Bài viết trình bày một số kiến thức nền tảng có liên quan đến bài toán trả lời tự động, bao gồm: Phân loại ý định người dùng, trả lời tự động, máy đọc hiểu văn bản, học chuyển đổi, mô hình BERT và XLM.
hình huấn luyện sử dụng kho liệu dịch Kho liệu HUFI_PostGrad cần cải tiến số lượng chất lượng Hiện tại, kho ngữ liệu hồn tồn khởi tạo thủ cơng từ tài liệu sẵn có Phịng Sau đại học ĐH CNTP TP HCM Trong tương lai, tiếp tục tìm hiểu kỹ thuật tự động khác nhằm tăng số lượng chất lượng cho kho ngữ liệu VI LỜI CẢM ƠN Đề tài thực nguồn kinh phí hỗ trợ từ Chương trình Vườn ươm Sáng tạo Khoa học Cơng nghệ Trẻ, quản lý Trung tâm Phát triển Khoa học Cơng nghệ Trẻ - Thành Đồn Thành phố Hồ Chí Minh Sở Khoa học Cơng nghệ Thành phố Hồ Chí Minh, theo hợp đồng số “08/2019/HĐ-KHCNT-VƯ” TÀI LIỆU THAM KHẢO [1] Mohammad Nuruzzaman and Omar Khadeer Hussain, “A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks”, A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks, 2018 [2] Nguyễn Thái Nghe Trương Quốc Định, “Hệ thống hỗ trợ tư vấn tuyển sinh đại học”, Tạp chí Khoa học Trường Đại học Cần Thơ, pp.152-159, 2015 [3] Daniel Jurafsky and James H Martin, “Speech and Language Processing: An Introduction to Natural Language Processing”, Computational Linguistics and Speech Recognition, 2008 Trần Thanh Trâm, Trần Thanh Phước, Nguyễn Thị Anh Thư, Nguyễn Thế Hữu, Văn Thế Thành 179 [4] Silvia Quarteroni, “A Chatbot-based Interactive Question Answering System”, 11th Workshop on the Semantics and Pragmatics of Dialogue: 8390, 2007 [5] D Hewlett, L Jones, and A Lacoste, “Accurate supervised and semi-supervised machine reading for long documents”, in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp 2011-2020, 2017 [6] Siva Reddy, Danqi Chen, and Christopher D Manning, “CoQA: A conversational question answering challenge”, Transactions of the Association for Computational Linguistics, Volume 7, pp 249-266, 2019 [7] L Cui, S Huang, F Wei, C Tan, C Duan, and M Zhou, “Superagent: a customer service chatbot for e-commerce websites”, in Proceedings of ACL , System Demonstrations, pp 97-102, 2017 [8] P Clark and O Etzioni, “My Computer Is an Honor Student - but How Intelligent Is It? Standardized Tests as a Measure of AI”, AIMag, vol 37, no 1, pp 5-12, 2016 [9] Pan, S J and Yang, Q, “A Survey on Transfer Learning”, IEEE Transactions on Knowledge and Data Engineering, volume 22, no 10, pp 1345-1359, 2010 [10] Sewon Min, Minjoon Seo, and Hannaneh Hajishirzi, “Domain Adaptation in Question Answering”, ArXiv, abs/1702.02171, 2017 [11] K Sparck Jones, “A statistical interpretation of term specificity and its application in retrieval”, Journal of documentation, vol 28, no 1, pp 11-21, 1972 [12] T Mikolov, I Sutskever, K Chen, G S Corrado, and J Dean, “Distributed representations of words and phrases and their compositionality”, in Advances in neural information processing systems, pp 3111-3119, 2013 [13] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, In Proceedings of NAACL-HLT 2019, pp 4171-4186, 2019 [14] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin, “Attention is all you need”, in Advances in Neural Information Processing Systems, pp 59986008, 2017 [15] Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov, “Unsupervised Cross-lingual Representation Learning at Scale”, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 8440-8451, 2020 [16] Patrick Lewis, Barlas Oguz, Ruty Rinott, Sebastian Riedel, and Holger Schwenk, “MLQA: Evaluating crosslingual extractive question answering”, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 7315-7330, 2020 [17] Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang, “SQuAD: 100,000+ Questions for Machine Comprehension of Text”, in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp 2383-2392, 2016 [18] Pranav Rajpurkar, Robin Jia, and Percy Liang, “Know What You Don’t Know: Unanswerable Questions for SQuAD”, in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp 784789, 2018 [19] Kyungjae Lee, Kyoungho Yoon, Sunghyun Park, and Seung-won Hwang, “Semi-supervised Training Data Generation for Multilingual Question Answering”, in Proceedings of the Eleventh International Conference on Language Resources and Evaluation, 2018 AN AUTOMATED ANSWERING SYSTEM FOR POSTGRADUATE ADMISSION ADVISORY Tran Thanh Tram, Tran Thanh Phuoc, Nguyen Thi Anh Thu, Nguyen The Huu, Van The Thanh ABSTRACT: Along with undergraduate training program, Postgraduate training program is one of the two main training missions of a research-oriented university Universities always want their postgraduate information to be promptly and properly delivered to potential students As for learners, they always want to have the fastest and most effective information about the curricula they are interested in Therefore, we have built an automated answering system for postgraduate admission to facilitate a more effective interaction between the university and potential students We have used the deep learning approach including two main models (Intent Classification model and Machine Reading Comprehension model) to build the automated answering system We have used two corpora for experiment, including the Stanford Question Answering Dataset (SQuAD) for transfer learning training and the Postgraduate dataset of the Ho Chi Minh City University of Food Industry for training and testing process The experiment shows that our automated answering system has given very positive results and can be extended to many majors in other departments