Conferences, Lectures, & Seminars
Events for April
-
NL Seminar- Abe Kazemzadeh:
Fri, Apr 05, 2013 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Abe Kazemzadeh, USC
Talk Title: Sentiment and Sarcasm in the 2012 US Presidential Election
Series: Natural Language Seminar
Abstract: Abstract: Political discourse is challenging from a sentiment analysis point of view because political issues are subjective and highly dynamic. Political language may contain neologisms that do not occur frequently in general purpose lexical sentiment models. Also, the presence of humor, sarcasm, and comparatives may introduce errors in sentiment analysis. In Twitter, these issues are amplified by the use of Twitter-specific features and constrained message lengths. In this presentation, we will present a collaborative project between the University of Southern California (USC) Signal Analysis and Interpretation Laboratory, USC Annenberg Innovation Laboratory, and IBM. Our system is relies on manual curation of keywords and hashtags, crowd-sourced annotation, statistical machine learned sentiment models, and a real-time visualization that is ideal for display during live events. We describe our corpus and several experiments using different settings of our sentiment models. Among our findings are that sentiment in politics is skewed towards negative, annotation agreement tend to be low, and that sarcasm is a factor that explains some of the annotator disagreement.
Biography: http://sail.usc.edu/~kazemzad/
Short Bio:
Abe Kazemzadeh is a PhD candidate at the USC Computer Science Dept and a research assistant at the Signal Analysis and Interpretation Laboratory (SAIL). His interests include natural language, logic, emotions, games, and algebra. He is currently the chief technology officer at the USC Annenberg Innovation Laboratory (AIL).
Host: Qing Dou
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - Marina Del Rey-11th Flr Conf Rm # 1135
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, Apr 12, 2013 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yan Liu, USC, Computer Science Department
Talk Title: When Big meets Complex: Learning and Mining in Large-scale Time Series Data
Abstract: Many emerging applications of machine learning, such as social media analysis, climate modeling, and computational biology, involve time series data with inherent structures. In this talk, I will discuss the practical challenges in analyzing time series data and our solutions via Granger graphical models.
Biography: Yan Liu is an assistant professor in Computer Science Department at University of Southern California from 2010. Before that, she was a Research Staff Member at IBM Research from 2006. She received her M.Sc and Ph.D. degree from Carnegie Mellon University in 2004 and 2006. Her research interest includes developing scalable machine learning and data mining algorithms with applications to social media analysis, computational biology, climate modeling and business analytics. She has received several awards, including NSF CAREER Award, ACM Dissertation Award Honorable Mention, Best Paper Award in SDM, and winner of several data mining competitions, such as KDD Cup and INFORMS data mining competition. She has published over 50 referred articles and served as a program committee of SIGKDD, ICML, NIPS, CIKM, SIGIR, ICDM, AAAI, COLING, EMNLP and co-chair of workshops in KDD and ICDM.
Host: David Chiang
More Info: TBA
Webcast: TBALocation: Information Science Institute (ISI) - Marina del Rey, 11th flr Conf. Room
WebCast Link: TBA
Audiences: Everyone Is Invited
Contact: Kary LAU
Event Link: TBA
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-Hui Zhang: "Beyond Left-to-Right: Multiple Decomposition Structures for SMT"
Fri, Apr 12, 2013 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Hui Zhang, USC
Talk Title: Beyond Left-to-Right: Multiple Decomposition Structures for SMT
Series: Natural Language Seminar
Abstract: Standard phrase-based translation models do not explicitly model context dependence between translation units. As a result, they rely on large phrase pairs and target language models to recover contextual effects in translation. In this work, we explore language models over Minimal Translation Units (MTUs) to explicitly capture contextual dependencies across phrase boundaries in the channel model. As there is no single best direction in which contextual information should flow, we explore multiple decomposition structures as well as dynamic bidirectional decomposition. The resulting models are evaluated in an intrinsic task of lexical selection for MT as well as a full MT system, through n-best re-ranking. These experiments demonstrate that additional contextual modeling does indeed benefit a phrase-based system(up to 2.8 BLEU score) and that the direction of conditioning is important. Integrating multiple conditioning orders provides consistent benefit, and the most important directions differ by language pair.
Biography: Home Page:
https://sites.google.com/site/zhangh1982
Host: Qing Dou
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - Marina Del Rey-11th Flr Conf Rm # 1135
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.
