Conferences, Lectures, & Seminars
Events for October
-
NL Seminar- Getting Good at Research
Fri, Oct 03, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Kevin Knight, USC/ISI
Talk Title: Getting Good at Research
Series: Natural Language Seminar
Abstract: If you do good research, you'll find that many doors open. I'll offer some suggest for how to make that happen. This should be an interactive session.
Biography: Kevin Knight is the director of the ISI Natural Language group, a professor of Computer Science at USC, and an ISI Fellow.
Host: Aliya Deri
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
AI SEMINAR
Fri, Oct 10, 2014 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yolanda Gil, Deputy Director, Intelligent Systems Division
Talk Title: Semantic Challenges in Getting Work Done
Abstract: In the new millennium, work involves an increasing amount of tasks that are knowledge-rich and collaborative. We are investigating how semantics can help on both fronts. Our focus is scientific work, in particular data analysis, where tremendous potential resides in combining the knowledge and resources of a highly fragmented science community. We capture task knowledge in semantic workflows, and use skeletal plan refinement algorithms to assist users when they specify high-level tasks. But the formulation of workflows is in itself a collaborative activity, a kind of meta-workflow composed of tasks such as finding the data needed or designing a new algorithm to handle the data available. We are investigating "organic data science", a new approach to collaboration that allows scientists to formulate and resolve scientific tasks through an open framework that facilitates ad-hoc participation. With a design based on social computing principles, our approach makes scientific processes transparent and incorporates semantic representations of tasks and their properties. The semantic challenges involved in this work are numerous and have great potential to transform the Web to help us do work in more productive and unanticipated ways.
Biography: Yolanda Gil is Director of Knowledge Technologies and Associate Division Director at the Information Sciences Institute of the University of Southern California, and Research Professor in the Computer Science Department. She received her M.S. and Ph. D. degrees in Computer Science from Carnegie Mellon University. Dr. Gil conducts research on various aspects of Interactive Knowledge Capture, including intelligent user interfaces, knowledge-rich problem solving, and the semantic web. In recent years, her work has focused on collaborative large-scale scientific data analysis through semantic workflows. She initiated and chaired the W3C Provenance Incubator that led to the PROV community standard. She was elected Fellow of the American Association of Artificial Intelligence (AAAI) in 2012. Dr. Gil is the current Chair of ACM SIGAI, the Association for Computing Machinery's Special Interest Group on Artificial Intelligence.
Host: Greg VerSteeg
Location: Information Science Institute (ISI) - 11th floor large conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar- Interplay between Continuous and Discrete Aspects of Brain Image Analysis
Fri, Oct 10, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Boris Gutman, USC/ISI
Talk Title: Interplay between Continuous and Discrete Aspects of Brain Image Analysis
Series: Natural Language Seminar
Abstract: Brain MRI offers tremendous opportunity to learn about cortical anatomy, function and connectivity. In this talk I will go over several standard techniques for image understanding used in brain imaging. These include image registration, segmentation, tractography and graph-based connectivity analyses. Among these algorithms, we routinely encounter both continuous and discrete types of analysis. Non-linear image registration, typically formalized as a diffeomorphism on the image domain, is an example of the former: we may ask for instance how much volume change the brain is experiencing locally over time, clearly a continuous measure. In another example, we may trace continuous curves in space that best fit a Diffusion Tensor MR image to approximate fibers in the brain’s white matter. One the other hand, connectivity between distinct units within the nervous system is an example of discrete analysis: for instance, the brain’s functionally distinct regions are thought of as nodes in a graph, whose edges are defined by the connecting fiber models.
After a brief description of the standard methods at hand, I will suggest an approach for combining the two types of analysis. By assuming the continuous paradigm for connectivity, we can push our connectome model from being a discrete graph to being a linear operator. Using some well-known results from operator theory, we can decompose the operator into its resident “eigen-networks,” and apply continuous methods directly. As an example, we can spatially register connectivity matrices with spatially distributed nodes. Finally, I will show two simple examples of continuous analogues for standard graph theory measures, and their potential application for an Alzheimer ’s disease study.
Biography: Boris Gutman received his B.S. in Applied Mathematics and PhD in Biomedical Engineering from UCLA before joining USC’s Imaging Genetics Center (IGC). He is currently a post-doctoral scholar at the IGC, under the supervision of Professor Paul M. Thompson.
Host: Aliya Deri and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Flr Conf Rm # 689 Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
AI Seminar-Topics in Constraint Satisfaction and Weighted Constraint Satisfaction
Fri, Oct 17, 2014 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Satish Kumar Thittamaranahalli , USC
Talk Title: Topics in Constraint Satisfaction and Weighted Constraint Satisfaction
Series: Artificial Intelligence Seminar
Abstract: In this talk, I will present two ideas: (a) the idea of "Smoothness" in constraint satisfaction; and (b) the idea of "Constraint Composite Graphs" in weighted constraint satisfaction. Smoothness helps us identify tractable classes of constraint satisfaction problems with important implications in such diverse areas as temporal reasoning, logical filtering, and distributed problem solving. In weighted constraint satisfaction, Constraint Composite Graphs yield a long-pursued unified mathematical framework for exploiting the graphical structure of the constraint network as well as the numerical structure of the weighted constraints.
Biography: Dr. Satish Kumar Thittamaranahalli (T. K. Satish Kumar) is a Research Scientist at the University of Southern California. He has published extensively on numerous topics in Artificial Intelligence spanning such diverse areas as Constraint Reasoning, Planning and Scheduling, Probabilistic Reasoning, Combinatorial Optimization, Approximation and Randomization, Heuristic Search, Model-Based Reasoning, Knowledge Representation and Spatio-Temporal Reasoning. He has served on the Program Committees of many international conferences in Artificial Intelligence and is a co-winner of the Best Student Paper Award from the 2005 International Conference on Automated Planning and Scheduling. Dr. Kumar received his PhD in Computer Science from Stanford University in March 2005. In the past, he has also been a Visiting Student at the NASA Ames Research Center, a Postdoctoral Research Scholar at the University of California, Berkeley, a Research Scientist at the Institute for Human and Machine Cognition, a Visiting Assistant Professor at the University of West Florida and a Senior Research and Development Scientist at Mission Critical Technologies
Host: Greg Ver Steeg
More Info: http://nlg.isi.edu/nl-seminar/
Webcast: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=bdc8f29218904371a2eb9a6c68d175c31dLocation: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=bdc8f29218904371a2eb9a6c68d175c31d
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar- Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation [EMNLP Practice Talk]
Fri, Oct 17, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Qing Dou, USC/ISI
Talk Title: Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation [EMNLP Practice Talk]
Series: Natural Language Seminar
Abstract: Inspired by previous work, where de- cipherment is used to improve machine translation, we propose a new idea to combine word alignment and decipher- ment into a single learning process. We use EM to estimate the model parameters, not only to maximize the probability of parallel corpus, but also the monolingual corpus. We apply our approach to im- prove Malagasy-English machine transla- tion, where only a small amount of paral- lel data is available. In our experiments, we observe gains of 0.9 to 2.1 Bleu over a strong baseline.
Biography: Qing Dou is a fifth year Ph.D. student at ISI. He works with Professor Kevin Knight on various decipherment problems and its application to different Natural Language Processing tasks.
Host: Aliya Deri and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - Conference Room # 689, Marina del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-Generating Psycholinguistic Norms
Fri, Oct 31, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Nikolaos Malandrakis , (USC/SAIL)
Talk Title: Generating Psycholiguistic Norms
Series: Natural Language Seminar
Abstract: numerical representations of word and term content are very popular in NLP applications of behavioral analysis, like sentiment analysis, where the low dimensional representation allows for the use of complicated machine learning techniques, despite the lack of annotated in-domain data. In this presentation we will discuss our experiments on automatically expanding manually annotated lexica of linguistic norms, starting from word emotion norms and generalizing to include higher order terms, norms beyond emotion (like concreteness and age of acquisition) as well as languages other than English. We will present our attempts at domain adaptation of these norms, as well as the composition of norms for larger lexical units via their constituents by utilizing distributional semantic representations. As examples of actual applications we will present a highly ranked system of sentiment analysis submitted to SemEval 2014 and a multi-modal depression diagnosis system for German submitted to AVEC 2014.
Biography: Nikolaos Malandrakis is a third year PhD student at the USC Computer Science Department and a research assistant at the Signal Analysis and Interpretation Laboratory (SAIL). He is originally from Chania, Greece, where he completed a BSc and MSc in Computer Engineering at the Technical University of Crete.
Host: Aliya Deri and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Flr Conf Rm # 689, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
