Conferences, Lectures, & Seminars
Events for January
-
NL Seminar-Learning Neural Network Structures for Natural Language
Fri, Jan 06, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Kenton Murray, Univ. of Notre Dame
Talk Title: Learning Neural Network Structures for Natural Language
Abstract: In recent years, deep learning has had a huge impact on natural language processing surpassing the performance of many other statistical and machine learning methods. One of the many promises of deep learning is that features are learned implicitly and that there is no need to manually engineer features for good performance. However, neural network performance is highly dependent on network architecture and selection of hyper-parameters. In many ways, architecture engineering has supplanted feature engineering in NLP tasks. In this talk, I will focus on two ways neural network structures can be learned while concurrently training models. First, I'll present a regularization scheme for learning the number of neurons in a neural language model during training (Murray and Chiang 2015) and show how it can be used in a Machine Translation task. Then, I'll move onto a Visual Question Answering task where denotations are selected by executing a probabilistic program that models non-determinism with neural networks (Murray and Krishnamurthy 2016).
Biography: Kenton Murray is a PhD student in the Natural Language Processing Lab at the University of Notre Dame's Computer Science and Engineering Department working with David Chiang. His research is on neural methods for human languages, particularly machine translation and question answering. Prior to Notre Dame, he was a Research Associate at the Qatar Computing Research Institute QCRI and received a Master's in Language Technologies from Carnegie Mellon University and a Bachelor's in Computer Science from Princeton University.
Host: Marjan Ghazvininejad and David Chiang
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-Speech-to-Translation Alignment for Documentation of Endangered Languages
Tue, Jan 10, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: David Chiang, Univ. of Notre Dame
Talk Title: Speech-to-Translation Alignment for Documentation of Endangered Languages
Series: Natural Language Seminar
Abstract: I will give an overview of this project, focusing on the pieces that my student, Antonios Anastasopoulos, and I have been most involved in. Our work is based on the premise that spoken language resources are more readily annotated with translations than with transcriptions. A first step towards making such data interpretable would be to automatically align spoken words with their translations. I'll present a neural attentional model (Duong et al., NAACL 2016) and a latent-variable generative model (Anastasopoulos and Chiang, EMNLP 2016) for this task.
Biography: David Chiang (PhD, University of Pennsylvania, 2004) is an associate professor in the Department of Computer Science and Engineering at the University of Notre Dame. His research is on computational models for learning human languages, particularly how to translate from one language to another. His work on applying formal grammars and machine learning to translation has been recognized with two best paper awards (at ACL 2005 and NAACL HLT 2009). He has received research grants from DARPA, CIA, NSF, and Google, has served on the executive board of NAACL and the editorial board of Computational Linguistics and JAIR, and is currently on the editorial board of Transactions of the ACL.
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. -
NL Seminar-HOW I LEARNED TO STOP WORRYING AND LOVE EVALUATIONS (AND KEEP WORRYING)
Fri, Jan 20, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jon May, USC/ISI
Talk Title: HOW I LEARNED TO STOP WORRYING AND LOVE EVALUATIONS (AND KEEP WORRYING)
Series: Natural Language Seminar
Abstract: Bake-offs, shared tasks, evaluations: these are names for short, high-stress periods in many CS researchers' lives where their algorithms and models are exposed to unseen data, often with reputations and funding on the line. Evaluations are sometimes perceived to be the bane of much of our work lives. We grouse about metrics, procedures, glitches, and all the time "wasted" chasing scores, rather than doing Real Science (TM). In this talk I will argue that despite valid criticisms of the approach, coordinated evaluation is a net benefit to NLP research and has led to accomplishments that might not have otherwise arisen. This argument will frame a more in-depth discussion of several pieces of recent evaluation-grounded work: rapid generation of translation and information extraction for low-resource surprise languages (DARPA LORELEI) and organization of SemEval shared tasks in semantic parsing and generation.
Biography: Jonathan May is a Research Assistant Professor at the University of Southern California's Information Sciences Institute (USC/ISI). Previously, he was a research scientist at SDL Research (formerly Language Weaver) and a scientist at Raytheon BBN Technologies. He received a Ph.D. in Computer Science from the University of Southern California in 2010 and a BSE and MSE in Computer Science Engineering and Computer and Information Science, respectively, from the University of Pennsylvania in 2001. Jon's research interests include automata theory, natural language processing, machine translation, and machine learning.
Host: Marjan Ghazvininejad and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Flr -CR#689 (ISI/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. -
Recruiting Seminar
Tue, Jan 24, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Shobeir Fakhraei, Ph.D. candidate at the Department of Computer Science, University of Maryland College Park
Talk Title: Collective Multi-relational Network Mining
Series: AI Seminar
Abstract: Our world is becoming increasingly interconnected and so is the data collected from it. Developing computational models capable of correctly representing the underlying interrelated structure and the heterogeneous characteristics of the real-world data is essential for representing and reasoning about it. Domains such as biology, online social networks, the World Wide Web, information networks, recommender systems, and scholarly networks are just a few examples that include explicit or implicit interdependent structures.
In this talk, I will present approaches to model heterogeneous interlinked data ranging from feature-based and embedding-based approaches to statistical relational learning methods that more explicitly model the dependencies between entities. I will discuss different methods of modeling node classification and link inference in networks for several domains and highlight the effect of two important aspects: (1) Heterogeneous entities and multi-relational structures, (2) joint inference and collective classification of the unlabeled data. I will also introduce a model for link inference that serves as a template to encode a variety of information such as structural, biological, social, and contextual interactions in various domains.
Biography: Shobeir Fakhraei is a Ph.D. candidate at the Department of Computer Science, University of Maryland College Park (UMD) and a visiting researcher at University of California Santa Cruz (UCSC). He holds two M.Sc. degrees specialized on Data Mining and Biomedical Informatics, and Computer Engineering, and has been recognized with awards such as outstanding graduate research assistant recognition award, and General Motors academic scholarship award. He has collaborated with several research teams in academia and industry including at Microsoft Research Redmond, Yahoo! Research Sunnyvale, Turi (Dato), Ifwe (Tagged), and Henry Ford Health System. His research interests include Machine Learning, Multi-Relational Graph Mining, Recommender Systems, Social Network Analysis, and Biomedical and Health Informatics
Host: Jose Luis Ambite and Kristina Lerman
Webcast: http://webcastermshd.isi.edu/Mediasite/Play/b53b0a1dfd3c44c8bda7a4001e8b3f101dLocation: Information Science Institute (ISI) -
WebCast Link: http://webcastermshd.isi.edu/Mediasite/Play/b53b0a1dfd3c44c8bda7a4001e8b3f101d
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. -
AI Seminar-Optimal structure and parameter learning of Ising models and calibration of the D-Wave quantum computer
Fri, Jan 27, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Andrey Lokhov , Los Alamos National Lab
Talk Title: Optimal structure and parameter learning of Ising models and calibration of the D-Wave quantum computer
Series: Artificial Intelligence Seminar
Abstract: Reconstruction of structure and parameters of a graphical model from binary samples is a problem of practical importance in a variety of disciplines, ranging from statistical physics and computational biology to image processing and machine learning. The focus of the research community shifted towards developing universal reconstruction algorithms which are both computationally efficient and require the minimal amount of expensive data. In this talk, we introduce a new method, Interaction Screening, which accurately estimates the model parameters using local optimization problems. We provide mathematical guarantees that the algorithm achieves perfect graph structure recovery with a near information-theoretically optimal number of samples and outperforms state of the art techniques, especially in the low-temperature regime which is known to be the hardest for learning. As an application, we show how the method can be used for correction of persistent biases and noise in the D-Wave quantum computer.
Biography: Currently Postdoctoral Research Assistant at Los Alamos National Laboratory (Theoretical Division and Center for Nonlinear Studies). Working on statistical physics and machine learning.
Ph.D. (2014) Physics, Laboratoire de Physique Théorique et Modèles Statistiques (LPTMS), Université Paris-Sud (University Paris 11), France
M.Sc. (2011) Theoretical Physics, Ecole Normale Superieure (ENS), Paris, France
M.Sc. (2011) Theoretical Physics, Novosibirsk State University, Novosibirsk, Russia
B.Sc. (2009) Physics, Ecole Polytechnique, Paris, France
Host: Aram Galstyan
Webcast: http://webcastermshd.isi.edu/Mediasite/Play/7e04be827bc34fc08ba5f0c2e73254411dLocation: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcastermshd.isi.edu/Mediasite/Play/7e04be827bc34fc08ba5f0c2e73254411d
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.
