This paper presents a method for combining query-relevance with information-novelty in the context of text retrieval and summarization.The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in re-ranking retrieved documents and in selecting apprw priate passages for text summarization. Preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization. The latter are borne out by the recent results of the SUMMAC conference in the evaluation of summarization systems. However, the clearest advantage is demonstrated in constructing non-redundant multi-document summaries, where MMR results are clearly superior to non-MMR passage selection.

This paper discusses a text extraction approach to multidocument summarization that builds on single-document summarization methods by using additional, available information on about the document set as a whole and the relationships between the documents. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Our approach addresses these issues by using domainindependent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements.

This paper presents a method for combining query-relevance with information-novelty in the context of text retrieval and summarization.The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in re-ranking retrieved documents and in selecting apprw priate passages for text summarization. Preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization. The latter are borne out by the recent results of the SUMMAC conference in the evaluation of summarization systems. However, the clearest advantage is demonstrated in constructing non-redundant multi-document summaries, where MMR results are clearly superior to non-MMR passage selection.

Tools for creating data graphics are complex, require significant graphic expertise, and use predefmed graphics that cannot integrate multiple data types. To solve these problems, we applied automatic data presentation capabilities to enable two interactive design tools. SageBrush enables users to assemble gmphical sketches from primitives and partial prototypes, SageBook enables users to browse previously created pictures relevant to new data. SAGE, an automatic presen~ation system, supports these by completing underspecified designs, rendering unique graphic combinations, searching for relevant pictures, and redesigning old pictures to display new data, Our claim is that design interfaces must have automatic graphic knowledge to be effective.We demonstrate a simple and powerful predictive interface technique for text editing tasks. With cur technique called thedynamic mucro creation, when a user types a special "repeat" key after doing repetitive operations in a [text editor, an editing sequence corresponding to one iteration is detected, defined as a macro, and executed at the same time. When we use another special "predict" key in addkion to the repeat key, wider range of prediction schemes can be performed (depending on the order of using these two keys.207

This paper discusses a text extraction approach to multidocument summarization that builds on single-document summarization methods by using additional, available in-, formation about the document set as a whole and the relationships between the documents. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Our approach addresses these issues by using domainindependent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements.