5 papers
Ranking suspected answers to natural language questions using predictive annotation
Dragomir R. Radev, John Prager, Valerie Samn
In this paper, we describe a system to rank suspected answers to natural language questions. We process both corpus and query using a new technique, predictive annotation, which au…
Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies
Dragomir R. Radev, Hongyan Jing, Malgorzata Budzikowska
We present a multi-document summarizer, called MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We also describe two new t…
Learning Correlations between Linguistic Indicators and Semantic Constraints: Reuse of Context-Dependent Descriptions of Entities
Dragomir R. Radev
This paper presents the results of a study on the semantic constraints imposed on lexical choice by certain contextual indicators. We show how such indicators are computed and how…
Tagging French Without Lexical Probabilities -- Combining Linguistic Knowledge And Statistical Learning
Evelyne Tzoukermann, Dragomir R. Radev, William A. Gale
This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected langua…
Use of Weighted Finite State Transducers in Part of Speech Tagging
Evelyne Tzoukermann, Dragomir R. Radev
This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state…