SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for April
-
AI Seminar
Fri, Apr 07, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Marijn ten Thij, Vrije Universiteit Amsterdam
Talk Title: Beyond tracking: modelling human behavior through social media
Abstract: In this talk, I present my ongoing work in modeling human behavior
using data from online platforms. I will discuss three of my projects
that focus on two online platforms Wikipedia and Twitter. First, I
will illustrate how I model the effect of promoting content on the
page view activity on Wikipedia by using the page view logs provided
by WikiMedia. I will then discuss the random graph model I designed
based on data from Twitter, which may be used to mimic the progression
of a trend through the network of Twitter. Finally, I will talk about
my current project, where we aim to capture business value from a
social feed for the Horticulture Industry.
Biography: Marijn ten Thij is a PhD student in Mathematics at Vrije Universiteit
Amsterdam, who graduated in Applied Mathematics at the Stochastic
Operations Research group at the University of Twente. His research
interest lies in the fields of Complex Science, Network Science and
Big Data. In 2014, Marijn was a member of the Dutch National
ThinkTank, where he worked on the question Can Big Data be used to
make the Netherlands more mobile, more social, and more healthy?
Marijn lives in Amsterdam and enjoys playing American pool billiards
in his spare time.
Host: Emilio Ferrara
More Info: http://webcastermshd.isi.edu/Mediasite/Play/d5714d851721421a857168a930b571e81d
Location: 11th floor large conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
Event Link: http://webcastermshd.isi.edu/Mediasite/Play/d5714d851721421a857168a930b571e81d
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 - ConversAtion level Syntax SImilarity Metric CASSIM)
Fri, Apr 07, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Reihane Boghrati , (USC)
Talk Title: ConversAtion level Syntax SImilarity Metric CASSIM
Series: Natural Language Seminar
Abstract: Abstract: The syntax and semantics of human language can illuminate many individual psychological differences and important dimensions of social interaction. Thus, analysis of language provides important insights into the underlying psychological properties of individuals and groups. Accordingly, psychological and psycholinguistic research has begun incorporating sophisticated representations of semantic content to better understand the connection between word choice and psychological processes. While the majority of language analysis work in psychology has focused on semantics, psychological information is encoded not just in what people say, but how they say it. We introduce ConversAtion level Syntax SImilarity Metric (CASSIM), a novel method for calculating conversation-level syntax similarity. CASSIM estimates the syntax similarity between conversations by automatically generating syntactical representations of the sentences in conversations, estimating the structural differences between them, and calculating an optimized estimate of the conversation-level syntax similarity. Also, we conduct a series of analyses with CASSIM to investigate syntax accommodation in social media discourse. Further, building off of CASSIM, we propose ConversAtion level Syntax SImilarity Metric-Group Representations CASSIM GR. This extension builds generalized representations of syntactic structures of documents, thus allowing researchers to distinguish between people and groups based on syntactic differences.
Biography: Reihane is a forth year Ph.D student at USC, working with Morteza Dehghani in Computational Social Science Laboratory. She is interested in introducing new methods and computational models to psychology, and more broadly to social sciences. Her work spans the boundary between natural language processing and psychology, as does her intellectual curiosity.
Host: Marjan Ghazvininejad and Kevin Knight
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, Apr 14, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Wei Wang, UCLA
Talk Title: Big Data Analytics in Science
Abstract: Big data analytics is the process of examining large amounts of data of a variety of types (big data) to uncover hidden patterns, unknown correlations, and other useful information. Its revolutionary potential is now universally recognized. Data complexity, heterogeneity, scale, and timeliness make data analysis a clear bottleneck in many biomedical applications, due to the complexity of the patterns and lack of scalability of the underlying algorithms. Advanced machine learning and data mining algorithms are being developed to address one or more challenges listed above. It is typical that the complexity of potential patterns may grow exponentially with respect to the data complexity, and so is the size of the pattern space. To avoid an exhaustive search through the pattern space, machine learning and data mining algorithms usually employ a greedy approach to search for a local optimum in the solution space or use a branch-and-bound approach to seeking optimal solutions, and consequently, are often implemented as iterative or recursive procedures. To improve efficiency, these algorithms often exploit the dependencies between potential patterns to maximize in-memory computation and/or leverage special hardware for acceleration. These lead to strong data dependency, operation dependency, and hardware dependency, and sometimes ad hoc solutions that cannot be generalized to a broader scope. In this talk, I will present some open challenges faced by data scientist in biomedical fields and the current approaches taken to tackle these challenges.
Biography: California, Los Angeles and the director of the Scalable Analytics Institute (ScAi). She received her Ph.D. degree in Computer Science from the University of California, Los Angeles in 1999. She was a professor in Computer Science at the University of North Carolina at Chapel Hill from 2002 to 2012 and was a research staff member at the IBM T. J. Watson Research Center between 1999 and 2002. Dr. Wang's research interests include big data analytics, data mining, bioinformatics and computational biology, and databases. She has filed seven patents and has published one monograph and more than one hundred seventy research papers in international journals and major peer-reviewed conference proceedings.
Dr. Wang received the IBM Invention Achievement Awards in 2000 and 2001. She was the recipient of an NSF Faculty Early Career Development (CAREER) Award in 2005. She was named a Microsoft Research New Faculty Fellow in 2005. She was honored with the 2007 Phillip and Ruth Hettleman Prize for Artistic and Scholarly Achievement at UNC. She was recognized with an IEEE ICDM Outstanding Service Award in 2012, an Okawa Foundation Research Award in 2013, and an ACM SIGKDD Service Award in 2016. Dr. Wang has been an associate editor of the IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Big Data, ACM Transactions on Knowledge Discovery in Data, Journal of Knowledge and Information Systems, Data Mining and Knowledge Discovery, and International Journal of Knowledge Discovery in Bioinformatics. She serves on the organization and program committees of international conferences including ACM SIGMOD, ACM SIGKDD, ACM BCB, VLDB, ICDE, EDBT, ACM CIKM, IEEE ICDM, SIAM DM, SSDBM, RECOMB, BIBM. She was elected to the Board of Directors of the ACM Special Interest Group on Bioinformatics, Computational Biology, and Biomedical Informatics (SIGBio) in 2015.
Host: Mayank Kejriwal
More Info: http://webcastermshd.isi.edu/Mediasite/Play/6660ae1a19c74378b4e0db116f3413291d
Location: Information Science Institute (ISI) - 11th floor large conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
Event Link: http://webcastermshd.isi.edu/Mediasite/Play/6660ae1a19c74378b4e0db116f3413291d
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- Why is it harder to build a tic tac toe playing robot than a tic tac toe playing program?
Fri, Apr 14, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Kevin Knight, USC/ISI
Talk Title: Why is it harder to build a tic tac toe playing robot than a tic tac toe playing program?
Series: Natural Language Seminar
Abstract: I wanted to understand why it's so hard to build working robots, so I programmed one to play tic tac toe. Now I understand a lot better! I thought I'd relate my experience right now, just in case I later become more knowledgeable and impossible to understand.
Biography: Kevin Knight is a Research Director at the Information Sciences Institute ISI of the University of Southern California USC, and a Professor in the USC Computer Science Department. He received a PhD in computer science from Carnegie Mellon University and a bachelors degree from Harvard University. Dr. Knights research interests include statistical machine translation, natural language generation, automata theory, and decipherment of historical manuscripts.
Host: Marjan Ghazvininejad
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, Apr 21, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Homa Hosseinmardi , Danaher Corporation
Talk Title: Multimodal Labeling and Characterization of Social Network Data for Detection/Prediction of Cyberbullying
Abstract: One of the most pressing problems in high schools is bullying. However, with todays online and mobile technologies, bullying is moving beyond the schoolyards via cell phones, social networks, online text, videos, and images. As bad as fighting and bullying were before the internet age, the recording and posting of hurtful content online have magnified the harmful reach of bullying, enabling it 24 7. Cyberbullying is a growing problem and incidents of cyberbullying with extreme consequences such as suicide are routinely reported in popular press now. This talk provides insights into the problem of cyberbullying in social networks by investigating profanity usage, ground truth labeling of cyberbullying, and characterization of relationships between cyberbullying and a variety of factors, including linguistic content, social graph features, temporal commenting behavior, and multimedia modality. It also looks at the propagation of cyberbullying behavior in a social network, and prediction of victims of such behavior.
Biography: Homa Hosseinmardi holds PhD in Computer Science from the University of Colorado Boulder. She joined Danaher Corporation in 2015 as Data Scientist at Danaher Labs. She also contributes as a researcher at the CU CyberSafety Research Center. Hosseinmardis interests lie in the area of computational social science and data mining. She is particularly interested in the use of large scale datasets and machine learning techniques to study problems with internet safety, misbehavior and cyberbullying. Her recent work has focused on studying triggers of cyberaggressive behaviors. Her past work also addressed various questions toward understanding cyberbullying in online social networks.
Host: Emilio Ferrara
Location: 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 - REINFORCEMENT LEARNING OF NEGOTIATION DIALOGUE POLICIES
Fri, Apr 21, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Kallirroi Georgila , USC/ICT
Talk Title: REINFORCEMENT LEARNING OF NEGOTIATION DIALOGUE POLICIES
Series: Natural Language Seminar
Abstract: The dialogue policy of a dialogue system decides on what dialogue move also called action, the system should make given the dialogue context also called dialogue state. Building hand crafted dialogue policies is a hard task, and there is no guarantee that the resulting policies will be optimal. This issue has motivated the dialogue community to use statistical methods for automatically learning dialogue policies, the most popular of which is reinforcement learning RL. However, to date, RL has mainly been used to learn dialogue policies in slot filling applications e.g. restaurant recommendation, flight reservation, etc. largely ignoring other more complex genres of dialogue such as negotiation. This talk presents challenges in reinforcement learning of negotiation dialogue policies. The first part of the talk focuses on applying RL to a two party multi issue negotiation domain. Here the main challenges are the very large state and action space, and learning negotiation dialogue policies that can perform well for a variety of negotiation settings, including against interlocutors whose behavior has not been observed before. Good negotiators try to adapt their behaviors based on their interlocutors' behaviors. However, current approaches to using RL for dialogue management assume that the users behavior does not change over time. In the second part of the talk, I will present an experiment that deals with this problem in a resource allocation negotiation scenario.
Biography: Kallirroi Georgila is a Research Assistant Professor at the Institute for Creative Technologies ICT at the University of Southern California US and at USCs Computer Science Department. Before joining USC ICT in 2009 she was a Research Scientist at the Educational Testing Service ETS and before that a Research Fellow at the School of Informatics at the University of Edinburgh. Her research interests include all aspects of spoken dialogue processing with a focus on reinforcement learning of dialogue policies, expressive conversational speech synthesis, and speech recognition. She has served on the organizing, senior, and program committees of many conferences and workshops. Her research work is funded by the National Science Foundation and the Army Research Office.
Host: Marjan Ghazvininejad and Kevin Knight
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, Apr 28, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Avi Pfeffer, Charles River Analytics
Talk Title: PROGRAMMING: PAST, PRESENT, AND FUTURE
Abstract: Probabilistic reasoning lets you predict the future, infer past causes of current observations, and learn from experience. It can be hard to implement a probabilistic application because you have to implement the representation, inference, and learning algorithms. Probabilistic programming makes this much easier by providing an expressive language to represent models as well as inference and learning algorithms that automatically apply to models written in the language. In this talk, I will present the past, present, and future of probabilistic programming and our Figaro probabilistic programming system. I will start with the motivation for probabilistic programming and Figaro. After presenting some basic Figaro concepts, I will introduce several applications we have been developing at Charles River Analytics using Figaro. Finally, I will describe our future vision of providing a probabilistic programming tool that domain experts with no machine learning knowledge can use. In particular, I will present a new inference method that is designed to work well on a wide variety of problems with no user configuration. Prior knowledge of machine learning is not required to follow the talk.
Biography: Dr. Avi Pfeffer is Chief Scientist at Charles River Analytics. Dr. Pfeffer is a leading researcher on a variety of computational intelligence techniques including probabilistic reasoning, machine learning, and computational game theory. Dr. Pfeffer has developed numerous innovative probabilistic representation and reasoning frameworks, such as probabilistic programming, which enables the development of probabilistic models using the full power of programming languages, and statistical relational learning, which provides the ability to combine probabilistic and relational reasoning. He is the lead developer of Charles River Analytics Figaro probabilistic programming language. As an Associate Professor at Harvard, he developed IBAL, the first general-purpose probabilistic programming language. While at Harvard, he also produced systems for representing, reasoning about, and learning the beliefs, preferences, and decision making strategies of people in strategic situations. Prior to joining Harvard, he invented object-oriented Bayesian networks and probabilistic relational models, which form the foundation of the field of statistical relational learning. Dr. Pfeffer serves as Action Editor of the Journal of Machine Learning Research and served as Associate Editor of Artificial Intelligence Journal and as Program Chair of the Conference on Uncertainty in Artificial Intelligence. He has published many journals and conference articles and is the author of a text on probabilistic programming. Dr. Pfeffer received his Ph.D. in computer science from Stanford University and his B.A. in computer science from the University of California, Berkeley.
Host: Craig Knoblock
More Info: http://webcastermshd.isi.edu/Mediasite/Play/9b1644b4150f48cabdccf208f55773a51d
Location: 11th floor large conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
Event Link: http://webcastermshd.isi.edu/Mediasite/Play/9b1644b4150f48cabdccf208f55773a51d
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-Modeling Dialog using Probabilistic Programs
Fri, Apr 28, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Andreas Stuhlmuller , Stanford Univ.
Talk Title: Modeling Dialog Using Probabilistic Programs
Series: Natural Language Seminar
Abstract: How can we effectively explore the space of automated dialog systems? In this talk, I introduce WebPPL, a probabilistic programming language that provides a wide range of inference and optimization algorithms out of the box. This language makes it easy to express and combine probabilistic models, including regression and categorization models, highly structured cognitive models, models of agents that make sequential plans, and deep neural nets. I show that this also includes recent sequence to sequence architectures for dialog. I then use this framework to implement *dialog automation using workspaces, a variation on these architectures that is aimed at dialogs that require sufficiently deep reasoning between utterances that it is difficult to learn how to automate them from transcripts alone.
Biography: Andreas Stuhlmüller is a post-doctoral researcher at Stanford, working in Prof. Noah Goodman's Computation & Cognition lab, and founder of Ought Inc. Previously, he received his Ph.D. in Brain and Cognitive Sciences from MIT, where he was part of Prof. Josh Tenenbaum's Computational Cognitive Science group. He has worked on the design and implementation of probabilistic programming languages, on their application to cognitive modeling, and recently on dialog systems. He is broadly interested in leveraging machine learning to help people think.
Host: Marjan Ghazvininejad and Kevin Knight
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.
