End-to-End Query Term Weighting (TW-BERT)
The document discusses a new model called Term Weighting BERT (TW-BERT) aimed at improving the effectiveness of lexical retrieval systems by predicting weights for query terms such as unigrams and read more
Towards Disentangling Relevance and Bias in Unbiased Learning to Rank
The paper is titled “Towards Disentangling Relevance and Bias in Unbiased Learning to Rank” by authors affiliated with various institutions including the University of Illinois and Google Research. The study read more
Training a Ranking Model
This patent application describes a method and system for training a ranking machine learning model, particularly for use in search engines to enhance the relevance and ranking of search results read more
Ranking Search Result Documents
The patent describes methods and apparatus for using document and query features to determine a presentation characteristic for displaying a search result. It focuses on improving the relevance and presentation read more
Learning-to-Rank with BERT in TF-Ranking
The paper introduces a machine learning algorithm for document ranking, employing BERT for query and document encoding and TF-Ranking (TFR) for further optimization. TF-Ranking, a TensorFlow-based library, specializes in ranking read more
Permutation Equivariant Document Interaction Network for Neural Learning-to-Rank
This research paper by Rama Kumar Pasumarthi, Honglei Zhuang, Xuanhui Wang, Michael Bendersky, and Marc Najork focuses on improving ranking performance in information retrieval using deep learning.
Generating author vectors
The patent revolves around methods, systems, and apparatuses for generating “author vectors,” which are essentially digital representations of authors based on their writing style and content. This invention uses neural read more
Website Representation Vector
This patent describes a system and method for improving web search results by using vectors to represent websites. These vectors help classify and differentiate websites based on their relevance and read more
Knowledge-Based Trust: Estimating the Trustworthiness of Web Sources
The document titled “Knowledge-Based Trust: Estimating the Trustworthiness of Web Sources” discusses a novel approach to evaluating the reliability of web sources based on the accuracy of factual information they read more
Systems and Methods for Re-Ranking ranked Search Results
The patent describes a system, a storage medium, and a method for re-ranking search results based on certain predefined criteria. Specifically, it focuses on swapping the positions of search results read more