%0 Journal Article %1 ponte_language_2017 %A Ponte, Jay M. %A Croft, W. Bruce %D 2017 %J SIGIR Forum %K texttechnologie %P 202--208 %T A language modeling approach to information retrieval %V 51 %X Models of document indexing and document retrieval have been extensively studied. The integration of these two classes of models has been the goal of several researchers but it is a very difficult problem. We argue that much of the reason for this is the lack of an adequate indexing model. This suggests that perhaps a better indexing model would help solve the problem. However, we feel that making unwarranted parametric assumptions will not lead to better retrieval performance. Furthermore, making prior assumptions about the similarity of documents is not warranted either. Instead, we propose an approach to retrieval based on probabilistic language modeling. We estimate models for each document individually. Our approach to modeling is non-parametric and integrates document indexing and document retrieval into a single model. One advantage of our approach is that collection statistics which are used heuristically in many other retrieval models are an integral part of our model. We have implemented our model and tested it empirically. Our approach significantly outperforms standard tf.idf weighting on two different collections and query sets.

@article{ponte_language_2017, abstract = {Models of document indexing and document retrieval have been extensively studied. The integration of these two classes of models has been the goal of several researchers but it is a very difficult problem. We argue that much of the reason for this is the lack of an adequate indexing model. This suggests that perhaps a better indexing model would help solve the problem. However, we feel that making unwarranted parametric assumptions will not lead to better retrieval performance. Furthermore, making prior assumptions about the similarity of documents is not warranted either. Instead, we propose an approach to retrieval based on probabilistic language modeling. We estimate models for each document individually. Our approach to modeling is non-parametric and integrates document indexing and document retrieval into a single model. One advantage of our approach is that collection statistics which are used heuristically in many other retrieval models are an integral part of our model. We have implemented our model and tested it empirically. Our approach significantly outperforms standard tf.idf weighting on two different collections and query sets.}, added-at = {2018-11-04T17:02:36.000+0100}, author = {Ponte, Jay M. and Croft, W. Bruce}, biburl = {https://www.bibsonomy.org/bibtex/20ed892d97ed5f3617765696988a51111/lepsky}, interhash = {554c406485bef5bf0021d8a19e1e1d8d}, intrahash = {0ed892d97ed5f3617765696988a51111}, issn = {01635840}, journal = {SIGIR Forum}, keywords = {texttechnologie}, month = jul, pages = {202--208}, timestamp = {2018-11-04T17:02:36.000+0100}, title = {A language modeling approach to information retrieval}, volume = 51, year = 2017 }