Pivoted document length normalization
SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Document normalization revisited
SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Analysis of anchor text for web search
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Simple BM25 extension to multiple weighted fields
Proceedings of the thirteenth ACM international conference on Information and knowledge management
A study of the dirichlet priors for term frequency normalisation
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
TREC: Experiment and Evaluation in Information Retrieval (Digital Libraries and Electronic Publishing)
How are we searching the World Wide Web? A comparison of nine search engine transaction logs
Information Processing and Management: an International Journal - Special issue: Formal methods for information retrieval
Term frequency normalisation tuning for BM25 and DFR models
ECIR'05 Proceedings of the 27th European conference on Advances in Information Retrieval Research
Retrieval sensitivity under training using different measures
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
| Hi-index | 0.00 |
Per-field normalisation has been shown to be effective for Web search tasks, e.g. named-page finding. However, per-field normalisation also suffers from having hyper-parameters to tune on a per-field basis. In this paper, we argue that the purpose of per-field normalisation is to adjust the linear relationship between field length and term frequency. We experiment with standard Web test collections, using three document fields, namely the body of the document, its title, and the anchor text of its incoming links. From our experiments, we find that across different collections, the linear correlation values, given by the optimised hyper-parameter settings, are proportional to the maximum negative linear correlation. Based on this observation, we devise an automatic method for setting the per-field normalisation hyper-parameter values without the use of relevance assessment for tuning. According to the evaluation results, this method is shown to be effective for the body and title fields. In addition, the difficulty in setting the per-field normalisation hyper-parameter for the anchor text field is explained.