Conferences, Lectures, & Seminars
Events for August
-
NL Seminar-UNDERSTANDING THE WORLD'S COMPOSITIONAL CONCEPTS
Fri, Aug 07, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Marius Pasca, Google
Talk Title: UNDERSTANDING THE WORLD'S COMPOSITIONAL CONCEPTS
Series: Natural Language Seminar
Abstract: Compositional topics ("Swiss passport", "German grammar") of interest to Web users may be available as entries within structured knowledge resources. But such topics are not necessarily connected to, let alone represented in relation to, entries of the constituent topics ("Switzerland" and "Passport", or "German language" and "Grammar") from which their approximate meaning could be aggregated. Web documents - more precisely, encyclopedic articles - and Web search queries are shown to be useful in complementary tasks relevant to understanding compositional topics. The tasks are the decomposition of potentially compositional topics into zero, one or more constituent topics; and the interpretation of the role ("issued by", "of") played by constituents ("Swiss", "German") within ambiguous compositional phrases that might refer to compositional topics.
Biography: Marius Pasca is a research scientist at Google in Mountain View, California. Current research interests include factual information extraction from unstructured text within documents and queries, and its applications to Web search.
Host: Nima Pourdamghani and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rms1135 & 1137 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-Going West: From Mansoura to LA via College Park
Tue, Aug 11, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Wael AbdAlmageed, USC/ISI
Talk Title: Going West: From Mansoura to LA via College Park
Series: Artificial Intelligence Seminar
Abstract: Over the last few years, three key research areas have captured my scientific interest: machine learning, bioinformatics and computer vision. In this talk, I will be giving an overview of all three. For machine learning, I will present work on using locality-preserving indexing techniques to accelerate various, widely used machine learning methods, in addition to more recent work on supervised feature selection using optimal design of experiments. Moving on to bioinformatics, I will share recent work on discovering subgroups of hepatocellular carcinoma patients by jointly analyzing miRNA and mRNA data using graph mining and graphical modeling techniques. In the area of computer vision, I will discuss recent research results on large-scale and partial signature matching, exploiting locality-sensitive hashing and graphical models. Last, but of equal importance, I will present an overview of ISI's GLAIVE project for large-scale face recognition in the wild.
Biography: Dr. Wael AbdAlmageed is a senior computer scientist with the University of Southern California's Viterbi School of Engineering Information Sciences Institute (USC/ISI). His research focus is machine learning (ML) and applying ML methods to computer vision, bioinformatics and other data analysis problems. His research interests also include implementing machine learning and computer vision algorithms on modern distributed and high-performance computing platforms, such as MapReduce and GPUs. Prior to joining ISI, from 2004 to 2013, Wael was a research scientist with the University of Maryland at College Park, where he led research and development efforts for various programs such as DARPA's MADCAT, VIVID, VIRAT and PerSEAS, IARPA's VACE, and ARL's RCTA. Wael obtained his Ph.D. with distinction from the University of New Mexico in 2003, where he also received the Outstanding Graduate Student award. He has two patents and over 50 publications in top machine learning, computer vision and high-performance computing conferences and journals. Wael currently leads ISI's face recognition research and development efforts under IARPA's JANUS program.
Host: Yigal Arens
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=f02ab403689f40a3b2996589bc729b441dLocation: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=f02ab403689f40a3b2996589bc729b441d
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. -
AI SEMINAR
Thu, Aug 13, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Paul Groth, Disruptive Tech Director, Elsevier Labs
Talk Title: Provenance for Data Munging Environments
Series: AI Seminar
Abstract: Data munging is a crucial task across domains ranging from drug discovery and policy studies to data science. Indeed, it has been reported that data munging accounts for 60% of the time spent in data analysis. Because data munging involves a wide variety of tasks using data from multiple sources, it often becomes difficult to understand how a cleaned dataset was actually produced (i.e. its provenance). In this talk, I discuss our recent work on tracking data provenance within desktop systems, which addresses problems of efficient and fine grained capture. I also describe our work on scalable provence tracking within a triple store/graph database that supports messy web data. Finally, I briefly touch on whether we will move from adhoc data munging approaches to more declarative knowledge representation languages such as Probabilistic Soft Logic.
Biography: Paul Groth (pgroth.com) is Disruptive Technology Director at Elsevier Labs. He holds a Ph.D. in Computer Science from the University of Southampton (2007) and has done research at the University of Southern California (ISI!) and the VU University Amsterdam. His research focuses on dealing with large amounts of diverse contextualized knowledge with a particular focus on the web and science applications. This includes research in data provenance, data science, data integration and knowledge sharing. Paul was co-chair of the W3C Provenance Working Group that created a standard for provenance interchange. He is co-author of Provenance: an Introduction to PROV and The Semantic Web Primer: 3rd Edition as well as numerous academic articles. He blogs at http://thinklinks.wordpress.com. You can find him on twitter: @pgroth .
Host: Ashish Vaswani
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=b46b31a4e04f4f83a6da32bf8dd040271dLocation: Information Science Institute (ISI) - 6th fl Large CR (689)
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=b46b31a4e04f4f83a6da32bf8dd040271d
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-Beyond Parallel Data - A Decipherment Approach for Better Quality Machine Translation
Fri, Aug 14, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Qing Dou, USC/ISI
Talk Title: A Decipherment Approach for Better Quality Machine Translation
Series: Natural Language Seminar
Abstract: Thanks to the availability of parallel data and advances in machine learning techniques, we have seen tremendous improvement in the field of machine translation over the past 20 years. However, due to lack of parallel data, the quality of machine translation is still far from satisfying for many language pairs and domains. In general, it is easier to obtain non-parallel data, and much work has tried to learn translations from non-parallel data. Nonetheless, improvements to machine translation have been limited. In this work, I follow a decipherment approach to learn translations from non parallel data and achieve significant gains in machine translation.
I apply slice sampling to Bayesian decipherment. Compared with the state- of-the-art algorithm, the new approach is highly scalable and accurate, making it possible to decipher billions of tokens with hundreds of thousands of word types at high accuracy for the first time. When it comes to deciphering foreign languages, I introduce dependency relations to address the problems of word reordering, insertion, and deletion. Experiments show that dependency relations help improve Spanish/English deciphering accuracy by over 5-fold. Moreover, this accuracy is further doubled when word embeddings are used to incorporate more contextual information.
Moreover, I decipher large amounts of monolingual data to improve the state- of-the-art machine translation systems in the scenario of domain adaptation and low density languages. Through experiments, I show that decipherment find high quality translations for out-of-vocabulary words in the task of domain adaptation, and help improve word alignment when the amount of parallel data is limited. I observe up to 3.8 point and 1.9 point BlEU gain in Spanish/French and Malagasy/English machine translation experiments respectively.
Biography: Qing is a PhD candidate at USC. His research interests focus on application of machine learning techniques to help computer better understand human languages. He is working with Kevin Knight on various problems related to Machine Translation and Decipherment. Prior to that, he has worked on computational phonology, including stress prediction and transliteration. He is interested in continuing his research in industrial settings to solve exciting large scale problems.
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. -
NL Seminar- Using HyTER networks for short-answer scoring
Tue, Aug 25, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Wenduan Xu, (Cambridge / ISI Intern)
Talk Title: Using HyTER networks for short-answer scoring
Series: Natural Language Seminar
Abstract: This talk summarizes my work so far on investigating the usefulness of HyTER networks for short-answer scoring. I will first introduce the task and the approach we take in this project. And finally I will show some initial results we have.
Biography: Wenduan Xu is a graduate student in Cambridge advised by Stephen Clark, working on CCG parsing.
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. -
NL Seminar-Distant supervision for relation extraction using AMR
Fri, Aug 28, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sudha Rao, Univ of Maryland / USC ISI Intern
Talk Title: Distant supervision for relation extraction using AMR
Series: Natural Language Seminar
Abstract: In this talk I will present the work I did with Prof Daniel Marcu and Prof Kevin Knight at ISI over the summer. In this work, we show how we can improve relation extraction for biomedical text using distant supervision from existing knowledge sources like BioPax. We label the data using heuristics from AMR which obviates the need for expensive manual annotation and allows us to make use of large amounts of data for training. I will also talk about some ongoing work on training a simpler model that exploits linguistic information stored in the path via the least common ancestor in an AMR.
Biography: I am a PhD student from University of Maryland, College Park working under Prof. Hal Daume III and Prof. Philip Resnik. My recent project on "Dialogue focus tracking for zero pronoun resolution" appeared at NAACL 2015. At ISI, I am working with Prof. Daniel Marcu and Prof. Kevin Knight on application of Abstract Meaning Representation (AMR) to biology literature. Specifically we will be developing techniques for constructing text level AMRs from sentence level AMRs and then assess its impact on reading-against-a-model molecular biology tasks. In my spare time, I enjoy singing, dancing and watching movies.
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.
