The goal of query performance prediction (QPP) is to automatically estimate the effectiveness of a search result for any given query, without relevance judgements. Post-retrieval features have been shown to be more effective for this task while being more expensive to compute than pre-retrieval features. Combining multiple post-retrieval features is even more effective, but state-of-the-art QPP methods are impossible to interpret because of the black-box nature of the employed machine learning models. However, interpretation is useful for understanding the predictive model and providing more answers about its behavior. Moreover, combining many post-retrieval features is not applicable to real-world cases, since the query running time is of utter importance. In this paper, we investigate a new framework for feature selection in which the trained model explains well the prediction. We introduce a step-wise (forward and backward) model selection approach where different subsets of query features are used to fit different models from which the system selects the best one. We evaluate our approach on four TREC collections using standard QPP features. We also develop two QPP features to address the issue of query-drift in the query feedback setting. We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness.

This article presents a summary graph to show the relationships between Information Retrieval (IR) and other related disciplines. The figure tells the key differences between them and the conditions under which one would transition into another. When I studied Machine Learning (ML), my favorite figure among all was "The Table of Common Distributions" in Casella and Berger's 2002 book "Statistical Inference". It appeared in the book's appendix. Every time when I saw this figure, I was in awe.

Online learning to rank (LTR) focuses on learning a policy from user interactions that builds a list of items sorted in decreasing order of the item utility. It is a core area in modern interactive systems, such as search engines, recommender systems, or conversational assistants. Previous online LTR approaches either assume the relevance of an item in the list to be independent of other items in the list or the relevance of an item to be a submodular function of the utility of the list. The former type of approach may result in a list of low diversity that has relevant items covering the same aspects, while the latter approaches may lead to a highly diversified list but with some non-relevant items. In this paper, we study an online LTR problem that considers both item relevance and topical diversity. We assume cascading user behavior, where a user browses the displayed list of items from top to bottom and clicks the first attractive item and stops browsing the rest. We propose a hybrid contextual bandit approach, called CascadeHybrid, for solving this problem. CascadeHybrid models item relevance and topical diversity using two independent functions and simultaneously learns those functions from user click feedback. We derive a gap-free bound on the n-step regret of CascadeHybrid. We conduct experiments to evaluate CascadeHybrid on the MovieLens and Yahoo music datasets. Our experimental results show that CascadeHybrid outperforms the baselines on both datasets.

According to new data, up to 80% of popular US-based e-commerce stores use JavaScript on crucial content such as product descriptions. That's an alarming number considering any time JavaScript is used to generate important content it runs the risk of not being indexed in search results. Google is getting better at crawling and rendering JavaScript, but it's not perfect. The company still recommends using static HTML as much as possible. The study, from software company Onely, found that 25% of web pages analyzed contained crucial JavaScript content that was unindexed by Google.

This paper introduces scikit-hubness, a Python package for efficient nearest neighbor search in high-dimensional spaces. Hubness is an aspect of the curse of dimensionality, and is known to impair various learning tasks, including classification, clustering, and visualization. scikit-hubness provides algorithms for hubness analysis ("Is my data affected by hubness?"), hubness reduction ("How can we improve neighbor retrieval in high dimensions?"), and approximate neighbor search ("Does it work for large data sets?"). It is integrated into the scikit-learn environment, enabling rapid adoption by Python-based machine learning researchers and practitioners. Users will find all functionality of the scikit-learn neighbors package, plus additional support for transparent hubness reduction and approximate nearest neighbor search. scikit-hubness is developed using several quality assessment tools and principles, such as PEP8 compliance, unit tests with high code coverage, continuous integration on all major platforms (Linux, MacOS, Windows), and additional checks by LGTM. The source code is available at https://github.com/VarIr/scikit-hubness under the BSD 3-clause license. Install from the Python package index with $ pip install scikit-hubness.

The motivation, concept, design and implementation of latent semantic search for search engines have limited semantic search, entity extraction and property attribution features, have insufficient accuracy and response time of latent search, may impose privacy concerns and the search results are unavailable in offline mode for robotic search operations. The alternative suggestion involves autonomous search engine with adaptive storage consumption, configurable search scope and latent search response time with built-in options for entity extraction and property attribution available as open source platform for mobile, desktop and server solutions. The suggested architecture attempts to implement artificial general intelligence (AGI) principles as long as autonomous behaviour constrained by limited resources is concerned, and it is applied for specific task of enabling Web search for artificial agents implementing the AGI.

Don't be limited by a search engine that doesn't understand the user intent or the context. Enjoy the power of highly targeted, intuitive and conceptual search and exploration. To help you easily skim through the results, we offer a wide variety of options like Clustering, Semantic Cloud and Intuitive Facets. You could also get exploratory with our Concept Search. We promise a quicker and better search every time!

Google's newest algorithmic update, BERT, helps Google understand natural language better, particularly in conversational search. BERT will impact around 10% of queries. It will also impact organic rankings and featured snippets. So this is no small change! But did you know that BERT is not just any algorithmic update, but also a research paper and machine learning natural language processing framework?

Listwise learning-to-rank methods form a powerful class of ranking algorithms that are widely adopted in applications such as information retrieval. These algorithms learn to rank a set of items by optimizing a loss that is a function of the entire set---as a surrogate to a typically non-differentiable ranking metric. Despite their empirical success, existing listwise methods are based on heuristics and remain theoretically ill-understood. In particular, none of the empirically-successful loss functions are related to ranking metrics. In this work, we propose a cross entropy-based learning-to-rank loss function that is theoretically sound and is a convex bound on NDCG, a popular ranking metric. Furthermore, empirical evaluation of an implementation of the proposed method with gradient boosting machines on benchmark learning-to-rank datasets demonstrates the superiority of our proposed formulation over existing algorithms in quality and robustness.

The excessively increased volume of data in modern data management systems demands an improved system performance, frequently provided by data distribution, system scalability and performance optimization techniques. Optimized horizontal data partitioning has a significant influence of distributed data management systems. An optimally partitioned schema found in the early phase of logical database design without loading of real data in the system and its adaptation to changes of business environment are very important for a successful implementation, system scalability and performance improvement. In this paper we present a novel approach for finding an optimal horizontally partitioned schema that manifests a minimal total execution cost of a given database workload. Our approach is based on a formal model that enables abstraction of the predicates in the workload queries, and are subsequently used to define all relational fragments. This approach has predictive features acquired by simulation of horizontal partitioning, without loading any data into the partitions, but instead, altering the statistics in the database catalogs. We define an optimization problem and employ a genetic algorithm (GA) to find an approximately optimal horizontally partitioned schema. The solutions to the optimization problem are evaluated using PostgreSQL's query optimizer. The initial experimental evaluation of our approach confirms its efficiency and correctness, and the numbers imply that the approach is effective in reducing the workload execution cost.