Good Places to Start:

Overview of Chapter 6: Discourse and Dialogue. By Professor Barbara Grosz, Harvard University. In Survey of the State of the Art in Human Language Technology (1996). Editorial Board: Ronald A. Cole, Editor in Chief, Joseph Mariani, Hans Uszkoreit, Annie Zaenen, Victor Zue; Managing Editors: Giovanni Battista Varile, Antonio Zampolli. "The problems addressed in discourse research aim to answer two general kinds of questions: (1) what information is contained in extended sequences of utterances that goes beyond the meaning of the individual utterances themselves? (2) how does the context in which an utterance is used affect the meaning of the individual utterances, or parts of them?"

• Also see Professor Grosz's home page at Harvard University: "Professor Grosz has developed a theory of discourse structure that specifies how discourse interpretation depends on interactions among speaker intentions, attentional state, and linguistic form. Her current research in discourse processing has two foci. First, with colleagues at AT&T; Bell Laboratories, she is using the theory to study the information about discourse structure conveyed by intonation, i.e., how tones demark, in spoken language, some of the structure that paragraphs and parentheses indicate in written language. Applications of this work should lead to better computer speech-synthesis systems. Second, she is involved in an interdisciplinary investigation of the connections between centering of attention and form of reference. These two strands of research are being combined in an effort (joint with Professor Stuart Shieber) that aims to provide the scientific and technological base for a new paradigm for human-computer interaction, one that would enable the principled design of multi-modal dialogue-supporting interfaces."

Two Thumbs Up. By Leah Hoffmann. Forbes.com. (November 15, 2005) "'Sentiment analysis,' as the field of research is known, is a hot topic among computer scientists these days. The goal is to create computer programs that can determine whether a document is positive or negative. ... Successful applications could help automate market and product research and dramatically alter the future of a simple Internet search. ... 'The variety of words that people use for subjective expressions is staggering,' says Janyce Wiebe, a professor of computer science at the University of Pittsburgh. Wiebe and her colleagues have already assembled a dictionary of some 8,000 indicator words and phrases. 'The dictionary tells you whether a word is positive or negative when it's taken out of context,' Wiebe explains. 'The challenge is to figure out whether it's positive or negative in each individual instance.' There are a number of different ways to accomplish this. ... Fast Search and Transfer ASA ... unveiled a customizable sentiment analysis program, Marketrac, last year. ... Other potential applications in the field of sentiment analysis include automated flame detectors for online bulletin boards, tracking systems for stock market reports and programs that monitor movie or product reviews."

Point of view and discourse processing. By Janyce M. Wiebe. Working Notes of the 1991 AAAI Fall Symposium on Discourse Structure in Natural Language Understanding and Generation, pp. 136-137. Paper (short) or Transparencies (more complete). "To determine the current [point of view], readers cannot consider sentences in isolation, because most subjective sentences are not explicitly marked for point of view. However, there are regularities in the ways that authors continue, resume, and initiate characters' points of view."

• Also by this author: Learning Subjective Adjectives from Corpora. Proc. 17th National Conference on Artificial Intelligence (AAAI-2000). American Association for Artificial Intelligence, Austin, Texas, July 2000. Postscript version. PDF version. "Subjectivity tagging is distinguishing sentences used to present opinions and evaluations from sentences used to objectively present factual information. There are numerous applications for which subjectivity tagging is relevant, including information extraction and information retrieval."

Discourse Analysis Tutorial. From Dave Inman, School of Computing, South Bank University, London.

Readings Online:

Discourse and Inference: Magnum Opus in Progress. By Jerry R. Hobbs, Information Sciences Institute, University of Southern California. Excerpt from The Problems of Discourse (Chapter 1 subsection): "From one point of view, the point of view of daily life, all of these problems are not really problems. How do we solve them? We just do. But if we ask about the mechanisms that underlie our ability to solve these problems, and we are very strict about what we mean by 'mechanism', all of these become significant problems indeed. For a number of years, researchers in the fields of artificial intelligence (AI) and cognitive psychology have looked at discourse from just such a point of view. The theory developed in this book arises out of this AI tradition. Workers in AI have tried to build natural language understanding systems, and the computer has placed quite stringent limits on what counts as a mechanism. This work is of more than just technological relevance. Today, only people understand language. Efforts to get computers to understand language must therefore draw on what is known about how people do it. Conversely, in spite of the substantial differences in architecture and power between the human brain and the present-day computer, there is embedded within most natural language processing systems a theory, implicit or explicit, of how language would be comprehended by any intelligent entity, hence by humans. If a theory of discourse is framed at a sufficiently abstract level, it may apply equally well to human and computer understanding. The fundamental lesson so far of this AI research is that we understand discourse so well because we know so much. We understood the Sapir text because we know a lot about speech, familiarity, features, daily life, and so on. But we do not just have the knowledge, we are able to use the knowledge to make sense of the text. The central problems in understanding how people interpret discourse are therefore how to characterize the knowledge that people have and the processes they use to deploy that knowledge in the task of interpreting discourse. It is the aim of this book to address these two problems."

• Also see his Publications in Discourse Analysis.

Blogging for Dollars - How would you like to survey 20 million consumers in two minutes? By Justin Martin. Forbes Small Business (December 2005). "[T]o know what the masses are saying about your product, you would have to dig through 350,000 fresh daily postings on a staggering 20 million blogs worldwide.... Enter Umbria, a market research firm in Boulder that designs software to find useful consumer intelligence on the Internet. ... Another big challenge is to decipher what's on a blogger's mind. To figure out whether an opinion is strong or tepid, for example, it helps to know that 'awesome' is a stronger endorsement than 'pretty cool,' and that 'shoddy' is less damning than 'abominable.' Umbria has several employees with Ph.D.s in linguistics and artificial intelligence who are forever tweaking the software to make it better at categorizing opinions. Kaushansky claims his software can even identify sarcasm, a useful skill in the prickly blogosphere. ... The software can also estimate the author's age and gender. ... Automation is the source of Umbria's competitive edge: affordability."

Local Discourse and Reference. Lecture notes from Bill Wilson, Associate Professor in the Artificial Intelligence Group, School of Computer Science and Engineering, University of NSW. "This section concerns the problem of deciding what phrases (especially noun phrases) refer to. It introduces a simple model of global discourse structure called the history list, and presents an algorithm for referent determination in simple cases."

Related Web Sites:

Computational Semantics Laboratory. "We are a research group at the Center for the Study of Language and Information (CSLI) at Stanford University, under the direction of Stanley Peters. We work on a number of projects which involve semantics -- the study of meaning -- at the intersection of linguistics and computer science. A unifying theme in our research is an emphasis on the role of context in determining meaning. We are particularly interested in theoretical models of communication, language, dialogue, computation, and inference which take into account the context in which these activities are occurring."

• Current projects include CALO, a Cognitive Agent that Learns and Organizes: "We are researching robust multimodal natural language and discourse understanding for use in monitoring, recording, and summarizing multi-party meetings. Research foci include automatic topic segmentation and extraction, decision detection, multimodal fusion, ontological discourse modelling, robust semantic parsing, and dialogue act detection."

SIGdial, the Special Interest Group on Discourse and Dialogue: "SIGdial is a Special Interest Group (SIG) of the Association for Computational Linguistics (ACL) and of the International Speech Communication Association(ISCA). Resources include:

• The Recent History of Dialogue Processing. By Lisa Harper (September 1998).

Related Pages in AI Topics:

• Commonsense
• General Index to AI in the news: Natural Language
• Interfaces
• Natural Language
• NL Understanding & Generation

More Readings:

Finding the WRITE Stuff: Automatic Identification of Discourse Structure in Student Essays. By Jill Burstein, Daniel Marcu, Kevin Knight. IEEE Intelligent Systems January/February 2003 (Vol. 18, No. 1). "Automated essay-scoring applications are widely used from the elementary-school through university levels for large-scale assessment and classroom instruction. This goes hand in hand with the increase of essay writing on standardized tests. Writing teachers show growing excitement about the innovative automated-essay-evaluation software that helps students improve their writing. Integration of this software into the curriculum is also consistent with the drive toward individualized assessment and instruction. One kind of application developed for this purpose is an essay-based discourse analysis system. This software shows students the presence and absence of relevant essay-based discourse elements in their essays, including introductory material, thesis statements, main ideas, supporting ideas, and conclusions."

Software referees group calls. By Kimberly Patch. Technology Research News (June 18/25, 2003). "The researchers tapped a sociological discipline -- conversation analysis -- to find ways to automatically tell who is talking to whom. ... Conversation analysts review examples of human interaction in order to understand how these practices work. The researchers quantified speech patterns gleaned by conversation analysts that generally show whether or not people are in conversation, and built software that determines what grouping of people is supported by the best evidence."