Conferences, Lectures, & Seminars
Events for August
-
Can machines understand and generate stories?
Wed, Aug 03, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Angeliki Lazaridou, USC/ISI Summer Intern
Talk Title: Can machines understand and generate stories?
Series: Natural Language Seminar
Abstract: Computational creativity is an emerging field of AI, with linguistic creativity being an interesting test-bed for developing and evaluating machines with reasoning capabilities. A concrete example is story generation and understanding, a task which unlike the vast majority of traditional NLP that treats sentences in isolation, requires deep understanding of the general context and discourse of stories.
In this talk, I will present some preliminary steps towards this goal and show how sequence-to-sequence models can be applied to this task. Overall, our results on story understanding are on par with current state-of-the-art (that nevertheless have no generative capabilities), while at the same time producing sometimes rather amusing story endings.
Biography: Angeliki is a final year PhD student at the Center for Mind/Brain Sciences of the University of Trento. She received her MSc from the Saarland University, where she worked with Ivan Titov and Caroline Sporleder on Bayesian models for sentiment and discourse. She is currently working at the intersection between language and vision under the supervision of Marco Baroni.
Host: Xing Shi and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Webcast: http://webcastermshd.isi.edu/Mediasite/Play/202452984a364bc8875b71bf115149281dLocation: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcastermshd.isi.edu/Mediasite/Play/202452984a364bc8875b71bf115149281d
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
Fri, Aug 19, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Xiang Li, USC/ISI Intern
Talk Title: Event extraction from AMR representations
Abstract: How to use NLP techniques to help medical researchers is crucial now. And making use of millions of medical passages is a good starting point. By doing this, we can extract useful information from these papers and help medical researchers a lot.
I will introduce a simple method to extract relations between proteins using AMR. By using this rule-base system, we can get AMR representation to simplified AMR(SMR) which only contains protein relation information.
Biography: Xiang Li (Lorraine) is a 2016 summer intern under the supervision of Prof Kevin Knight and Prof Daniel Marcu. She is also going to be a PhD student at the University of Massachusetts Amherst in Andrew McCallums research group in this coming Fall. She got her B.S at the East China Normal University, Shanghai, China and got her M.S at the University of Chicago. Her research interest mainly focused on natural language processing and machine learning.
Host: Xing Shi
Location: Information Science Institute (ISI) - 1135 - 11th fl Large CR
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
Fri, Aug 26, 2016 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Ke Tran , USC/ISI Intern
Talk Title: Unsupervised learning linguistic structures with deep neural networks
Series: NL Seminar
Abstract: We present a general framework for unsupervised learning that combines probalistic graphical models with the power of deep nets. We employ a neuralized expectation miminization algorithm for learning. We apply this framework for unsupervised sequential tagging and show some interesting results.
Biography: Ke is a PhD candidate at University of Amsterdam. He is interning at ISI, working with Yonatan Bisk, Ashish Vaswani, Kevin Knight, and Daniel Marcu. His research focuses on deep learning and machine translation.
Host: Xing Shi
Location: Information Science Institute (ISI) - 1135 - 11th fl Large CR
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
Tue, Aug 30, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Fei Sha, UCLA
Talk Title: Large-scale Zero-Shot Learning
Abstract: Abstract: Is it possible for computer vision systems to recognize visual object categories that they have never seen before? More precisely, in the paradigm of zero-shot learning, a learner has access to only a subset of the labels in the labeling space (and its associated exemplar images). Nonetheless, our goal for the learner is to recognize future occurrences of images from all possible categories. This is an important research problem with great application potential for automatic object recognition in the wild where the number of possible visual categories continuously rises and there is little hope to collect adequate labeling samples for those categories fast enough.
In this talk, I will describe a few work from my research group on tackling this challenge. We have demonstrated that it is possible to train vision systems on the ImageNet images from 1,000 visual categories yet attaining meaningful results on recognizing a disjoint set of 20,000 visual categories.
This is a joint research work with my PhD students (Soravit Changpinyo and Weilun Chao ) at USC and our collaborator Prof. Boqing Gong (U. of Central Florida).
Host: Emilio Ferrara
Location: Information Science Institute (ISI) - 11th floor Large Conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
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.
