Conferences, Lectures, & Seminars
Events for July
-
NL Seminar- A Graph-Based Approach to String Regeneration [Intern talk]
Wed, Jul 02, 2014 @ 02:30 PM - 03:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Matic Horvat, University of Cambridge
Talk Title: A Graph-Based Approach to String Regeneration [Intern talk]
Series: Natural Language Seminar
Abstract: I'll talk about a graph based approach to the string regeneration problem, published at 2014 EACL Student Research Workshop. I will conclude my talk by briefly talking about my PhD research direction of including semantics (MRS) into a state-of-the-art SMT system.
String regeneration is the problem of generating a fluent sentence from an unordered list of words. The purpose of investigating and developing approaches to solving the string regeneration problem is grammaticality and fluency improvement of machine generated text. I investigated a graph-based approach to the string regeneration problem that finds a permutation of words with the highest probability under an n-gram language model.
Biography: I am a PhD student at University of Cambridge researching integration of semantics and Statistical Machine Translation. I am originally from Ljubljana, Slovenia, where I completed a BSc in Computer Science in 2012. I continued with a masters in Advanced Computer Science at University of Cambridge, graduating in 2013.
Host: Aliya Deri 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. -
NL Seminar- Factored Markov Translation with Robust Modeling
Fri, Jul 11, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yang Feng, USC/ISI
Talk Title: Factored Markov Translation with Robust Modeling
Series: Natural Language Seminar
Abstract: Phrase-based translation models usually memorize local translation literally and make independent assumption between phrases which makes it neither generalize well on unseen data nor model sentence-level effects between phrases. We present a new method to model correlations between phrases as a Markov model and meanwhile employ a robust smoothing strategy to provide better generalization. This method defines a recursive estimation process and backs off in parallel paths to infer richer structures. Our evaluation shows an 1.1â⬓3.2% BLEU improvement over competitive baselines for Chinese-English and Arabic-English translation.
Biography: Yang Feng is a postdoctoral scholar in Kevin Knight's NLP group in USC/ISI. She got her Ph.D. degree in 2011 from Institute of Computing Technology, Chinese Academy of Sciences. Her interests are machine translation and machine learning, focusing on Bayesian inference and Gaussian process. Now her main work is to improve ISI syntax-based system.
Host: Aliya Deri 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. -
On the relation between the psychological and thermodynamic arrows of time
Fri, Jul 18, 2014 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Todd A. Brun, USC, Associate Professor
Talk Title: On the relation between the psychological and thermodynamic arrows of time
Series: AISeminar
Abstract: Why do we remember the past, and not the future? Why do we perceive time as flowing, with a fixed past separated from an indefinite future by an instantaneous moment known as `now?' This perception is the psychological arrow of time. In this talk I will lay out an argument that generically the psychological arrow of time should align with the thermodynamic arrow of time where that arrow is well defined. This argument applies to any physical system that can act as a memory, in the sense of preserving a record of the state of some other system. This result follows from two principles: the robustness of the thermodynamic arrow of time to small perturbations in the state, and the principle that a memory should not have to be fine-tuned to match the state of the system being recorded. This argument applies even if the memory system itself is completely reversible and nondissipative. I make the argument using a paradigmatic system, and then formulate it more broadly for any system that can be considered a memory, illustrating it with a few examples.
Biography: Todd A. Brun received his Ph.D. in Physics from Caltech in 1994, and then held a variety of postdoctoral positions at the University of London, the Institute for Theoretical Physics in Santa Barbara, Carnegie Mellon University, and the Institute for Advanced Study in Princeton, working on various aspects of quantum theory. Since 2003, he has been a faculty member in the Electrical Engineering Department at the University of Southern California, where he works on quantum computers and quantum information science. As a hobby, he thinks about the nature of time.
Host: Greg Ver Steeg
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=bf95b30ee6b34399ad74d741535fa5a71dLocation: 1135
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=bf95b30ee6b34399ad74d741535fa5a71d
Audiences: Everyone Is Invited
Contact: Alma Nava / Information Sciences Institute
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-An Arabizi-English Social Media Statistical Machine Translation System
Fri, Jul 18, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jonathan May, USC/ISI
Talk Title: An Arabizi-English Social Media Statistical Machine Translation System
Series: Natural Language Seminar
Abstract: We present a machine translation engine that can translate romanized Arabic, often known as Arabizi, into English. With such a system we can, for the first time, translate the massive amounts of Arabizi that are generated every day in the social media sphere but until now have been uninterpretable by automated means. We accomplish our task by leveraging a machine translation system trained on non-Arabizi social media data and a weighted finite-state transducer-based Arabizi-to-Arabic conversion module, equipped with an Arabic character-based n-gram language model. The resulting system allows high capacity on-the-fly translation from Arabizi to English. We demonstrate via several experiments that our performance is quite close to the theoretical maximum attained by perfect deromanization of Arabizi input. This constitutes the first presentation of an end-to-end social media Arabizi-to-English translation system.
Biography: Jonathan May is a computer scientist at USC-ISI, where he also received a PhD in 2010. His current focus areas are in machine translation, machine learning, and natural language understanding. Jonathan co-developed and patented a highly portable method for optimizing thousands of features in machine translation systems that has since been incorporated into all leading open source MT systems. He has previously worked in automata theory and information extraction and at SDL Language Weaver and BBN Technologies.
Host: Aliya Deri 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-Fast algorithms for nearest neighbor classification
Fri, Jul 25, 2014 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sanjoy Dasgupta, UCSD
Talk Title: Fast Algorithms for Nearest Neighbor Classification
Series: Artificial Intelligence Seminar
Abstract: Nearest neighbor (NN) search is one of the simplest and most enduring methods of statistical estimation. We examine its algorithmic complexity via two results.
1. Randomized tree structures for fast NN search
The k-d tree was one of the first spatial data structures proposed for NN search. Its efficacy is diminished in high-dimensional spaces, but several variants, with randomization and overlapping cells, have proved to be successful in practice. We analyze three such schemes. We show that the probability that they fail to find the nearest neighbor, for any data set and any query point, is directly related to a simple potential function that captures the difficulty of the point configuration. We then bound this potential function in several situations of interest: when the data are drawn from a doubling measure; when the data and query distributions are identical and are supported on a set of bounded doubling dimension; and when the data are documents from a topic model.
2. Data structures that adapt to a query distribution
Can we leverage learning techniques to build a fast NN retrieval data structure? We present a general learning framework for the NN problem in which sample queries are used to learn the parameters of a data structure that minimize the retrieval time and/or the miss rate. We explore the potential of this framework through two popular NN data structures: k-d trees and the rectilinear structures employed by locality sensitive hashing. We derive a generalization theory for these data structure classes and present simple learning algorithms for both. Experimental results reveal that learning often improves on the already strong performance of these data structures.
This is joint work with Lawrence Cayton, Eugene Che, Kaushik Sinha, and Zhen Zhai.
Biography: Sanjoy Dasgupta is a Professor in the Department of Computer Science and Engineering at UC San Diego. He received his PhD from Berkeley in 2000, and spent two years at AT&T Research Labs before joining UCSD. His area of research is algorithmic statistics, with a focus on unsupervised and minimally supervised learning. He is the author of a textbook, "Algorithms" (with Christos Papadimitriou and Umesh Vazirani), that appeared in 2006.
Home Page:
http://cseweb.ucsd.edu/users/dasgupta/
Host: Greg Ver Steeg
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=84af215b6be04e48b5f164352b9f20e31dLocation: 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=84af215b6be04e48b5f164352b9f20e31d
Audiences: Everyone Is Invited
Contact: Peter Zamar
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- Navigation Dynamics in Networks
Fri, Jul 25, 2014 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Daniel Lamprecht, Graz University of Technology
Talk Title: Navigation Dynamics in Networks
Series: Natural Language Seminar
Abstract: Research on networks has already revealed much about the structure of real-world networks. Network dynamics such as navigation or exploration, however, are something less well-researched. Yet, we constantly design and use networked systems meant for navigation and exploration. In this talk, I will present a short overview of what we know about navigability, followed by the our work on exploring dynamics occurring on recommendation networks - networks formed implicitly by recommender systems. Navigability can serve as an evaluation criterion for recommender systems and reveal to what extent a system supports navigation and exploration. Based on analysis of topology and dynamical processes, we find that current systems do not support navigation very well, and propose techniques to overcome this.
Biography: Daniel Lamprecht is a PhD student at Graz University of Technology and is interning at ISI this summer. His research explores network science, web science and recommender systems and especially focuses on network navigability. This summer, he's working with Kristina Lerman on navigation dynamics and click biases in Wikigames. In the past, he has also studied navigation dynamics in information networks with the aid of biomedical ontologies.
Host: Aliya Deri and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - Conference Room # 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. -
NL Seminar-Computational Modeling of Bottom-up and Top-down Visual Attention
Thu, Jul 31, 2014 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Ali Borji, USC
Talk Title: Computational Modeling of Bottom-up and Top-Down Visual Attention
Series: Natural Language Seminar
Abstract: Over the last two decades, the inter-disciplinary fields of visual attention and saliency have attracted a lot of interest in cognitive sciences, computer vision, robotics, and machine learning. The high complexity of natural environments requires the primate visual system to combine, in a highly dynamic and adaptive manner, sensory signals that originate from the environment (bottom-up) with behavioral goals and priorities dictated by the task at hand (top-down). I will talk about my recent research in two directions: 1) Bottom-up attention: I will give a snapshot of biological findings on visual attention (e.g., how gaze direction of people in a scene influences eye movements of an external observer), theoretical background on saliency concepts, our model benchmark and saliency models, and 2) Top-down attention: I will describe our neuromorphic algorithms to predict, in a task-independent manner, which elements in a video scene might more strongly attract the gaze of a human. Multi-modal data including bottom-up saliency, "gist" or global context, physical actions and object properties (using example recorded eye movements and videos of humans engaged in various 3D video games, including flight combat, driving, first-person shooting, running a hot-dog stand that serves hungry customers) are utilized to associate particular scenes with particular locations of interest, given the task (e.g., when the task is to drive, if the scene depicts a road turning left, the system learns to look at that left turn). Finally, I will present some successful engineering and clinical applications of our models.
Biography: Ali Borji received the BS and MS degrees in computer engineering from the Petroleum University of Technology, Tehran, Iran, 2001 and Shiraz University, Shiraz, Iran, 2004, respectively. He received the PhD degree in computational neurosciences from the Institute for Studies in Fundamental Sciences (IPM) in Tehran, 2009. He then spent a year at University of Bonn as a postdoc. He has been a postdoctoral scholar at iLab, University of Southern California, Los Angeles since March 2010.
His research interests include computer vision, machine learning, and neurosciences with particular emphasis on visual attention, visual search, active learning, scene and object recognition, and biologically plausible vision models.
Host: Aliya Deri 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.
