@inproceedings{zhang-zhao-2021-structural,
title = "Structural Pre-training for Dialogue Comprehension",
author = "Zhang, Zhuosheng and
Zhao, Hai",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.399",
doi = "10.18653/v1/2021.acl-long.399",
pages = "5134--5145",
abstract = "Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training. However, even with the help of the powerful PrLMs, it is still challenging to effectively capture task-related knowledge from dialogue texts which are enriched by correlations among speaker-aware utterances. In this work, we present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives: 1) utterance order restoration, which predicts the order of the permuted utterances in dialogue context; 2) sentence backbone regularization, which regularizes the model to improve the factual correctness of summarized subject-verb-object triplets. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-zhao-2021-structural">
<titleInfo>
<title>Structural Pre-training for Dialogue Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuosheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training. However, even with the help of the powerful PrLMs, it is still challenging to effectively capture task-related knowledge from dialogue texts which are enriched by correlations among speaker-aware utterances. In this work, we present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives: 1) utterance order restoration, which predicts the order of the permuted utterances in dialogue context; 2) sentence backbone regularization, which regularizes the model to improve the factual correctness of summarized subject-verb-object triplets. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.</abstract>
<identifier type="citekey">zhang-zhao-2021-structural</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.399</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.399</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>5134</start>
<end>5145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structural Pre-training for Dialogue Comprehension
%A Zhang, Zhuosheng
%A Zhao, Hai
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F zhang-zhao-2021-structural
%X Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training. However, even with the help of the powerful PrLMs, it is still challenging to effectively capture task-related knowledge from dialogue texts which are enriched by correlations among speaker-aware utterances. In this work, we present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives: 1) utterance order restoration, which predicts the order of the permuted utterances in dialogue context; 2) sentence backbone regularization, which regularizes the model to improve the factual correctness of summarized subject-verb-object triplets. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.
%R 10.18653/v1/2021.acl-long.399
%U https://aclanthology.org/2021.acl-long.399
%U https://doi.org/10.18653/v1/2021.acl-long.399
%P 5134-5145
Markdown (Informal)
[Structural Pre-training for Dialogue Comprehension](https://aclanthology.org/2021.acl-long.399) (Zhang & Zhao, ACL-IJCNLP 2021)
ACL
- Zhuosheng Zhang and Hai Zhao. 2021. Structural Pre-training for Dialogue Comprehension. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5134–5145, Online. Association for Computational Linguistics.