Invited Speakers
Identifying Affective Events and the Reasons for their Polarity - Ellen Riloff
Recognizing affective language is essential for narrative text understanding and for natural language processing applications such as conversational dialogue, summarization, and sarcasm detection. Many tools have been developed to recognize explicit expressions of sentiment, but affective language also includes linguistic phenomena that carry implicit sentiment such as affective events, sarcasm, and similes. Affective events are experiences that positively or negatively impact on our lives. For example, graduating from college and buying a home are typically positive (desirable) events, while being laid off or rushed to the hospital are typically negative (undesirable) events. We will present our recent work on identifying affective events and categorizing them based on the underlying reasons for their affective polarity. First, we will describe a weakly supervised learning method to induce a large set of affective events from a text corpus by optimizing for semantic consistency. Second, we will present learning models to classify affective events based on Human Need Categories, which often explain people's motivations and desires. We will conclude with a discussion of interesting directionsfor future work in this area.
Ellen Riloff is a Professor in the School of Computing at the University of Utah. Her primary research area is natural language processing, with an emphasis on information extraction, sentiment analysis, semantic class induction, and bootstrapping methods that learn from unannotated texts. Recently, she was the General Chair for the EMNLP 2018 conference and a member of the NAACL Executive Board for 2017-2018. Previously, Prof. Riloff has served as Program Co-Chair for the NAACL HLT 2012 and CoNLL 2004 conferences and on the Computational Linguistics Editorial Board, the Transactions of the Association for Computational Linguistics (TACL) Editorial Board, and the NAACL Executive Board and Human Language Technology (HLT) Advisory Board for 2004-2005.
Grounded Emotions - Rada Mihalcea
Emotions are grounded in contextual experience. While natural language processing tools typically look at textual content to find clues pertaining to an author’s emotional state, factors occurring throughout the day, such as weather or news exposure, may prime one toward a particular emotional response. I will explore several types of external factors and show their impact and correlation with a user’s emotional state. Ultimately, we show that when combining all extrinsic features, we are able to predict the emotional state of a user.
Rada Mihalcea is a Professor in the Computer Science and Engineering department at the University of Michigan. Her research interests are in computational linguistics, with a focus on lexical semantics, multilingual natural language processing, and computational social sciences. She serves or has served on the editorial boards of the Journals of Computational Linguistics, Language Resources and Evaluations, Natural Language Engineering, Research in Language in Computation, IEEE Transactions on Affective Computing, and Transactions of the Association for Computational Linguistics. She was a program co-chair for ACL 2011 and EMNLP 2009, and a general chair for NAACL 2015 and *SEM 2019. She is the recipient of a National Science Foundation CAREER award (2008) and a Presidential Early Career Award for Scientists and Engineers awarded by President Obama (2009). In 2013, she was made an honorary citizen of her hometown of Cluj-Napoca, Romania.
Affective Search: Helping Users Create Positive Experiences - Alon Halevy
With the development of Positive Psychology, there has been recent interest in developing technology that helps individuals increase their well-being. This talk describes two inter-related projects at Megagon Labs that develop new AI techniques for enabling such technology. The first project, Jo, is a smart-journaling application that allows users to enjoy the insights of Positive Psychology in the context of their own lives. Users log their important moments via short texts and Jo attempts to give them insights that help them take steps toward creating more positive moments in their lives. The second project helps users create positive experiences when they shop online for services. The observation underlying our project is that while users are searching for experiences (e.g., restaurant outings, vacations), online services only enable them to search based on objective non-experiential attributes. Our Voyageur search service attempts to put experiences at the center of the search process.
Alon Halevy is the CEO of Megagon Labs. Previously, Alon led the Structured Data Research Group at Google for 10 years and before that he was a professor of computer science at the University of Washington. Alon is a founder Nimble Technology, and of Transformatic, Inc., which was acquired by Google in 2005. Alon is the author of two books: "The Infinite Emotions of Coffee" and "Principles of Data Integration." Alon is an ACM Fellow, received the Sloan Fellowship and the PECASE Award. He received his Ph.D. in Computer Science from Stanford University in 1993.