Conferences, Lectures, & Seminars
Events for July
-
NL Seminar-Parsing with word vectors
Fri, Jul 10, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Deniz Yuret, (Koç University / USC / ISI Visitor)
Talk Title: Parsing with word vectors
Series: Natural Language Seminar
Abstract: We investigate the use of distributed word representations instead of word forms and parts of speech in syntactic parsing. Distributed representations are dense, low-dimensional, and real valued vector representations (embeddings) for words. Instead of ad-hoc feature conjunctions, we use kernels and neural networks for non-linearity, greatly simplifying feature engineering. We show that dense representations offer both computational and learning advantages compared to sparse one-hot vector representations. We introduce context vectors, distributed representations for word contexts, and show that they can replace or complement parts of speech in parsing models. We show that distributed representations give accuracies comparable to the state-of-the-art word form and part-of-speech based feature sets.
Biography: http://www.denizyuret.com/
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. -
AI SEMINAR
Fri, Jul 17, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mesrob I. Ohannessian, Postdoctoral researcher at UC San Diego
Talk Title: Good-Turing rare probability estimation: When it does and doesn't work.
Series: AI Seminar
Abstract: The "missing mass" is the probability of all unseen symbols in i.i.d. samples from a discrete distribution. It captures a very fundamental notion of rare event. Being able to estimate this probability was critical in the wartime efforts of Alan Turing and his coworker Jack Good. Together, they proposed a very simple estimator that has been very influential to this day. In this talk, I will first overview the Good-Turing estimator and its favorable properties. I will then dismantle this impeccable image. In particular, I will show that Good-Turing can fail to learn the missing mass in relative error, for even the simplest light-tailed distributions. In fact, no other estimator can do this without further specifying the distribution class. I will then reconstruct a new reputation for this old estimator, as a highly effective specialized rare probability estimator for heavy-tailed distributions. This explains its success in areas where these distributions arise, such as in natural language modeling. This change in perspective opens the door to streamlined estimation techniques that are inspired by extreme value theory, and that extend far beyond missing mass estimation.
Biography: Mesrob I. Ohannessian is a postdoctoral researcher at UC San Diego. Previously, he spent two years in France, one at the Microsoft Research - Inria joint centre as a postdoc, and another at Université Paris-Sud as a Marie Curie Fellow under an ERCIM Alain Bensoussan Fellowship. He received his PhD in Electrical Engineering and Computer Science from MIT. His research interests are broadly in statistics, information theory, machine learning, and their applications, particularly to problems marked by data scarcity.
Host: Aram Galstyan
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=55d2344730a54d739928f6a760f319511dLocation: Information Science Institute (ISI) - 1135 - 11th fl Large CR
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=55d2344730a54d739928f6a760f319511d
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-Shift-Reduce CCG Parsing with a Dependency Model
Fri, Jul 17, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Wenduan Xu, University of Cambridge/ USC ISI Intern
Talk Title: Shift-Reduce CCG Parsing with a Dependency Model
Series: Natural Language Seminar
Abstract: CCG is able to derive typed dependency structures, providing a useful approximation to the underlying predicate-argument relations of -who did what to whom- and dependency structures form an integral part of CCG. In this talk, I will first cover some essential background on CCG, its dependency structures and CCG parsing; I will then discuss a recent dependency model we developed for shift-reduce CCG parsing. A challenge arises in this model from the fact that the oracle needs to keep track of exponentially many gold-standard derivations, which are all hidden. And we solve this by integrating a packed parse forest with the beam-search decoder and introduce a novel technique for querying an exponentially-sized oracle on-the-fly during beam-search decoding.
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: 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- Dialogue focus tracking for zero pronoun resolution
Fri, Jul 24, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sudha Rao, Univ of Maryland / USC ISI Intern
Talk Title: Dialogue focus tracking for zero pronoun resolution
Series: Natural Language Seminar
Abstract: We take a novel approach to zero pronoun resolution in Chinese: our model explicitly tracks the flow of focus in a discourse. Our approach, which generalizes to deictic references, is not reliant on the presence of overt noun phrase antecedents to resolve to, and allows us to address the large percentage of -non-anaphoric- pronouns filtered out in other approaches. We furthermore train our model using readily available parallel Chinese/English corpora, allowing for training without hand-annotated data. Our results demonstrate improvements on two test sets, as well as the usefulness of linguistically motivated features.
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.
