Conferences, Lectures, & Seminars
Events for September
-
NL Seminar-How Much Information Does a Human Translator Add to the Original?
Fri, Sep 04, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Barret Zoph, USC/ISI
Talk Title: How Much Information Does a Human Translator Add to the Original?
Series: Natural Language Seminar
Abstract: We ask how much information a human translator adds to an original text, and we provide a bound. We address this question in the context of bilingual text com- pression: given a source text, how many bits of additional information are required to specify the target text produced by a human translator? We develop new compression algorithms and establish a benchmark task.
Host: Nima Pourdamghani and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: 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. -
NL Seminar-Neuromorphic Language Understanding
Fri, Sep 11, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Guido Zarella, MITRE Corporation
Talk Title: Neuromorphic Language Understanding
Series: Natural Language Seminar
Abstract: Recurrent neural networks are effective tools for processing natural language. RNNs can be effectively trained to perform sequence processing tasks such as translation, classification, language modeling, and paraphrase detection. However despite major gains in fields related to these power hungry artificial neural networks, it remains difficult to construct functional models of cognition inspired by biological nervous systems. In this talk I'll describe how RNNs can be trained to excel at language understanding tasks and then adapted to run on ultra-low power neuromorphic hardware which simulates the spiking of individual neurons. The result is an interactive embedded system that uses recurrent neural networks to process language while consuming an estimated .000048 watts (48 microwatts).
Biography: Guido Zarrella is a Principal Artificial Intelligence Engineer at the MITRE Corporation in Denver, Colorado. He leads a R&D effort pursuing advances in deep learning for language understanding. He is a former President of the Association for Computational Linguistics, having served in this role on December 5th, 201
Host: Nima Pourdamghani 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
Fri, Sep 18, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Philipp Singer, post doc (GESIS) in Cologne (Germany)
Talk Title: Comparing Hypotheses about Human Trails on the Web
Series: AI Seminar
Abstract: When users interact with the Web today, they leave sequential digital trails on a massive scale. Examples of such human trails include Web navigation, sequences of online restaurant reviews, or online music play lists. Understanding the factors that drive the production of these trails can be useful for e.g., improving underlying network structures, predicting user clicks or enhancing recommendations. In this talk, I present a general approach called HypTrails for comparing a set of hypotheses about human trails on the Web, where hypotheses represent beliefs about transitions between states. The approach utilizes Bayesian inference and the core idea is to incorporate hypotheses as priors into the inference process and utilize the sensitivity of Bayes factors on the prior for gaining insights into the relative plausibility of hypotheses. I will also present results from empirical experiments studying several different kinds of human trails such as (i) human navigational trails, (ii) online editing trails or (iii) human mobility trails.
Biography: Dr. Philipp Singer is a post doctoral researcher at the Computational Social Science Department of the Leibniz Institute for the Social Sciences (GESIS) in Cologne (Germany). Philipp is interested in data science, statistics with a focus on Bayesian statistics, machine learning and web science. In the past few years, Philipp has been mainly concerned with modeling aspects of human trails on the Web. Human trails can emerge by any kind of human interaction with the Web such as the navigation of websites. In detail, he has been dedicated to provide tools that facilitate future research concerned with the study of regularities, patterns and strategies in human trails on the Web. Philipp has published his work in top-tier conferences and journals such as WWW, ISWC, CIKM or IJHCS.
Host: Kristina Lerman
Webcast: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=21f9e396f7834b709900db913153f91f1dLocation: Information Science Institute (ISI) - 689
WebCast Link: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=21f9e396f7834b709900db913153f91f1d
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- Automated Deep Multi-Phenotyping with Noisy Labels
Fri, Sep 25, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: David Kale, USC/ISI
Talk Title: Automated Deep Multi-Phenotyping with Noisy Labels
Series: Natural Language Seminar
Abstract: The increasing volume of electronic health records (EHR) data has spurred significant interest in the development of algorithmic phenotyping, used to identify patient cohorts in massive databases. Data-driven phenotyping, which formulates phenotyping as a statistical learning problem, offers superior scalability and generalization. Building upon previous work at Stanford, we propose a deep multi-phenotyping model: we train a single multi-task neural network to recognize multiple phenotypes, trained on noisy labels generated via an automatic process. We present preliminary results on classifying over 30 different phenotypes on a data set of over one million patients from the Stanford clinical system. This is joint work with Nigam Shah at Stanford University Center for Biomedical Informatics Research.
Biography: Dave Kale is a fourth year PhD student in Computer Science and an Alfred E. Mann Innovation in Engineering Fellow at the University of Southern California. He is advised by Greg Ver Steeg. Before joining USC and ISI, he worked in the Whittier VPICU at Children's Hospital LA and co-founded the Meaningful Use of Complex Medical Data (MUCMD) Symposium. Dave holds a BS and MS from Stanford University.
Host: Nima Pourdamghani 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.
