{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T05:18:32Z","timestamp":1719724712565},"reference-count":40,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T00:00:00Z","timestamp":1690156800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia","award":["Grant No. 2051"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"Machine reading comprehension (MRC) is one of the most challenging tasks and active fields in natural language processing (NLP). MRC systems aim to enable a machine to understand a given context in natural language and to answer a series of questions about it. With the advent of bi-directional deep learning algorithms and large-scale datasets, MRC achieved improved results. However, these models are still suffering from two research issues: textual ambiguities and semantic vagueness to comprehend the long passages and generate answers for abstractive MRC systems. To address these issues, this paper proposes a novel Extended Generative Pretrained Transformers-based Question Answering (ExtGPT-QA) model to generate precise and relevant answers to questions about a given context. The proposed architecture comprises two modified forms of encoder and decoder as compared to GPT. The encoder uses a positional encoder to assign a unique representation with each word in the sentence for reference to address the textual ambiguities. Subsequently, the decoder module involves a multi-head attention mechanism along with affine and aggregation layers to mitigate semantic vagueness with MRC systems. Additionally, we applied syntax and semantic feature engineering techniques to enhance the effectiveness of the proposed model. To validate the proposed model\u2019s effectiveness, a comprehensive empirical analysis is carried out using three benchmark datasets including SQuAD, Wiki-QA, and News-QA. The results of the proposed ExtGPT-QA outperformed state of art MRC techniques and obtained 93.25% and 90.52% F1-score and exact match, respectively. The results confirm the effectiveness of the ExtGPT-QA model to address textual ambiguities and semantic vagueness issues in MRC systems.<\/jats:p>","DOI":"10.7717\/peerj-cs.1422","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T09:17:01Z","timestamp":1690190221000},"page":"e1422","source":"Crossref","is-referenced-by-count":2,"title":["On solving textual ambiguities and semantic vagueness in MRC based question answering using generative pre-trained transformers"],"prefix":"10.7717","volume":"9","author":[{"given":"Muzamil","family":"Ahmed","sequence":"first","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan"}]},{"given":"Hikmat","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan"}]},{"given":"Tassawar","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan"}]},{"given":"Fawaz","family":"Khaled Alarfaj","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, School of Business, King Faisal University, Hofuf, Saudi Arabia"}]},{"given":"Abdullah","family":"Alomair","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, School of Business, King Faisal University, Hofuf, Saudi Arabia"}]},{"given":"Naif","family":"Almusallam","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, School of Business, King Faisal University, Hofuf, Saudi Arabia"}]}],"member":"4443","published-online":{"date-parts":[[2023,7,24]]},"reference":[{"issue":"11","key":"10.7717\/peerj-cs.1422\/ref-1","doi-asserted-by":"publisher","first-page":"8484","DOI":"10.1007\/s10489-021-02348-9","article-title":"Automatic question-answer pairs generation and question similarity mechanism in question answering system","volume":"51","author":"Aithal","year":"2021","journal-title":"Applied Intelligence"},{"key":"10.7717\/peerj-cs.1422\/ref-2","article-title":"NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension","author":"Back","year":"2020"},{"key":"10.7717\/peerj-cs.1422\/ref-3","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.neucom.2022.08.057","article-title":"Domain adaptive multi-task transformer for low-resource machine reading comprehension","volume":"509","author":"Bai","year":"2022","journal-title":"Neurocomputing"},{"issue":"6","key":"10.7717\/peerj-cs.1422\/ref-4","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1017\/S1351324921000395","article-title":"A survey on machine reading comprehension systems","volume":"28","author":"Baradaran","year":"2022","journal-title":"Natural Language Engineering"},{"issue":"5","key":"10.7717\/peerj-cs.1422\/ref-5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439800","article-title":"Bi-directional long short-term memory model with semantic positional attention for the question answering system","volume":"20","author":"Bi","year":"2021","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"10.7717\/peerj-cs.1422\/ref-6","doi-asserted-by":"publisher","first-page":"7833","DOI":"10.1109\/ICASSP39728.2021.9414067","article-title":"Adaptive bi-directional attention: exploring multi-granularity representations for machine reading comprehension","author":"Chen","year":"2021"},{"key":"10.7717\/peerj-cs.1422\/ref-7","doi-asserted-by":"publisher","first-page":"8810366","DOI":"10.1155\/2021\/8810366","article-title":"MTQA: text-based multitype question and answer reading comprehension model","volume":"2021","author":"Chen","year":"2021","journal-title":"Computational Intelligence and Neuroscience"},{"key":"10.7717\/peerj-cs.1422\/ref-8","doi-asserted-by":"publisher","first-page":"5755327","DOI":"10.1155\/2022\/5755327","article-title":"Intelligent question answering system by deep convolutional neural network in finance and economics teaching","volume":"2022","author":"Chen","year":"2022","journal-title":"Computational Intelligence and Neuroscience"},{"key":"10.7717\/peerj-cs.1422\/ref-9","first-page":"444","article-title":"Relying on discourse analysis to answer complex questions by neural machine reading comprehension","author":"Galitsky","year":"2021"},{"key":"10.7717\/peerj-cs.1422\/ref-10","doi-asserted-by":"publisher","article-title":"TANDA: transfer and adapt pre-trained transformer models for answer sentence selection. arXiv preprint","author":"Garg","year":"2019","DOI":"10.48550\/ARXIV.1911.04118"},{"key":"10.7717\/peerj-cs.1422\/ref-11","doi-asserted-by":"publisher","first-page":"7839840","DOI":"10.1155\/2022\/7839840","article-title":"RLAS-BIABC: a reinforcement learning-based answer selection using the BERT model boosted by an improved ABC algorithm","volume":"2022","author":"Gharagozlou","year":"2022","journal-title":"Intelligence and Neuroscience"},{"key":"10.7717\/peerj-cs.1422\/ref-12","doi-asserted-by":"publisher","first-page":"891","DOI":"10.18653\/v1\/2020.acl-main.83","article-title":"A frame-based sentence representation for machine reading comprehension","author":"Guo","year":"2020"},{"issue":"05","key":"10.7717\/peerj-cs.1422\/ref-13","doi-asserted-by":"publisher","first-page":"2251004","DOI":"10.1142\/S0218001422510041","article-title":"Machine reading comprehension with rich knowledge","volume":"36","author":"He","year":"2022","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"10.7717\/peerj-cs.1422\/ref-14","doi-asserted-by":"publisher","article-title":"To answer or not to answer? Improving machine reading comprehension model with span-based contrastive learning. arXiv preprint","author":"Ji","year":"2022","DOI":"10.48550\/ARXIV.2208.01299"},{"issue":"01","key":"10.7717\/peerj-cs.1422\/ref-15","doi-asserted-by":"publisher","first-page":"2150013","DOI":"10.1142\/S0218126621500134","article-title":"Automatic question answering system based on convolutional neural network and its application to waste collection system","volume":"30","author":"Jiang","year":"2021","journal-title":"Journal of Circuits, Systems and Computers"},{"key":"10.7717\/peerj-cs.1422\/ref-16","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.7717\/peerj-cs.1422\/ref-17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/3411174.3411184","article-title":"Machine reading comprehension on multiclass questions using bidirectional attention flow models with contextual embeddings and transfer learning in Thai corpus","author":"Lapchaicharoenkit","year":"2020"},{"key":"10.7717\/peerj-cs.1422\/ref-18","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/NICS56915.2022.10013390","article-title":"Integrating semantic information into sketchy reading module of retro-reader for vietnamese machine reading comprehension","author":"Le","year":"2022"},{"key":"10.7717\/peerj-cs.1422\/ref-19","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.neucom.2022.02.082","article-title":"Multi-task joint training model for machine reading comprehension","volume":"488","author":"Li","year":"2022","journal-title":"Neurocomputing"},{"issue":"3","key":"10.7717\/peerj-cs.1422\/ref-20","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1007\/s11280-021-00980-6","article-title":"Contrastive heterogeneous graphs learning for multi-hop machine reading comprehension","volume":"25","author":"Liao","year":"2022","journal-title":"Natural Language Engineering"},{"key":"10.7717\/peerj-cs.1422\/ref-21","first-page":"121","volume-title":"Selecting paragraphs to answer questions for multi-passage machine reading comprehension BT-information retrieval","author":"Lin","year":"2019"},{"key":"10.7717\/peerj-cs.1422\/ref-22","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1016\/j.neucom.2022.03.016","article-title":"Document-level event argument linking as machine reading comprehension","volume":"488","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.1422\/ref-23","doi-asserted-by":"publisher","article-title":"LogiQA: a challenge dataset for machine reading comprehension with logical reasoning. arXiv preprint","author":"Liu","year":"2020","DOI":"10.48550\/ARXIV.2007.08124"},{"issue":"1","key":"10.7717\/peerj-cs.1422\/ref-24","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s10796-020-09996-1","article-title":"Towards end-to-end multilingual question answering","volume":"23","author":"Loginova","year":"2021","journal-title":"Information Systems Frontiers"},{"issue":"Part 3","key":"10.7717\/peerj-cs.1422\/ref-25","doi-asserted-by":"publisher","first-page":"3719","DOI":"10.1016\/j.matpr.2021.07.369","article-title":"Smart question answering system using vectorization approach and statistical scoring method","volume":"80","author":"Manjunath","year":"2021","journal-title":"Materials Today: Proceedings"},{"key":"10.7717\/peerj-cs.1422\/ref-26","doi-asserted-by":"crossref","article-title":"Ensemble transformer for efficient and accurate ranking tasks: an application to question answering systems","author":"Matsubara","year":"2022","DOI":"10.18653\/v1\/2022.findings-emnlp.537"},{"issue":"3","key":"10.7717\/peerj-cs.1422\/ref-27","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.jksuci.2014.10.007","article-title":"A survey on question answering systems with classification","volume":"28","author":"Mishra","year":"2016","journal-title":"Journal of King Saud University\u2014Computer and Information Sciences"},{"key":"10.7717\/peerj-cs.1422\/ref-28","doi-asserted-by":"publisher","article-title":"A comprehensive survey on multi-hop machine reading comprehension approaches. arXiv preprint","author":"Mohammadi","year":"2022","DOI":"10.48550\/ARXIV.2212.04072"},{"key":"10.7717\/peerj-cs.1422\/ref-29","doi-asserted-by":"publisher","article-title":"Know what you don\u2019t know: unanswerable questions for SQuAD","author":"Rajpurkar","year":"2018","DOI":"10.48550\/ARXIV.1806.03822"},{"key":"10.7717\/peerj-cs.1422\/ref-30","doi-asserted-by":"publisher","article-title":"Answer span correction in machine reading comprehension. arXiv preprint","author":"Reddy","year":"2020","DOI":"10.48550\/ARXIV.2011.03435"},{"key":"10.7717\/peerj-cs.1422\/ref-31","doi-asserted-by":"publisher","article-title":"A survey of machine narrative reading comprehension assessments. arXiv preprint","author":"Sang","year":"2022","DOI":"10.48550\/ARXIV.2205.00299"},{"issue":"6","key":"10.7717\/peerj-cs.1422\/ref-32","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.jksuci.2018.08.005","article-title":"A literature review on question answering techniques, paradigms and systems","volume":"32","author":"Soares","year":"2020","journal-title":"Journal of King Saud University\u2014Computer and Information Sciences"},{"key":"10.7717\/peerj-cs.1422\/ref-33","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1093\/mind\/LIX.236.433","article-title":"I.\u2013computing machinery and intelligence","volume":"LIX(236)","author":"Turing","year":"1950","journal-title":"Mind"},{"key":"10.7717\/peerj-cs.1422\/ref-34","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1109\/IALP57159.2022.9961260","article-title":"A survey of machine reading comprehension methods","author":"Xu","year":"2022"},{"issue":"12","key":"10.7717\/peerj-cs.1422\/ref-35","doi-asserted-by":"publisher","first-page":"e5828","DOI":"10.1002\/cpe.5828","article-title":"Question answering model based on machine reading comprehension with knowledge enhancement and answer verification","volume":"34","author":"Yang","year":"2022","journal-title":"Concurrency and Computation"},{"key":"10.7717\/peerj-cs.1422\/ref-36","first-page":"2013","article-title":"Wikiqa: a challenge dataset for open-domain question answering","author":"Yang","year":"2015"},{"key":"10.7717\/peerj-cs.1422\/ref-37","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.18653\/v1\/P19-1217","article-title":"Inferential machine comprehension: answering questions by recursively deducing the evidence chain from text","author":"Yu","year":"2019"},{"key":"10.7717\/peerj-cs.1422\/ref-38","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-030-88361-4_6","article-title":"Large-scale multi-granular concept extraction based on machine reading comprehension","author":"Yuan","year":"2021"},{"issue":"21","key":"10.7717\/peerj-cs.1422\/ref-39","doi-asserted-by":"publisher","first-page":"7640","DOI":"10.3390\/app10217640","article-title":"A survey on machine reading comprehension\u2014tasks, evaluation metrics and benchmark datasets","volume":"10","author":"Zeng","year":"2020","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.1422\/ref-40","doi-asserted-by":"publisher","first-page":"114910","DOI":"10.1016\/j.eswa.2021.114910","article-title":"A non-factoid question answering system for prior art search","volume":"177","author":"Zihayat","year":"2021","journal-title":"Expert Systems with Applications"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-1422.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1422.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1422.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1422.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T16:45:58Z","timestamp":1702831558000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-1422"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,24]]},"references-count":40,"alternative-id":["10.7717\/peerj-cs.1422"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.1422","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,24]]},"article-number":"e1422"}}
