",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.479",
doi = "10.18653/v1/2022.emnlp-main.479",
pages = "7111--7122",
abstract = "Paraphrase identification has been formulated as a binary classification task to decide whether two sentences hold a paraphrase relationship. Existing paraphrase datasets only annotate a binary label for each sentence pair. However, after a systematical analysis of existing paraphrase datasets, we found that the degree of paraphrase cannot be well characterized by a single binary label. And the criteria of paraphrase are not even consistent within the same dataset. We hypothesize that such issues would limit the effectiveness of paraphrase models trained on these data. To this end, we propose a novel fine-grained paraphrase annotation schema that labels the minimum spans of tokens in a sentence that don{'}t have the corresponding paraphrases in the other sentence. Under this setting, we frame paraphrasing as a sequence tagging task. We collect 30k sentence pairs in English with the new annotation schema, resulting in the ParaTag dataset. In addition to reporting baseline results on ParaTag using state-of-art language models, we show that ParaTag is especially useful for training an automatic scorer for language generation evaluation. Finally, we train a paraphrase generation model from ParaTag and achieve better data augmentation performance on the GLUE benchmark than other public paraphrasing datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-paratag">
<titleInfo>
<title>ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuohang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrase identification has been formulated as a binary classification task to decide whether two sentences hold a paraphrase relationship. Existing paraphrase datasets only annotate a binary label for each sentence pair. However, after a systematical analysis of existing paraphrase datasets, we found that the degree of paraphrase cannot be well characterized by a single binary label. And the criteria of paraphrase are not even consistent within the same dataset. We hypothesize that such issues would limit the effectiveness of paraphrase models trained on these data. To this end, we propose a novel fine-grained paraphrase annotation schema that labels the minimum spans of tokens in a sentence that don’t have the corresponding paraphrases in the other sentence. Under this setting, we frame paraphrasing as a sequence tagging task. We collect 30k sentence pairs in English with the new annotation schema, resulting in the ParaTag dataset. In addition to reporting baseline results on ParaTag using state-of-art language models, we show that ParaTag is especially useful for training an automatic scorer for language generation evaluation. Finally, we train a paraphrase generation model from ParaTag and achieve better data augmentation performance on the GLUE benchmark than other public paraphrasing datasets.</abstract>
<identifier type="citekey">wang-etal-2022-paratag</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.479</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.479</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7111</start>
<end>7122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data Augmentation
%A Wang, Shuohang
%A Xu, Ruochen
%A Liu, Yang
%A Zhu, Chenguang
%A Zeng, Michael
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-etal-2022-paratag
%X Paraphrase identification has been formulated as a binary classification task to decide whether two sentences hold a paraphrase relationship. Existing paraphrase datasets only annotate a binary label for each sentence pair. However, after a systematical analysis of existing paraphrase datasets, we found that the degree of paraphrase cannot be well characterized by a single binary label. And the criteria of paraphrase are not even consistent within the same dataset. We hypothesize that such issues would limit the effectiveness of paraphrase models trained on these data. To this end, we propose a novel fine-grained paraphrase annotation schema that labels the minimum spans of tokens in a sentence that don’t have the corresponding paraphrases in the other sentence. Under this setting, we frame paraphrasing as a sequence tagging task. We collect 30k sentence pairs in English with the new annotation schema, resulting in the ParaTag dataset. In addition to reporting baseline results on ParaTag using state-of-art language models, we show that ParaTag is especially useful for training an automatic scorer for language generation evaluation. Finally, we train a paraphrase generation model from ParaTag and achieve better data augmentation performance on the GLUE benchmark than other public paraphrasing datasets.
%R 10.18653/v1/2022.emnlp-main.479
%U https://aclanthology.org/2022.emnlp-main.479
%U https://doi.org/10.18653/v1/2022.emnlp-main.479
%P 7111-7122
Markdown (Informal)
[ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data Augmentation](https://aclanthology.org/2022.emnlp-main.479) (Wang et al., EMNLP 2022)
ACL