Enhancing Multiple-Choice Question Answering Through Sequential Fine-Tuning and Curriculum Learning Strategies

dc.authorid Yiğit, Gülsüm/0000-0001-7010-169X
dc.authorwosid Yiğit, Gülsüm/IVU-8380-2023
dc.contributor.author Yigit, Gulsum
dc.contributor.author Yiğit, Gülsüm
dc.contributor.author Amasyali, Mehmet Fatih
dc.contributor.other Computer Engineering
dc.date.accessioned 2023-10-19T15:12:48Z
dc.date.available 2023-10-19T15:12:48Z
dc.date.issued 2023
dc.department-temp [Yigit, Gulsum] Kadir Has Univ, Dept Comp Engn, Istanbul, Turkiye; [Yigit, Gulsum; Amasyali, Mehmet Fatih] Yildiz Tech Univ, Dept Comp Engn, Istanbul, Turkiye en_US
dc.description.abstract With the transformer-based pre-trained language models, multiple-choice question answering (MCQA) systems can reach a particular level of performance. This study focuses on inheriting the benefits of contextualized language representations acquired by language models and transferring and sharing information among MCQA datasets. In this work, a method called multi-stage-fine-tuning considering the Curriculum Learning strategy is presented, which proposes sequencing not training samples, but the source datasets in a meaningful order, not randomized. Consequently, an extensive series of experiments over various MCQA datasets shows that the proposed method reaches remarkable performance enhancements than classical fine-tuning over picked baselines T5 and RoBERTa. Moreover, the experiments are conducted on merged source datasets, and the proposed method achieves improved performance. This study shows that increasing the number of source datasets and even using some small-scale datasets helps build well-generalized models. Moreover, having a higher similarity between source datasets and target also plays a vital role in the performance. en_US
dc.description.sponsorship Scientific and Technological Research Council of Turkey (TUBITAK) [120E100]; TUBITAK national fellowship program for PhD studies [BIDEB 2211/A] en_US
dc.description.sponsorship This research is supported by The Scientific and Technological Research Council of Turkey (TUBITAK) in part of the project with 120E100 Grant Number. G. Yigit is supported by TUBITAK - BIDEB 2211/A national fellowship program for PhD studies. en_US
dc.identifier.citationcount 0
dc.identifier.doi 10.1007/s10115-023-01918-2 en_US
dc.identifier.endpage 5042 en_US
dc.identifier.issn 0219-1377
dc.identifier.issn 0219-3116
dc.identifier.issue 11 en_US
dc.identifier.scopus 2-s2.0-85164111490 en_US
dc.identifier.scopusquality Q1
dc.identifier.startpage 5025 en_US
dc.identifier.uri https://doi.org/10.1007/s10115-023-01918-2
dc.identifier.uri https://hdl.handle.net/20.500.12469/5536
dc.identifier.volume 65 en_US
dc.identifier.wos WOS:001023370300001 en_US
dc.identifier.wosquality Q2
dc.khas 20231019-WoS en_US
dc.language.iso en en_US
dc.publisher Springer London Ltd en_US
dc.relation.ispartof Knowledge and Information Systems en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.scopus.citedbyCount 2
dc.subject MCQA en_US
dc.subject T5 en_US
dc.subject Commonsense En_Us
dc.subject RoBERTa en_US
dc.subject Fine-tuning en_US
dc.subject Commonsense
dc.subject Curriculum-learning en_US
dc.title Enhancing Multiple-Choice Question Answering Through Sequential Fine-Tuning and Curriculum Learning Strategies en_US
dc.type Article en_US
dc.wos.citedbyCount 1
dspace.entity.type Publication
relation.isAuthorOfPublication 363c092e-cd4b-400e-8261-ca5b99b1bea9
relation.isAuthorOfPublication.latestForDiscovery 363c092e-cd4b-400e-8261-ca5b99b1bea9
relation.isOrgUnitOfPublication fd8e65fe-c3b3-4435-9682-6cccb638779c
relation.isOrgUnitOfPublication.latestForDiscovery fd8e65fe-c3b3-4435-9682-6cccb638779c

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
5536.pdf
Size:
911.46 KB
Format:
Adobe Portable Document Format
Description:
Tam Metin / Full Text