@inproceedings{mengyuan-etal-2022-pali,
title = "{PALI} at {S}em{E}val-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts",
author = "Mengyuan, Zhou and
Hu, Dou and
Yuan, Mengfei and
Zhi, Jin and
Du, Xiyang and
Jiang, Lianxin and
Mo, Yang and
Shi, Xiaofeng",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.153/",
doi = "10.18653/v1/2022.semeval-1.153",
pages = "1084--1089",
abstract = "This paper describes our system used in the SemEval-2022 Task 7(Roth et al.): Identifying Plausible Clarifications of Implicit and Under-specified Phrases. Semeval Task7 is an more complex cloze task, different than normal cloze task, only requiring NLP system could find the best fillers for sentence. In Semeval Task7, NLP system not only need to choose the best fillers for each input instance, but also evaluate the quality of all possible fillers and give them a relative score according to context semantic information. We propose an ensemble of different state-of-the-art transformer-based language models(i.e., RoBERTa and Deberta) with some plug-and-play tricks, such as Grouped Layerwise Learning Rate Decay (GLLRD) strategy, contrastive learning loss, different pooling head and an external input data preprecess block before the information came into pretrained language models, which improve performance significantly. The main contributions of our sys-tem are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task; 2) presenting an efficient learning-rate and parameter attenuation strategy when fintuning pretrained language models; 3) adding different constrative learning loss to improve model performance; 4) showing the useful of the different pooling head structure. Our system achieves a test accuracy of 0.654 on subtask1(ranking 4th on the leaderboard) and a test Spearman`s rank correlation coefficient of 0.785 on subtask2(ranking 2nd on the leaderboard)."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mengyuan-etal-2022-pali">
<titleInfo>
<title>PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Mengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dou</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengfei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyang</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofeng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system used in the SemEval-2022 Task 7(Roth et al.): Identifying Plausible Clarifications of Implicit and Under-specified Phrases. Semeval Task7 is an more complex cloze task, different than normal cloze task, only requiring NLP system could find the best fillers for sentence. In Semeval Task7, NLP system not only need to choose the best fillers for each input instance, but also evaluate the quality of all possible fillers and give them a relative score according to context semantic information. We propose an ensemble of different state-of-the-art transformer-based language models(i.e., RoBERTa and Deberta) with some plug-and-play tricks, such as Grouped Layerwise Learning Rate Decay (GLLRD) strategy, contrastive learning loss, different pooling head and an external input data preprecess block before the information came into pretrained language models, which improve performance significantly. The main contributions of our sys-tem are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task; 2) presenting an efficient learning-rate and parameter attenuation strategy when fintuning pretrained language models; 3) adding different constrative learning loss to improve model performance; 4) showing the useful of the different pooling head structure. Our system achieves a test accuracy of 0.654 on subtask1(ranking 4th on the leaderboard) and a test Spearman‘s rank correlation coefficient of 0.785 on subtask2(ranking 2nd on the leaderboard).</abstract>
<identifier type="citekey">mengyuan-etal-2022-pali</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.153</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.153/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1084</start>
<end>1089</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts
%A Mengyuan, Zhou
%A Hu, Dou
%A Yuan, Mengfei
%A Zhi, Jin
%A Du, Xiyang
%A Jiang, Lianxin
%A Mo, Yang
%A Shi, Xiaofeng
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F mengyuan-etal-2022-pali
%X This paper describes our system used in the SemEval-2022 Task 7(Roth et al.): Identifying Plausible Clarifications of Implicit and Under-specified Phrases. Semeval Task7 is an more complex cloze task, different than normal cloze task, only requiring NLP system could find the best fillers for sentence. In Semeval Task7, NLP system not only need to choose the best fillers for each input instance, but also evaluate the quality of all possible fillers and give them a relative score according to context semantic information. We propose an ensemble of different state-of-the-art transformer-based language models(i.e., RoBERTa and Deberta) with some plug-and-play tricks, such as Grouped Layerwise Learning Rate Decay (GLLRD) strategy, contrastive learning loss, different pooling head and an external input data preprecess block before the information came into pretrained language models, which improve performance significantly. The main contributions of our sys-tem are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task; 2) presenting an efficient learning-rate and parameter attenuation strategy when fintuning pretrained language models; 3) adding different constrative learning loss to improve model performance; 4) showing the useful of the different pooling head structure. Our system achieves a test accuracy of 0.654 on subtask1(ranking 4th on the leaderboard) and a test Spearman‘s rank correlation coefficient of 0.785 on subtask2(ranking 2nd on the leaderboard).
%R 10.18653/v1/2022.semeval-1.153
%U https://aclanthology.org/2022.semeval-1.153/
%U https://doi.org/10.18653/v1/2022.semeval-1.153
%P 1084-1089
Markdown (Informal)
[PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts](https://aclanthology.org/2022.semeval-1.153/) (Mengyuan et al., SemEval 2022)
ACL
- Zhou Mengyuan, Dou Hu, Mengfei Yuan, Jin Zhi, Xiyang Du, Lianxin Jiang, Yang Mo, and Xiaofeng Shi. 2022. PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1084–1089, Seattle, United States. Association for Computational Linguistics.