Conferences, Lectures, & Seminars
Events for April
-
NL Seminar- Finding memory in time
Fri, Apr 13, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yuanhang Su , USC
Talk Title: Finding memory in time
Series: Natural Language Seminar
Abstract: For a large number of natural language processing NLP problems, we are concerned with finding semantic patterns from input sequences. In recurrent neural network RNN based approach, such pattern is encoded in a vector called hidden state. Since Elmans Finding structure in time published in 1990, it has long been believed that the magic power of RNNs memory, which is enclosed inside the hidden state, can handle very long sequences. Yet besides some experimental observations, there is no formal definition of RNNs memory, let alone a rigid mathematical analysis of how RNNs memory forms.
This talk will focus on understanding memory from two viewpoints. The first viewpoint is that memory is a function that maps certain elements in the input sequences to the current output. Such definition, for the first time in literature, allows us to do detailed analysis of the memory of simple RNN SRN, long short term memory ELSTM, and gated recurrent unit GRU. It also opens the door for further improving the existing RNN basic models. The end results are the proposal of a new basic RNN model called extended LSTM ELSTM with outstanding performance for complex language tasks, and a new macro RNN model called dependent bidirectional RNN DBRNN with smaller cross entropy than bidirectional RNN BRNN and encoderdecoder enc dec models. The second viewpoint is that memory is a compact representation of sparse sequential data. From this perspective, the process of generating hidden state of RNN is simply dimension reduction. Thus, method like principal component analysis PCA which does not require labels for training becomes attractive. However, there are two known problems in implementing PCA for NLP problems: the first is computational complexity; the second is vectorization of sentence data for PCA. To deal with this problem, an efficient dimension reduction algorithm called tree structured multi linear PCA is proposed.
Biography: Yuanhang Su received the dual B.S. degree in Electrical Engineering and Automation and Electronic and Electrical Engineering from University of Strathclyde, Glasgow, U.K. and Shanghai University of Electric Power, Shanghai, China, respectively in 2009, and the M.S. degree in Electrical Engineering from the University of Southern California, Los Angeles, CA, in 2010. From 2011 to 2015, he worked as image video camera software and algorithm engineer for a Los Angeles startup named Exaimage, Shanghai Aerospace Electronics Technology Institute in China and Huawei Technology in China consecutively. He joined MCL lab in 2016 spring, and is currently pursing his Ph.D. in computer vision, natural language processing and machine learning.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: 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-Language as a Scaffold for Visual Recognition
Fri, Apr 20, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mark Yatskar , AI2
Talk Title: Language as a Scaffold for Visual Recognition
Series: Natural Language Seminar
Abstract: In this talk we propose to use natural language as a guide for what people can perceive about the world from images and what ultimately machines should aim to see as well. We discuss two recent structured prediction efforts in this vein: scene graph parsing in Visual Genome, a framework derived from captions, and visual semantic role labeling in imSitu, a formalism built on FrameNet and WordNet. In scene graph parsing, we examine the problem of modeling higher order repeating structure motifs and present new state of the art baselines and methods. We then look at the problem semantic sparsity in visual semantic role labeling: infrequent combinations of output semantics are frequent. We present new compositional and data-augmentation methods for dealing with this challenge, significantly improving on prior work.
Biography: Mark Yatskar is a post-doc at the Allen Institute for Artificial Intelligence and recipient of their Young Investigator Award. His primary research is in the intersection of language and vision, natural language generation, and ethical computing. He received his Ph.D. from the University of Washington with Luke Zettlemoyer and Ali Farhadi and in 2016 received the EMNLP best paper award and his work has been featured in Wired and the New York Times.
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. -
NL-Seminar Extracting and Aligning Quantitative Data with Tex
Fri, Apr 27, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jay Pujara, USC/ISI
Talk Title: Extracting and Aligning Quantitative Data with Tex
Series: Natural Language Seminar
Abstract: Quantitative data, such as time series and numerical attribute data, often play a crucial role in understanding the world and validating factual statements. Unfortunately, quantitative datasets are often expressed in diverse formats that exhibit significant variation, posing difficulties to machine reading approaches. Furthermore, the scant context that accompanies these data often makes it difficult to relate the quantitative data with broader ideas. Finally, the vast amount of quantitative data make it difficult for humans to find, understand, or access. In this talk, I highlight my recent work, which focuses on developing general approaches to extracting quantitative data from structured sources, creating high level descriptions of these sources, and aligning quantitative data with textual and ontological labels.
Biography: Jay Pujara is a research scientist at the University of Southern California's Information Sciences Institute whose principal areas of research are machine learning, artificial intelligence, and data science. He completed a postdoc at UC Santa Cruz, earned his PhD at the University of Maryland, College Park and received his MS and BS at Carnegie Mellon University. Prior to his PhD, Jay spent six years at Yahoo! working on mail spam detection, and he has also worked at Google, LinkedIn and Oracle. Jay is the author of over thirty peer-reviewed publications and has received three best paper awards for his work. He is a recognized authority on knowledge graphs, and has organized the Automatic Knowledge Base Construction AKBC and Statistical Relational AI StaRAI workshops, presented tutorials on knowledge graph construction at AAAI and WSDM, and had his work featured in AI Magazine.
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.
