Conferences, Lectures, & Seminars
Events for February
-
Abbreviation Disambiguation and NLP tools for Danish
Thu, Feb 08, 2018 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Manuel Ciosici, Aarhus University, Denmark
Talk Title: NL Seminar-Abbreviation Disambiguation and NLP tools for Danish
Series: Natural Language Seminar
Abstract: This talk will cover two topics. The first part will be a brief overview of Manuel's recent project in abbreviation disambiguation. Following, Manuel will give a brief overview of how various NLP methods are used in an industrial setting in a danish company that provides text analytics services for publishers such as Springer-Nature.
Biography: Manuel is a 3rd year PhD student at Aarhus University in Denmark. His PhD is focused on applying Data Mining and Machine Learning on large collections of unstructured text documents with the goal of extracting and representing knowledge embedded in the documents.
Host: Nanyun Peng and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Floor Conf Rm-CR# 689
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-Contextual Bandits in a Collaborative Environment
Fri, Feb 09, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Hongning Wang , University of Virginia
Talk Title: Contextual Bandits in a Collaborative Environment
Series: Natural Language Seminar
Abstract: Contextual bandit algorithms provide principled online learning solutions to find optimal trade offs between exploration and exploitation with companion side-information. They have been extensively used in various important practical scenarios, such as display advertising and content recommendation. A common practice estimates the unknown bandit parameters pertaining to each user independently. This unfortunately ignores dependency among users and thus leads to suboptimal solutions, especially for the applications that have strong social components.
In this talk, I will introduce our newly developed collaborative contextual bandit algorithm, in which the adjacency graph of users is leveraged to share context and payoffs among neighboring users during online updating. We rigorously prove an improved upper regret bound of the proposed collaborative bandit algorithm comparing to conventional independent bandit algorithms. More importantly, we also prove that user dependency relation is only needed to be time-invariant, such that a sublinear upper regret bound is still achievable in such an algorithm. This enables online user dependency estimation. Extensive experiments on both synthetic and three large scale real world datasets verified the improvement of our proposed algorithm against several state-of-the-art contextual bandit algorithms. In addition, I will also cover our recent progress in online matrix factorization, optimizing user long- term engagement, and bandit learning in a non-stationary environment.
Biography: Dr. Hongning Wang is now an Assistant Professor in the Department of Computer Science at the University of Virginia. He received his Ph.D. degree in computer science at the University of Illinois at Champaign Urbana in 2014. His research generally lies in the intersection among machine learning, data mining and information retrieval, with a special focus on computational user intent modeling. His work has generated over 40 research papers in top venues in data mining and information retrieval areas. He is a recipient of 2016 National Science Foundation CAREER Award and 2014 Yahoo Academic Career Enhancement Award.
Host: Nanyun Peng 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. -
Non traditional resources and improved tools for low resource machine translation
Mon, Feb 12, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Nima Pourdamghani, USC/ ISI
Talk Title: NL Seminar-Non-traditional resources and improved tools for low resource machine translation
Series: Natural Language Seminar
Abstract: Thanks to massive training data, and powerful machine translation techniques, machine translation quality has reached acceptable levels for a handful of languages. However, for hundreds of other languages, translation quality decreases quickly as the size of the available training data becomes smaller. For languages with a few millions or less tokens of translation data called low resource languages in this dissertation traditional machine translation technologies fail to produce understandable translations into English. In this work, I explore various non-traditional sources for improving low-resource machine translation.
Biography: Nima Pourdamghani is a phd student at USC ISI working with professor Kevin Knight. Nima's interests are natural language processing, and applications of machine learning in general. His phd thesis is on building tools to improve machine translation for hundreds of low-resource languages.
Host: Nanyun Peng 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 Digital Humanities Lots of Text Based Corpora Lots of Questions
Fri, Feb 23, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Miriam Posner Dave Shepard and Andrew Wallace , UCLA
Talk Title: Digital Humanities Lots of Text Based Corpora Lots of Questions
Series: Natural Language Seminar
Abstract: Digital humanities is a field that uses digital tools to explore humanities questions. That work can take many different forms, from maps to data visualization to video based projects. In this talk, we will discuss humanities approaches to large scale text analysis, with a focus on corpora that may be of interest to computer scientists. We will also talk about the distinctive ways that humanists approach text analysis, and some of the live questions in the field that might interest NLP researchers.
Biography: Bio: Miriam Posner is an assistant professor at the UCLA School of Information. She is also a digital humanist with interests in labor, race, feminism, and the history and philosophy of data. As a digital humanist, she is particularly interested in the visualization of large bodies of data from cultural heritage institutions, and the application of digital methods to the analysis of images and video. She is at work on two projects the first on what data might mean for humanistic research and the second on how multinational corporations are making use of data in their supply chains.
Bio: David Shepard UCLA is Lead Academic Developer at UCLAs Center for Digital Humanities. After receiving his PhD in English from UCLA in 2012, he coauthored the book HyperCities Thick Mapping in the Digital Humanities and has worked on social media and text mining. His work focuses on large scale analysis of social media in disasters.
Bio: Andrew Wallace is a software developer in the UCLA digital library. He received his PhD in Cognitive Science from Brown University in 2011.
Host: Nanyun Peng
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.
