This paper introduces the technique of Predictive Annotation, a methodology for indexing texts for retrieval aimed at answering fact-seeking questions. The essence of the approach can be stated simply: index the answers. This is done by establishing about 20 classes of objects that can be identified in text by shallow parsing, and by annotating and indexing the text with these labels, which we call QA-Tokens. Given a question, its class is identified and the question is modified accordingly to include the appropriate token(s). The search engine is modified to rank and return short passages of text rather than documents. The QA-Tokens are used in later stages of analysis to extract the supposed answers from these returned passages. Finally, all potential answers are ranked using a novel formula, which determines which ones among them are most likely to be correct.

On-line sources of news typically follow a particular pattern when presenting updates on a news event over time. First, they produce a preliminary report on the event, and later send out updates as the story evolves. There are two classes of readers accessing the latter stories - these who have read the original announcement and are familiar with the story background and those who are \joining" the thread at a later point in time. Because of the existence of the two clases of readers, news sources typically include in consequent stories some information that was already present in earlier stories. We discuss our approach to identifying such repeated pieces of information in news threads and show how this knowledge can help in generating userspeci c summaries of entire threads of articles. 1 Introduction To be able to generate summaries of threads of articles, it is important to do two things: identify which articles belong together (because they refer to the same event) and id...

Automatic text summarization provides a concise summary for a document. In this thesis, we present a cut-and-paste approach to addressing the text generation problem in domain-independent, single-document summarization. We found that professional abstractors often reuse the text in an original docu-ment for producing the text in a summary. But rather than simply extracting the original text, as in most existing automatic summarizers, humans often edit the extracted sen-tences. We call such editing operations “revision operations”. Our summarizer simu-lates two revision operations that are frequently used by humans: sentence reduction and sentence combination. Sentence reduction removes inessential phrases from sentences and sentence combination merges sentences and phrases together. The sentence reduc-tion algorithm we propose relies on multiple sources of knowledge to decide when it is appropriate to delete a phrase from a sentence, including linguistic knowledge, prob-abilities trained from corpus examples, and context information. The sentence combi-nation module relies on a set of rules to decide how to combine sentences and phrases and when to combine them. Sentence reduction aims to improve the conciseness of

In this thesis, we present a user-sensitive approach to text summarization. One domain which would highly benefit from tailoring summaries to both individual and class-based user characteristics is the medical domain, where physicians and patients access similar information, each with their own needs and abilities. Our framework is a medical digital library for physicians and patients. We describe a summarizer, which generates summaries of findings in an input set of clinical studies. When a physician is treating a specific patient, he’s looking for information relevant to the patient’s history and problems. The summarizer takes the user’s interests into account and presents only the findings pertaining to a user model, as approximated by an existing patient record. The same synthesis of information can also be of interest to the patient. The summarizer predicts which medical terms used in a text will be too technical for patients, and augments it with appropriate definitions when necessary. We adopt a generation-like architecture for our summarizer. However, be-cause our input is textual and not semantic, new challenges arise. We operate over

In this paper, we propose using standard XML messaging interfaces between components of natural language dialog systems. We describe a stock trading and information access system, where XML is used to encode speech acts, transactions and retrieved information in messages between system components. We use an XML/XSL based unification approach to display personalized, multi-modal system responses. We are proposing the creation of XML standards for all messaging between components of NLP systems. We hope that the use of XML in messaging will promote greater interoperability of both data and code. The working name of the proposed standard messaging language(s) is DSML ("Dialog System Markup Language".) 1