Branimir Boguraev and Nicolas Nicolov

Current Trends and Techniques in Temporal Analysis

Branimir Boguraev

Branimir Boguraev is a Research Staff Member at IBM's T.J. Watson Research Center at Yorktown Heights, New York. He holds graduate degrees in electronics and computing machinery from Sofia University, a diploma in applied mathematics from the Bulgarian Academy of Sciences, and a diploma in computer science and a Ph.D. in computational linguistics from Trinity College, Cambridge. His research covers areas as diverse as uniform parsing frameworks, computational lexicology, deep content analysis via shallow syntactic and semantic models, document summarisation, information extraction, and language engineering, among others.

He has participated in a number of joint academic projects and industrial consortia (including foundational work under the Alvey and ESPRIT initiatives), has been funded by research agencies on both sides of the Atlantic (such as SERC, DARPA, NSF), and has managed the natural language programs at two research centres of excellence (IBM's Department of Artificial Intelligence at T.J. Watson, in the early 90'ies, and the Intelligent Systems Department at Apple Computer's Advanced Technologies Group, through the late 90'ies).

He has published extensively in numerous areas of applied natural language processing; has served on the editorial boards of Computational Linguistics and Journal of Semantics; until recently was Editor of the CUP/ACL Series on Studies in Natural Language Processing, and is a founding editor of the Journal of Natural Language Engineering.

Nicolas Nicolov

Dr. Nicolas Nicolov is a chief scientist in the Web Mining group at Umbria Communications. Previously he was a research staff member at IBM's T.J.Watson Research Center. His research focuses on robust, efficient and scalable techniques for multimodal and multilingual language processing.

He received an M.Sci. from the University of Sofia in 1992. He then joined the Department of Artificial Intelligence at the University of Edinburgh where he did his Ph.D. in the area of Natural Language Generation. He was the developer of the PROTECTOR NLG system. Between 1996-1999 he was a postdoctoral fellow at the School of Cognitive Science, University of Sussex working on grammar engineering and wide-coverage parsing for English. He has been with IBM since 1999 working on dialog systems, automatic content extraction, segmentation, time analysis, and lemmatization. He has worked for Apple on OS localization and was a visiting scholar at LIMSI-CNRS (1992) and IMS, University of Stuttgart (1996).

Current Trends and Techniques in Temporal Analysis

As more natural language processing (NLP) applications are looking to incorporate some form of temporal reasoning, computational analysis of time is becoming a prominent research topic. Temporal analysis, however, requires much more than identifying temporal expressions in text: time structures are considerably more complex than entities typically at the focus of traditional information extraction (IE) work. This is not surprising, as reasoning is a more demanding operation than e.g., template filling or gisting, but it introduces additional challenges at representational and analytical levels.

While many of the lessons learnt while solving traditional IE problems are also applicable to (IE-like) aspects of temporal analysis, there are tasks in that space which require novel approaches and solutions.

We will look at existing, and evolving, representational devices for computationally modeling time; we will relate these to a broad range of annotation schemes; we will consider challenges facing both human and computer annotators; and we will present a number of computational (algorithmic) strategies for temporal analysis of text documents.