Book Review: Statistical Language Models for Information Retrieval by ChengXiang Zhai

By Chengxiang Zhai. 2008

200 citations recorded by the source corpus.

Statistical language models have recently been successfully applied to many information retrieval problems. A great deal of recent work has shown that statistical language models not only achieve superior empirical performance, but also facilitate parameter tuning and provide a more principled way, in general, for modeling various kinds of complex and non-traditional retrieval problems.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xueqi Cheng
2. Jiafeng Guo
3. Yixing Fan
4. Xinyu Ma
5. Ruqing Zhang
6. Xiang Ji
7. Shizhu He
8. Dong Zhou

In Information Systems

1. Xinyu Ma
2. Dong Zhou
3. T. Brailsford
4. Mark Truran
5. Helen Ashman
6. Vincent P. Wade
7. Xueqi Cheng
8. Jiafeng Guo

Citations in the corpus

• Translation techniques in cross-language information retrieval (2012, background): “The basic idea here is to estimate the probability of a query given a document language model (see [Liu and Croft 2005; Zhai 2009] for surveys of language models and their uses).”
• NIRMAL: Automatic identification of software relevant tweets leveraging language model (2015, unknown): “[10], [12], [13], [30].”
• A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development (2023, background): “However, the strong creativity of ChatGPT is a double-edged sword, especially in the filed of education and science [31], [32].”
• PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval (2020, methodology): “Different methods have been proposed for the document language model θD , among which a multinomial unigram language model has been most popular and most successful [42].”