Titlebook: Language Modeling for Information Retrieval; W. Bruce Croft (Distinguished Professor),John Laff Book 2003 Springer Science+Business Media

喚醒

拾落穗

紅腫

puzzle

Language Modeling and Relevance,e examine the issues involved, especially in dealing with multiple relevant documents and in applying relevance feedback, and consider various strategies for developing the language modeling approach to accommodate multiple, rather than single, relevant documents in a theoretically principled way.

BALE

Grating

細(xì)頸瓶

A Probabilistic Approach to Term Translation for Cross-Lingual Retrieval,, when used with a probabilistic retrieval model, can produce better retrieval than non-probabilistic techniques such as structural query translation (Pirkola, 1998) and Machine Translation. We will also show that parallel corpora and manual lexicons are complementary and their combination is essent

Memorial

Using Compression-Based Language Models for Text Categorization,ategorization. Category models are constructed using the Prediction by Partial Matching (PPM) text compression scheme, specifically using character-based rather than word-based contexts. Two approaches to compression-based categorization are presented, one based on ranking by document cross entropy

施舍

過時

An Unbiased Generative Model for Setting Dissemination Thresholds, profile. Documents with scores above profile-specific dissemination thresholds are delivered. Optimal dissemination thresholds are usually difficult to determine a priori, so they are often learned during filtering, using relevance feedback about disseminated documents. However, the scores of disse