Advanced deep learning methods and applications in opendomain question answering
➤ Gửi thông báo lỗi ⚠️ Báo cáo tài liệu vi phạmNội dung chi tiết: Advanced deep learning methods and applications in opendomain question answering
Advanced deep learning methods and applications in opendomain question answering
VIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answeringOMAIN QUESTION ANSWERINGMASTER THESISMajor: Computer ScienceHANOI-2019VIETNAM NATIONAL I"NB ERSITY. HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS LN OPEN-DOMAIN QUESTION ANSWERINGMASTER THESISMajor: Computer ScienceSupervisor: Assoc. P Advanced deep learning methods and applications in opendomain question answeringrof. Ila Quang I huyPh.D. Nguyen Ba DatHA NO! -2019AbstractEver since the Internet has become ubiquitous, the amount of data accessible by informationAdvanced deep learning methods and applications in opendomain question answering
retrieval systems has increased exponentially. As for information consumers, being able to obtain a short and accurate answer for any query is one ofVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answering. An opendomain QA system usually consists of two modules: retriever and reader. Each is developed to solve a particular task. While the problem of document comprehension has received multiple success with the help of large training corpora and the emergence of attention mechanism, the development o Advanced deep learning methods and applications in opendomain question answeringf document retrieval in open-domain QA has not gain much progress, in this thesis, we propose a novel encoding method for learning question-aware selfAdvanced deep learning methods and applications in opendomain question answering
-attentive document representations. Then, these representations are utilized by applying pair-wise ranking approach to them. The resulting model is aVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answeringaluated using QƯASAR-T dataset and shows surpassing results compared to other state-of-the-art methods.Keywords: Open-domain Question Answering, Document Retrieval, Learning to Rank, Self-attention mechanism.iiiAcknowledgementsForemost, I would like to express my sincere gratitude to my supervisor A Advanced deep learning methods and applications in opendomain question answeringssoc. Prof. Ha Quang Thuy for the continuous support of my Master study and research, for his patience, motivation, enthusiasm, and immense knowledge.Advanced deep learning methods and applications in opendomain question answering
His guidance helped me in all the time of research and writing of this thesis.I would also like to thank my co-supervisor Ph.D. Nguyen Ba Dat who hasVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answeringc. Vu Thi Ly for offering me the summer internship opportunities in NTU. Singapore and leading me working on diverse exciting projects.I thank my fellow labmates in KTLab: M.Sc. Lc Hoang Quynh. B.Sc. Can Duy Cat. B.Sc. Tran Van Lien for the stimulating discussions, and for all the fun we have had in Advanced deep learning methods and applications in opendomain question answering the last two years.Last but not the least. I would like to thank my parents for giving birth to me at the first place and supporting me spiritually tAdvanced deep learning methods and applications in opendomain question answering
hroughout my life.ivDeclarationI declare that die thesis has been composed by myself and that the work has not be submitted for any other degree or prVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answeringen included.My contribution and those of the other authors to this work have been explicitly indicated below. I confirm that appropriate credit has been given within this thesis where reference has been made to the work of others. The work presented in Chapter 3 was previously published in Proceedin Advanced deep learning methods and applications in opendomain question answeringgs of the 3rd ICMLSC as “QASA: Advanced Document Retriever for open Domain Question Answ ering by Learning to Rank Question-Aw are Self-Attentive DocuAdvanced deep learning methods and applications in opendomain question answering
ment Representations" by Trang M. Nguyen (myself). Van-Lien Tran. Duy-Cat Can. Quang-Thuy Ha (my supervisor), Ly T. Vu. Eng-Siong Chng. This study wasVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DO Advanced deep learning methods and applications in opendomain question answeringuyen Minh TrangVTable of ContentsAbstract........................................................ iiiVIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGYNguyen Minh TrangADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DOGọi ngay
Chat zalo
Facebook