Coupled Hierarchical IR and Stochastic Models for Surface Information Extraction

We present in this paper a combination of Machine Learning based Information Retrieval (IR) techniques and stochastic language modelling in a hierarchical system that extracts surface information from text. At the lowest level of this hierarchy, documents and paragraphs are successively routed with IR techniques. At the top level, a stochastic language model extracts the most relevant phrases, and labels the type of information they contain. The approach and preliminary results are demonstrated on a subset of the MUC-6 Scenario Templates task.

• Type: Conference
• Year: 1998
• Where: ECIR
• Authors: Hugo Zaragoza, Patrick Gallinari
• Keywords: ECIR 1998, Information Technology, IR Techniques, Stochastic Language, Stochastic Language Modelling