SUNMONTUEWEDTHUFRISAT
Events for April 21, 2017
-
AI Seminar
Fri, Apr 21, 2017 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Homa Hosseinmardi , Danaher Corporation
Talk Title: Multimodal Labeling and Characterization of Social Network Data for Detection/Prediction of Cyberbullying
Abstract: One of the most pressing problems in high schools is bullying. However, with todays online and mobile technologies, bullying is moving beyond the schoolyards via cell phones, social networks, online text, videos, and images. As bad as fighting and bullying were before the internet age, the recording and posting of hurtful content online have magnified the harmful reach of bullying, enabling it 24 7. Cyberbullying is a growing problem and incidents of cyberbullying with extreme consequences such as suicide are routinely reported in popular press now. This talk provides insights into the problem of cyberbullying in social networks by investigating profanity usage, ground truth labeling of cyberbullying, and characterization of relationships between cyberbullying and a variety of factors, including linguistic content, social graph features, temporal commenting behavior, and multimedia modality. It also looks at the propagation of cyberbullying behavior in a social network, and prediction of victims of such behavior.
Biography: Homa Hosseinmardi holds PhD in Computer Science from the University of Colorado Boulder. She joined Danaher Corporation in 2015 as Data Scientist at Danaher Labs. She also contributes as a researcher at the CU CyberSafety Research Center. Hosseinmardis interests lie in the area of computational social science and data mining. She is particularly interested in the use of large scale datasets and machine learning techniques to study problems with internet safety, misbehavior and cyberbullying. Her recent work has focused on studying triggers of cyberaggressive behaviors. Her past work also addressed various questions toward understanding cyberbullying in online social networks.
Host: Emilio Ferrara
Location: 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. -
NL Seminar - REINFORCEMENT LEARNING OF NEGOTIATION DIALOGUE POLICIES
Fri, Apr 21, 2017 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Kallirroi Georgila , USC/ICT
Talk Title: REINFORCEMENT LEARNING OF NEGOTIATION DIALOGUE POLICIES
Series: Natural Language Seminar
Abstract: The dialogue policy of a dialogue system decides on what dialogue move also called action, the system should make given the dialogue context also called dialogue state. Building hand crafted dialogue policies is a hard task, and there is no guarantee that the resulting policies will be optimal. This issue has motivated the dialogue community to use statistical methods for automatically learning dialogue policies, the most popular of which is reinforcement learning RL. However, to date, RL has mainly been used to learn dialogue policies in slot filling applications e.g. restaurant recommendation, flight reservation, etc. largely ignoring other more complex genres of dialogue such as negotiation. This talk presents challenges in reinforcement learning of negotiation dialogue policies. The first part of the talk focuses on applying RL to a two party multi issue negotiation domain. Here the main challenges are the very large state and action space, and learning negotiation dialogue policies that can perform well for a variety of negotiation settings, including against interlocutors whose behavior has not been observed before. Good negotiators try to adapt their behaviors based on their interlocutors' behaviors. However, current approaches to using RL for dialogue management assume that the users behavior does not change over time. In the second part of the talk, I will present an experiment that deals with this problem in a resource allocation negotiation scenario.
Biography: Kallirroi Georgila is a Research Assistant Professor at the Institute for Creative Technologies ICT at the University of Southern California US and at USCs Computer Science Department. Before joining USC ICT in 2009 she was a Research Scientist at the Educational Testing Service ETS and before that a Research Fellow at the School of Informatics at the University of Edinburgh. Her research interests include all aspects of spoken dialogue processing with a focus on reinforcement learning of dialogue policies, expressive conversational speech synthesis, and speech recognition. She has served on the organizing, senior, and program committees of many conferences and workshops. Her research work is funded by the National Science Foundation and the Army Research Office.
Host: Marjan Ghazvininejad 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.
