Logistic Regression and EVIs for XML Books and the Heterogeneous Track

Authors:
Ray R. Larson
Affiliations:
School of Information, University of California, Berkeley, Berkeley, USA 94720-4600
Venue:
Focused Access to XML Documents
Year:
2008

Citing 14
Cited 2

Relevance feedback and other query modification techniques

Information retrieval
Probabilistic retrieval based on staged logistic regression

SIGIR '92 Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval
Searching distributed collections with inference networks

SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
Effective retrieval with distributed collections

Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
GlOSS: text-source discovery over the Internet

ACM Transactions on Database Systems (TODS)
A logistic regression approach to distributed IR

SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Generalizing GlOSS to Vector-Space Databases and Broker Hierarchies

VLDB '95 Proceedings of the 21th International Conference on Very Large Data Bases
Multilingual Information Retrieval Using English and Chinese Queries

CLEF '01 Revised Papers from the Second Workshop of the Cross-Language Evaluation Forum on Evaluation of Cross-Language Information Retrieval Systems
Multilingual Information Retrieval Using Machine Translation, Relevance Feedback and Decompounding

Information Retrieval
A Fusion Approach to XML Structured Document Retrieval

Information Retrieval
Entry vocabulary: a technology to enhance digital search

HLT '01 Proceedings of the first international conference on Human language technology research
Probabilistic retrieval, component fusion and blind feedback for XML retrieval

INEX'05 Proceedings of the 4th international conference on Initiative for the Evaluation of XML Retrieval
Domain-specific CLIR of english, german and russian using fusion and subject metadata for query expansion

CLEF'05 Proceedings of the 6th international conference on Cross-Language Evalution Forum: accessing Multilingual Information Repositories
Component ranking and automatic query refinement for XML retrieval

INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval

Overview of the INEX 2007 Book Search track: BookSearch '07

ACM SIGIR Forum
Overview of the INEX 2007 Book Search Track (BookSearch'07)

Focused Access to XML Documents

Quantified Score

Hi-index	0.00

Visualization

Abstract

For this year's INEX UC Berkeley focused on the Book track and the Heterogeneous track, For these runs we used the TREC2 logistic regression probabilistic model with blind feedback as well as Entry Vocabulary Indexes (EVIs) for the Books Collection MARC data. For the full text records of the book track we encountered a number of interesting problems in setting up the database, and ended up using page-level indexing of the full collection.As (once again) the only group to actually submit runs for the Het track, we are guaranteed both the highest, and lowest, effectiveness scores for each task. However, because it was again deemed pointless to conduct the actual relevance assessments on the submissions of a single system, we do not know the exact values of these results.