|
Thanks to the increasing rise of interest in chatbot from the industry, conversational AI (Artificial Intelligence) is a new hot research field in Natural Language Processing (NLP), Machine Learning and Deep Learning. The main goal of conversational AI is to generate a human-like conversation. However, it is a challenging task due to the complex nature of human conversations, co-reference, etc. Conversations are broadly categorized into two classes: task-oriented and chit-chat (also called as non-task oriented). Both kinds of conversations are governed by different factors or pragmatics, such as topic, interlocutors’ personality, argumentation logic, viewpoint, intent, and so on. It is thus extremely important to properly model all these factors for effective conversational analysis. In this very emerging and advanced course, we will discuss the modern technologies of deep learning and word representations such as BERT, GPT-2, Seq2seq, Transformer for conversation analysis and generation. We will also take a step ahead from generation to classification by shedding light on the emotion recognition in conversation, emotion-oriented dialogue generation, conversational question-answering (QA), intent classification etc. This course will help students, faculty members, researchers and practitioners to understand both the basic and advanced techniques of conversational AI.
Foreign speaker:
Dr. Soujanya Poria, Singapore University of Technology Design (SUTD), Singapore
Indian speaker:
Dr. Asif Ekbal, Indian Institute of Technology Patna, India
Target groups:
Executives, engineers and researchers from service and government organizations including R&D institutions. Students at all levels (BTech / MSc / MTech / PhD) or Faculty from reputed academic institutions and technical institutions.
Duration:
April 13-24, 2022
This course will cover various fundamental concepts of NLP, recent research directions and hads-on on various machine learning and deep learning approaches to NLP. Following topics in NLP will be discussed in details: N-gram models, Word sense disambiguation, Parsing, Part-of-speech tagging, Sentiment Analysis, Machine Translation, Question Answering, Natural Language Understanding, Natural Language Generation etc. The course will also cover a number of standard algorithms that are used throughout language processing. Modern NLP algorithms are grounded in machine learning. In recent years, Deep Learning approaches have been showing very impressive performance across many different NLP tasks, using single end-to-end neural models that do not require traditional, task-specific feature engineering. In this course, participants will gain a thorough introduction to cutting-edge research in NLP. Through lectures, tutorials, assignments and laboratories, participants will learn the necessary skills to design, implement, and understand their own machine learning models for solving a NLP problem.
Prof. Stefan Kramer is full professor, head of department of the institute of computer of Johannes Gutenberg University (JGU) Mainz, Germany, and honorary professor of The University of Waikato in Hamilton, New Zealand. Before his appointment at JGU, he was associate professor at the computer science department of Technische Universität München (2003 to 2011). He has been active in the field of data mining since the first conference worldwide in 1995 and is author of award-winning papers at ICDM, KDD, ILP and ICBK. He was vice-chair of ICDM 2013 and isregularly area chair of conferences like ECML/PKDD. His research interests include mining structured data, stream mining, process mining and clustering.
Dr. Erik Cambria received his BEng and MEng with honors in Electronic Engineering from the University of Genoa in 2005 and 2008, respectively. In 2012, he was awarded his PhD in Computing Science and Mathematics following the completion of an EPSRC project in collaboration with MIT Media Lab, which was selected as impact case study by the University of Stirling for the UK Research Excellence Framework (REF2014). After working at HP Labs India, Microsoft Research Asia, and NUS Temasek Labs, in 2014 Dr Cambria joined NTU School of Computer Science and Engineering as Assistant Professor. His current affiliations also include Rolls-Royce@NTU, Delta@NTU, A*STAR IHPC, MIT Synthetic Intelligence Lab, and the Brain Sciences Foundation. He is Associate Editor of Elsevier KBS and IPM, Springer AIRE and Cognitive Computation, IEEE CIM, and Editor of the IEEE IS Department on Affective Computing and Sentiment Analysis, fields in which he is one of the most productive authors. Dr Cambria is also recipient of several awards, e.g., the Temasek Research Fellowship, and is involved in many international conferences as Workshop Organizer, e.g., ICDM and KDD, PC Member, e.g., AAAI and ACL, Program Chair, e.g., ELM and FLAIRS, and Keynote Speaker, e.g., CICLing.
Prof. Andy Way has more than 25 year experience in Machine Translation R&D, first on the Eurotra project, then by running his own translation company, and subsequently by building up his own worldleading group at DCU. Between 2011-13, he worked in the translation industry in the UK. On Jan 1st 2014, he rejoined DCU as Associate Professor in Computing to take up the role of Deputy Director of the Centre for Next Generation Localization. In April 2015, he was promoted to Full Professor (personal chair). From Jan 1st 2015, he has been Deputy Director of the ADAPT Centre for Digital Content Technology. From 2009-15 he was President of the European Association for Machine Translation and was President of the International Association for Machine Translation (2011-13). He is also the Editor of the Machine Translation Journal (2007-till now).
Prof. Massimo Poesio is a Professor of Computer Science in the School of Computer Science and Electronic Engineering, University of Essex (UK) and a Professor in Computational Linguistics at the Center for Mind/Brain Sciences, University of Trento, Italy. He is a cognitive scientist with a particular focus on human language technology; his research interests include computational models of semantic interpretation (especially anaphora resolution); the creation of large corpora of semantically annotated data, also using games‐with‐a‐purpose (www.phrasedetectives.org); the study of conceptual knowledge using a combination of methods from human language technology and from neuroscience; emotions and their influence on language interpretation and on agent technology and deception detection.
Prof. Carlos Artemio Coello Coello received a PhD in Computer Science from Tulane University (USA) in 1996. He is currently full professor with distinction (Investigador Cinvestav 3F) at CINVESTAV-IPN in Mexico City, Mexico. Dr. Coello has done pioneering research work in an area which is now known as "evolutionary multi-objective optimization", mainly related to the development of new algorithms. He is an IEEE Fellow for "contributions to multi-objective optimization and constraint-handling techniques". He is also the recipient of the prestigious 2013 IEEE Kiyo Tomiyasu Award and of the 2012 National Medal of Science and Arts in the area of Physical, Mathematical and Natural Sciences. His publications currently report over 29,000 citations, according to Google Scholar (his h-index is 67).
Prof. Sadao Kurohashi is currently a professor of the Graduate School of Informatics at Kyoto University, Japan. He has presented scientific papers in many national and international conferences and published in various journals and books in the field of Natural Language Processing. He is and has been a regular reviewer for several journals and conferences, and has served in program committees of many conferences. He has been doing pioneer work in the domain of Machine Translation and Information Extraction. He has received 2009 IBM Faculty Award and 2010 NTT DOCOMO Mobile Science Award.