14^th Mexican International Conference on Artificial Intelligence

Research area: sentiment analysis, opinion mining, natural language processing.

Keynote talk: Sentiment analysis and text similarity measures.

Bio: Prof. Gelbukh holds MSc in mathematics by the Lomonosov Moscow State University, Russia, and PhD in computer science by the All-Russian Institute for Scientific and Technical Information. He is Research Professor and Head of the Natural Language Processing Laboratory of the Center for Computing Research of the Instituto Politécnico Nacional, Mexico, and invited professor of the National University of Colombia; he has been invited researcher at Waseda University, Japan, and distinguished visiting professor at Chung-Ang University, Korea. He is member of the Mexican Academy of Sciences and past President of the Mexican Association of Natural Language Processing. He is author of more than 500 journal and conference papers; co-author of 4 books; editor-in-chief or member of editorial board for a more than 10 international journals, and editor of more than 70 books and journal issues. He is the founder and Chair of the CICLing series of conferences on computational linguistics and natural language processing. He has been chair, honorary chair, or program committee chair of more than 30 international conferences, and (co-)advisor of more than 20 PhD students.

Research area: plagiarism detection, irony detection and author profiling in social media.

Keynote talk:  The hard life of an opinion mining tool: dealing with deceptive opinions and irony.

Abstract: With the increasing of social media, consumers rely more than ever on online reviews to make their decisions. A recent survey found that 87% of them have reinforced their decisions to purchase a product due to positive online reviews. At the same time 80% of consumers have changed their minds on the basis of negative information they found online. Therefore, online opinions play an important role for companies and there is an increasing trend to post fake reviews with the aim to sound authentic and deceive the consumers. The detection of deceptive opinions is a quite challenging problem and not only automatically (only 60% of humans discriminate between truthful and deceptive opinions with a certain degree of accuracy). In the first part of the talk I will give an overview of the state-of-thye-art approaches for detecting deceptive opinions. The second part of the talk is devoted to another issue that makes the life of a sentiment analysis tool quite difficult: detecting irony. In ironic opinions what is literally said is usually negated, and in absence of an explicit negation marker. This makes sentiment analysis quite challenging. Therefore, there is a growing interest from the research community in investigating the impact of irony on sentiment analysis and a task has been organized recently at SemEval in 2015 on sentiment analysis of figurative language in Twitter. In the talk I will describe how irony is employed in tweets and reviews and what are the recent state-of-the-art attempts for its automatic detection. Linguistic devices such as ambiguity, incongruity, unexpectedness and emotional contexts play an important role as triggers of irony. At the end I will also address the even more challenging fine-grained problem of discriminating between irony and sarcasm: e.g. If you find it hard to laugh at yourself, I would be happy to do it for you.

Bio: Paolo Rosso is an associate professor of computer science at the Universitat Politècnica of València and is a member of the Pattern Recognition and Human Language Technology (PRHLT) research centre. His research interests include author profiling and irony detection in social media, opinion spam detection, as well as text reuse and plagiarism detection. Since 2009 he has been involved in the organization of PAN benchmark activities, since 2010 and 2011 in the framework of CLEF and FIRE evaluation forums, on plagiarism / text reuse detection and author profiling. He has been also co-organiser of the shared tasks on Sentiment polarity classification at Evalita and on Sentiment analysis of figurative language in Twitter at SemEval-2015. The shared tasks have been organized in the framework of the EC project on Web information quality evaluation initiative (WIQ-EI). He has been involved in several national and international research projects (seven as PI). At the moment he is PI of the SOCOCODE project on Social copying community detection, funded by the US Army Research Office (ARO), and whose aim is to detect copying in social media. He is the deputy steering committee chair for the CLEF conference, and co-author of 30+ articles in international journals and 350+ articles in conferences and workshops. He has been organization chair of CERI-2012, organization co-chair of CLEF-2013, program co-chair of *SEM-2015, and he has organized several workshops at IBERAMIA, LREC, CIKM, SEPLN, AIIA and AAMAS. He has been advisor of 10 PhD students and at the moment he is (co)advisor of 10.

Research area: artificial neural networks, automatic text summarization, written natural language processing.

Keynote talk: Automatic Text Summarization: What have we succeeded and what we need to do?

Abstract: Text summarization, the reduction of a text to its essential content, is a task that requires linguistic competence, world knowledge, and intelligence. Automatic text summarization, the production of summaries by computers is therefore a very difficult task. One may wonder whether machines would ever be able to produce summaries which are indistinguishable from human summaries, a kind of Turing test and a motivation to advance the state of the art in Natural Language Processing. Automatic text summarization is an application discipline in which the final expression is represented by real systems. In spite of the aforementioned difficulties, results are tangible. There are multiple applications for automatic text summarization: news, RSS, email, web page and blog summarization; specialized document, meeting and report summarization; biographic extracts; opinion summarization; automatic title generation etc. However, after more than 50 years of research into automatic text summarization, where are we now? What still needs to be done? In which direction should we go?

Bio: Prof. Torres Moreno was born in Veracruz, Mexico. He works in Avignon, France. In the past, he worked for the Ecole Polytechnique de Montreal, Canada, and Université du Québec. He holds a PhD in Neural Networks by the Center of Nuclear Studies of Grenoble, France, an MSc degree by the INPG of Grenoble, and a BSc degree as Engineer in Electronics from the UAM-Azcapotzalco. He has written a collection of  Nouvelles de la cité. Another of his likings is philately, as well as painting (the engravings of Escher), music, and good science fiction movies.

Zita Vale, Politécnico do Porto

Keynote talk: Field and Market Data Mining for Smart Grid Operation (to be confirmed)

Tutorial: Data Mining

Bio: Zita Vale works in the area of Power Systems, with special interest in network planning and operation. She has been working in the application of Artificial Intelligence techniques to Power Systems since 1988.
She has been involved in several projects involving the development and use of Knowledge-Based systems, Multi-Agent systems, Genetic Algorithms, Neural networks, Particle Swarm Intelligence, Constraint Logic Programming and Data Mining. The main application field of these projects are: Smart Grids, accommodating an intensive use of Renewable Energy Sources, Distributed Energy Resources (DER) and Distributed Generation (DG), addressing the management of energy resources, the impact of DER on electrical networks, the negotiation of DER in electricity markets, demand response, and electrical vehicles, including the ones with gridable capability (V2G). She is the Director of GECAD - Knowledge Engineering and Decision-Support Research Center, a research center with more than one hundred researchers, settled at ISEP/IPP. She is a coordinator researcher of GECAD where she coordinates the Power and Energy Systems group.

Ruslan Salakhutdinov, University of Toronto.

Research area: Deep Learning, Probabilistic Graphical Models, and Large-scale Optimization.

Keynote talk: Recent Advances in Deep Learning. (The talk will be delivered via videoconference.)

Abstract: Building intelligent systems that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many Artificial Intelligence tasks, including visual object recognition, information retrieval, speech perception, and language understanding. In this talk I will first introduce various deep learning models and show that they can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will also discuss deep models that are capable of extracting a unified representation that fuses together multiple data modalities. I will show that on several tasks, including modelling images and text, video and sound, these models significantly improve upon many of the existing techniques.

Bio: Ruslan Salakhutdinov is an assistant professor of Computer Science and Statistics at the University of Toronto; Microsoft Faculty Fellow, and Sloan Fellow. He works in the field of statistical machine learning. He received his PhD in computer science from the University of Toronto in 2009. After spending two post-doctoral years at MIT, he joined the University of Toronto in 2011. He is or has been Action Editor, Journal of Machine Learning Research (JMLR); Editorial Board member, Journal of Artificial Intelligence Research (JAIR); Area Chair, NIPS 2012, NIPS 2011, and ICML 2015, 2013,2012, 2011; Workshop Chair, UAI 2012; Demonstration Chair, NIPS 2013; Tutorial Chair, ICML 2014; Guest editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Special Issue on Learning Deep Architectures, 2014. He has recently given over 70 invited talks at international conferences.

Gennady S. Osipov, National Research University Higher School of Economics; Federal Research Center for Computer Science and Control of the Russian Academy of Sciences, Russia.

Keynote talk: Signs-based vs. Symbolic Models

Gennady Osipov, PhD, DSc is the deputy director of the Federal Research Center for Computer Science and Control of the Russian Academy of Sciences (RAS), professor of the Moscow Institute of Physics and Technology, of the Bauman Moscow State Technical University and of the National Research University Higher School of Economics. His areas of research are intelligent dynamic systems, heterogeneous semantic networks, relational-situational methods of text analysis and semantic search engines. He is the President of the Russian Association for Artificial Intelligence, the Fellow of the European Coordinating Committee for Artificial Intelligence (ECCAI), the recipient of the Governmental Grants for Outstanding Scholars from the President of Russian Federation. He is the vice-editor in chief of the journal “Artificial Intelligence and Decision Making” published by RAS. He is an author of 170 papers, 7 monographs, 2 manuals, and 4 patents.