Noah Smith (CMU)
- Text-Driven Forecasting
Text-driven forecasting is the challenge of making concrete, testable predictions about future events and trends from publicly available text data. This talk considers a few recent success stories that use various kinds of text (expert-written analysis, blog posts, tweets) to predict interesting things about the future in various domains (finance, political discourse, and public opinion polls). Forecasting challenges much of the standard methodology in NLP while opening up a new driving force for useful models of real-world text that are grounded in real-world events.
Noah Smith is an assistant professor in the School of Computer Science at Carnegie Mellon University, where he leads a team of researchers exploring a broad range of problems in natural language processing and machine learning, including supervised and unsupervised NLP, many kinds of parsing and linguistic analysis, and applications like translation and forecasting. He completed his Ph.D. in Computer Science at Johns Hopkins University in 2006 on a Hertz Foundation fellowship.
Casey Whitelaw (Google)
- Google Wave as a Computational Linguistic Platform
Google Wave is a new platform for real-time, rich media communication and collaboration. There are some properties of Google Wave that make it particularly relevant to social media and computational linguistics. Wave content is structured, including arbitrary annotations; content is mutable by other participants, which may include third-party software agents ("robots"); Waves are versioned and allow access to the detailed, attributed history. We discuss how this provides both new kinds of human interaction, and new opportunities for corpus collection, training, data analysis, and human-computer interaction.
Casey is a software engineer on the Google Wave project, where he works on applying NLP and machine learning techniques to improve communication and collaboration tools. Before joining Google, Casey's PhD at the University of Sydney included research on linguistically-motivated text classification and sentiment analysis. He was a visiting scholar at the Illinois Institute of Technology and an intern at Microsoft Research.
Jochen Leidner (Thomson Reuters)
- The Interaction between News and Social Media
Traditional news outlets such as news agencies, newspapers or television channels have recently been complemented by content contributed on social media platforms. This presentation investigates the nature of news, social media what they have in common, how they differ, the interaction between, and how that interaction is changing over time, giving some examples of the technical, social, and political implications of this change. I conclude with some personal conjectures about possible future directions.
Jochen is a Research Scientist with Thomson Reuters Corporation's Research & Development group and a Director of Linguit Ltd. He holds an M.A. in computational linguistics, English language and literature and Computer Science from the University of Erlangen-Nuremberg, an M.Phil. in Computer Speech, Text and Internet Technology from the University of Cambridge, and a Ph.D. in Informatics from the University of Edinburgh. Jochen is the recipient of the first ACM SIGIR Doctoral Consortium Award (2004) and a Royal Society of Edinburgh Enterprise Fellowship in Electronic Markets (2006) for his work in mobile search. His main interests are information extraction, open-domain question answering, and geographic information systems, and he has co-authored several patent applications and over 20 publications.