@inproceedings{xiang-etal-2022-connprompt,
title = "{C}onn{P}rompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition",
author = "Xiang, Wei and
Wang, Zhenglin and
Dai, Lu and
Wang, Bang",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.75",
pages = "902--911",
abstract = "Implicit Discourse Relation Recognition (IDRR) is to detect and classify relation sense between two text segments without an explicit connective. Vanilla pre-train and fine-tuning paradigm builds upon a Pre-trained Language Model (PLM) with a task-specific neural network. However, the task objective functions are often not in accordance with that of the PLM. Furthermore, this paradigm cannot well exploit some linguistic evidence embedded in the pre-training process. The recent pre-train, prompt, and predict paradigm selects appropriate prompts to reformulate downstream tasks, so as to utilizing the PLM itself for prediction. However, for its success applications, prompts, verbalizer as well as model training should still be carefully designed for different tasks. As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task. Specifically, we design two styles of ConnPrompt template: Insert-cloze Prompt (ICP) and Prefix-cloze Prompt (PCP) and construct an answer space mapping to the relation senses based on the hierarchy sense tags and implicit connectives. Furthermore, we use a multi-prompt ensemble to fuse predictions from different prompting results. Experiments on the PDTB corpus show that our method significantly outperforms the state-of-the-art algorithms, even with fewer training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiang-etal-2022-connprompt">
<titleInfo>
<title>ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenglin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Implicit Discourse Relation Recognition (IDRR) is to detect and classify relation sense between two text segments without an explicit connective. Vanilla pre-train and fine-tuning paradigm builds upon a Pre-trained Language Model (PLM) with a task-specific neural network. However, the task objective functions are often not in accordance with that of the PLM. Furthermore, this paradigm cannot well exploit some linguistic evidence embedded in the pre-training process. The recent pre-train, prompt, and predict paradigm selects appropriate prompts to reformulate downstream tasks, so as to utilizing the PLM itself for prediction. However, for its success applications, prompts, verbalizer as well as model training should still be carefully designed for different tasks. As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task. Specifically, we design two styles of ConnPrompt template: Insert-cloze Prompt (ICP) and Prefix-cloze Prompt (PCP) and construct an answer space mapping to the relation senses based on the hierarchy sense tags and implicit connectives. Furthermore, we use a multi-prompt ensemble to fuse predictions from different prompting results. Experiments on the PDTB corpus show that our method significantly outperforms the state-of-the-art algorithms, even with fewer training data.</abstract>
<identifier type="citekey">xiang-etal-2022-connprompt</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.75</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>902</start>
<end>911</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition
%A Xiang, Wei
%A Wang, Zhenglin
%A Dai, Lu
%A Wang, Bang
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F xiang-etal-2022-connprompt
%X Implicit Discourse Relation Recognition (IDRR) is to detect and classify relation sense between two text segments without an explicit connective. Vanilla pre-train and fine-tuning paradigm builds upon a Pre-trained Language Model (PLM) with a task-specific neural network. However, the task objective functions are often not in accordance with that of the PLM. Furthermore, this paradigm cannot well exploit some linguistic evidence embedded in the pre-training process. The recent pre-train, prompt, and predict paradigm selects appropriate prompts to reformulate downstream tasks, so as to utilizing the PLM itself for prediction. However, for its success applications, prompts, verbalizer as well as model training should still be carefully designed for different tasks. As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task. Specifically, we design two styles of ConnPrompt template: Insert-cloze Prompt (ICP) and Prefix-cloze Prompt (PCP) and construct an answer space mapping to the relation senses based on the hierarchy sense tags and implicit connectives. Furthermore, we use a multi-prompt ensemble to fuse predictions from different prompting results. Experiments on the PDTB corpus show that our method significantly outperforms the state-of-the-art algorithms, even with fewer training data.
%U https://aclanthology.org/2022.coling-1.75
%P 902-911
Markdown (Informal)
[ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition](https://aclanthology.org/2022.coling-1.75) (Xiang et al., COLING 2022)
ACL