The following speakers have graciously accepted to give keynotes at EMNLP 2018.
Title: The Moment of Meaning and the Future of Computational Semantics
Abstract: There are many recent advances in semantic parsing: we see a rising number of semantically annotated corpora and there is exciting technology (such as neural networks) to be explored. In this talk I will discuss what role computational semantics could play in future natural language processing applications (including fact checking and machine translation). I will argue that we should not just look at semantic parsing, but that things can get really interesting when we can use language-neutral meaning representations to draw (transparent) inferences. The main ideas will be exemplified by the parallel meaning bank, a new corpus comprising texts annotated with formal meaning representations for English, Dutch, German and Italian.
Johan Bos is Professor of Computational Semantics at the University of Groningen (Netherlands). He received his doctorate from the Computational Linguistics Department at the University of the Saarland (Germany) and held post-doc positions at the University of Edinburgh (UK) and the La Sapienza University in Rome (Italy). In 2010, he moved to his current position in Groningen, leading the computational semantics group. Bos is the developer of Boxer, a state-of-the-art wide-coverage semantic parser for English, initiator of the Groningen Meaning Bank, a large semantically-annotated corpus of texts, and inventor of Wordrobe, a game with a purpose for semantic annotation. Bos received a $1.5-million Vici grant from NWO (Netherlands Organisation for Scientific Research) in 2015 to investigate the role of meaning in human and machine translation. A concrete outcome of this project is the Parallel Meaning Bank containing detailed meaning representations for English, German, Dutch and Italian sentences.
Title: Truth or Lie? Spoken Indicators of Deception in Speech
Abstract: Detecting deception from various forms of human behavior is a longstanding research goal which is of considerable interest to the military, law enforcement, corporate security, social services and mental health workers. However, both humans and polygraphs are very poor at this task. We describe more accurate methods we have developed to detect deception automatically from spoken language. Our classifiers are trained on the largest cleanly recorded corpus of within-subject deceptive and non-deceptive speech that has been collected. To distinguish truth from lie we make use of acoustic-prosodic, lexical, demographic, and personality features. We further examine differences in deceptive behavior based upon gender, personality, and native language (Mandarin Chinese vs. English), comparing our systems to human performance. We extend our studies to identify cues in trusted speech vs. mistrusted speech and how these features differ by speaker and by listener. Why does a listener believe a lie?
Julia Hirschberg is Percy K. and Vida L. W. Hudson Professor and Chair of Computer Science at Columbia University. She previously worked at Bell Laboratories and AT&T Labs where she created the HCI Research Department. She has been editor of Computational Linguistics and Speech Communication, is a fellow of AAAI, ISCA, ACL, ACM, and IEEE, and a member of the National Academy of Engineering. She received the IEEE James L. Flanagan Speech and Audio Processing Award and the ISCA Medal for Scientific Achievement. She currently serves on the IEEE Speech and Language Processing Technical Committee, is co-chair of the CRA-W Board, and has worked for diversity for many years at AT&T and Columbia. She works on spoken language processing and NLP, studying text-to-speech synthesis, spoken dialogue systems, entrainment in conversation, detection of deceptive and emotional speech, hedging behavior, and linguistic code-switching (language mixing).
Title: Understanding the News that Moves Markets
Abstract: Since the dawn of human civilization, finance and language technology have been connected. However, only recently have advances in statistical language understanding, and an ever-increasing thirst for market advantage, led to the widespread application of natural language technology across the global capital markets. This talk will review the ways in which language technology is enabling market participants to quickly understand and respond to major world events and breaking business news. It will outline the state of the art in applications of NLP to finance and highlight open problems that are being addressed by emerging research.
Gideon Mann is the Head of Data Science at Bloomberg L.P., where he guides the strategic direction for machine learning, natural language processing (NLP) and search across the company. He is part of the leadership team for the Office of the CTO. He served as a founding member of both the Data for Good Exchange (D4GX), an annual conference on data science applications for social good, and the Shift Commission on Work, Workers and Technology. He has also been active in academic research in fact extraction, weakly-supervised learning, and distributed optimization. Recently, he has also been interested in applications of machine learning to problems in software engineering. From 2007 to 2014, he worked at Google Research in New York City, and his team built core machine learning libraries, released the Google Prediction API, and developed Colaboratory. Mann graduated Brown University in 1999 and received a Ph.D. from The Johns Hopkins University in 2006.