Query Performance Prediction (QPP) estimates the effectiveness of retrieval systems for a given query, offering valuable insights for search effectiveness and query processing. Despite extensive research, a critical gap remains in understanding how well QPPs generalize across diverse retrieval paradigms and collections, a question of robustness that has significant implications for their practical utility. This article provides the first comprehensive cross-paradigm evaluation of QPP robustness and generalization capabilities, examining state-of-the-art QPPs including NQC, WIG, LETOR-based features, and newly explored dense-based predictors MQPPF and BERT-QPP. We systematically assess their performance across diverse sparse (BM25, DFree with and without query expansion), hybrid (SPLADE), and dense (ColBERT, TCT-ColBERT) rankers on four benchmark collections: TREC Robust, GOV2, WT10G, and MS-MARCO. The results reveal fundamental robustness challenges: predictors exhibit significant variability in accuracy, with collection being the dominant factor, followed by ranker type. Some sparse predictors perform adequately on specific collections such as TREC Robust and GOV2, but critically fail to generalize to other collections like WT10G and MS-MARCO. Dense-based predictors, while showing promise in specific scenarios with dense rankers, similarly lack generalization to sparse contexts. We demonstrate that these generalization failures severely limit practical applications: QPP-driven selective query processing achieves only marginal gains ( \(\approx\) 4% NDCG improvement), with reliability varying dramatically across settings. Our findings underscore that current QPP methods lack the robustness necessary for real-world deployment and highlight the urgent need for predictors that generalize reliably across diverse collections, align with modern dense retrieval architectures, and provide consistent utility for downstream applications. We publicly release our data and code to facilitate future research on robust QPP methods ( https://github.com/adrianchifu/UncoveringTheLimitationsofQPP/ ).

This paper presents our investigation into dense retrieval models for Amharic, a low-resource language spoken by more than 120 million people.We constructed training datasets tailored to dense retrieval models and evaluated model performance by comparing dense and sparse retrieval approaches on Amharic information retrieval.The study also highlights the challenges and efforts involved in advancing retrieval systems for low-resource languages.

In information retrieval systems, search parameters are optimized to ensure high effectiveness based on a set of past searches, and these optimized parameters are then used as the search configuration for all subsequent queries. A better approach, however, would be to adapt the parameters to fit the query at hand. Selective query expansion is one such an approach, in which the system decides automatically whether or not to expand the query, resulting in two possible search configurations. This approach was extended recently to include many other parameters, leading to many possible search configurations where the system automatically selects the best configuration on a per-query basis. One problem with this approach is the system training, which requires evaluation of each training query with every possible configuration. In real-world systems, so many parameters and possible values must be evaluated that this approach is impractical, especially when the system must be updated frequently, as is the case for commercial search engines. In general, the more configurations, the greater the effectiveness when configuration selection is appropriate but also the greater the risk of decreasing effectiveness in the case of an inappropriate configuration selection. To determine the ideal configurations to be used for each query in real-world systems, we have developed a method in which a limited number of possible configurations are pre-selected, then used in a meta-search engine that decides the best search configuration for each query. We define a risk-sensitive approach for configuration pre-selection that considers the risk-reward tradeoff between the number of configurations kept and system effectiveness. We define two alternative risk functions to apply to different goals. For final configuration selection, the decision is based on query feature similarities. We compare two alternative risk functions on two query types (ad hoc and diversity) and compare these to more sophisticated machine learning based methods. We find that a relatively small number of configurations (20) selected by our risk-sensitive model is sufficient to obtain results close to the best achievable results for each query. Effectiveness is increased by about 15% according to the P@10 and nDCG@10 evaluation metrics when compared to traditional grid search using a single configuration and by about 20% when compared to learning to rank documents. Our risk-sensitive approach works for both diversity- and ad hoc oriented searches. Moreover, the similarity-based selection method outperforms the more sophisticated approaches. Thus, we demonstrate the feasibility of developing per-query information retrieval systems, which will guide future research in this direction.

To date, query performance prediction (QPP) in the context of content-based image retrieval remains a largely unexplored task, especially in the query-by-example scenario, where the query is an image. To boost the exploration of the QPP task in image retrieval, we propose the first benchmark for image query performance prediction (iQPP). First, we establish a set of four data sets (PASCAL VOC 2012, Caltech-101, ROxford5k and RParis6k) and estimate the ground-truth difficulty of each query as the average precision or the precision@k, using two state-of-the-art image retrieval models. Next, we propose and evaluate novel pre-retrieval and post-retrieval query performance predictors, comparing them with existing or adapted (from text to image) predictors. The empirical results show that most predictors do not generalize across evaluation scenarios. Our comprehensive experiments indicate that iQPP is a challenging benchmark, revealing an important research gap that needs to be addressed in future work. We release our code and data as open source at https://github.com/Eduard6421/iQPP, to foster future research.

A search engine generally applies a single search strategy to any user query. The search combines many component processes (e.g., indexing, query expansion, search-weighting model, document ranking) and their hyperparameters, whose values are optimized based on past queries and then applied to all future queries. Even an optimized system may perform poorly on some queries, however, whereas another system might perform better on those queries. Selective search strategy aims to select the most appropriate combination of components and hyperparameter values to apply for each individual query. The number of candidate combinations is huge. To adapt best to any query, the ideal system would use many combinations. In the real world it would be too costly to use and maintain thousands of configurations. A trade-off must therefore be found between performance and cost. In this paper, we describe a risk-sensitive approach to optimize the set of configurations that should be included in a selective search strategy. This approach solves the problem of which and how many configurations to include in the system. We show that the use of 20 configurations results in significantly greater effectiveness than current approaches when tested on three TREC reference collections, by about 23% when compared to L2R documents and about 10% when compared to other selective approaches, and that it offers an appropriate trade-off between system complexity and system effectiveness.

In information retrieval (IR), documents that match the query are retrieved. Search engines usually conflate word variants into a common stem when indexing documents because queries and documents do not need to use exactly the same word variant for the documents to be relevant. Stemmers are known to be effective in many languages for IR. However, there are still languages where stemmers or morphological analyzers are missing; this is the case for Amharic which is the working language of Ethiopia. Morphological analysis is the key to derive stems, roots (primary lexical units) and grammatical markers of words such as person, tense and negation markers. This paper presents morphologically annotated Amharic lexicons as well as stem-based and root-based morphologically annotated corpora which could be used by the research community as benchmark collections either to evaluate morphological analyzers or information retrieval for Amharic. Such resources are believed to foster research in Amharic IR.

Performance anomalies are a core problem in modern information systems, that affects the execution of the hosted applications. The detection of these anomalies often relies on the analysis of the application execution logs. The current most effective approach is to detect samples that differ from a learnt nominal model. However, current methods often focus on detecting sequential anomalies in logs, neglecting the time elapsed between logs, which is a core component of the performance anomaly detection. In this paper, we develop a new model for performance anomaly detection that captures temporal deviations from the nominal model, by means of a sliding window data representation. This nominal model is trained by a Long Short-Term Memory neural network, which is appropriate to represent complex sequential dependencies. We assess the effectiveness of our model on both simulated and real datasets. We show that it is more robust to temporal variations than current state-of-the-art approaches, while remaining as effective.

International audience

Automatic fact-checking is an important challenge nowadays since anyone can write about anything and spread it in social media, no matter the information quality. In this paper, we revisit the information check-worthiness problem and propose a method that combines the "information nutritional label" features with POS-tags and word-embedding representations. To predict the information check-worthy claim, we train a machine learning model based on these features. We experiment and evaluate the proposed approach on the CheckThat! CLEF 2018 collection. The experimental result shows that our model that combines information nutritional label and word-embedding features outperforms the baselines and the official participants' runs of CheckThat! 2018 challenge.

Modern Information Retrieval (IR) systems have become more and more complex, involving a large number of parameters. For example, a system may choose from a set of possible retrieval models (BM25, language model, etc.), or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. Traditionally, these parameters are set at a system level based on training queries, and the same parameters are then used for different queries. We observe that it may not be easy to set all these parameters separately, since they can be dependent. In addition, a global setting for all queries may not best fit all individual queries with different characteristics. The parameters should be set according to these characteristics. In this article, we propose a novel approach to tackle this problem by dealing with the entire system configurations (i.e., a set of parameters representing an IR system behaviour) instead of selecting a single parameter at a time. The selection of the best configuration is cast as a problem of ranking different possible configurations given a query. We apply learning-to-rank approaches for this task. We exploit both the query features and the system configuration features in the learning-to-rank method so that the selection of configuration is query dependent. The experiments we conducted on four TREC ad hoc collections show that this approach can significantly outperform the traditional method to tune system configuration globally (i.e., grid search) and leads to higher effectiveness than the top performing systems of the TREC tracks. We also perform an ablation analysis on the impact of different features on the model learning capability and show that query expansion features are among the most important for adaptive systems.

Query performance prediction (QPP) aims at automatically estimating the information retrieval system effectiveness for any user's query. Previous work has investigated several types of pre- and post-retrieval query performance predictors; the latter has been shown to be more effective. In this paper we investigate the use of features that were initially defined for learning to rank in the task of QPP. While these features have been shown to be useful for learning to rank documents, they have never been studied as query performance predictors. We developed more than 350 variants of them based on summary functions. Conducting experiments on four TREC standard collections, we found that Letor-based features appear to be better QPP than predictors from the literature. Moreover, we show that combining the best Letor features outperforms the state of the art query performance predictors. This is the first study that considers such an amount and variety of Letor features for QPP and that demonstrates they are appropriate for this task.

Some methods have been developed for automatic effectiveness evaluation without relevance judgments. We propose to use those methods, and their combination based on a machine learning approach, for query performance prediction. Moreover, since predicting average precision as it is usually done in query performance prediction literature is sensitive to the reference system that is chosen, we focus on predicting the average of average precision values over several systems. Results of an extensive experimental evaluation on ten TREC collections show that our proposed methods outperform state-of-the-art query performance predictors.

Sentence ordering (SO) is a key component of verbal ability. It is also crucial for automatic text generation. While numerous researchers developed various methods to automatically evaluate the informativeness of the produced contents, the evaluation of readability is usually performed manually. In contrast to that, we present a self-sufficient metric for SO assessment based on text topic-comment structure. We show that this metric has high accuracy.

Information Retrieval (IR) systems heavily rely on a large number of parameters, such as the retrieval model or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. However, setting all these parameters individually can often be a tedious task, since they can all affect one another, while also vary for different queries. We propose to tackle this problem by dealing with entire system configurations (i.e. a set of parameters representing an IR system) instead of single parameters, and to apply state-of-the-art Learning to Rank techniques to select the most appropriate configuration for a given query. The experiments we conducted on two TREC AdHoc collections show that this approach is feasible and significantly outperforms the traditional way to configure a system, as well as the top performing systems of the TREC tracks. We also show an analysis on the impact of different features on the model's learning capability.

Predicting if a query will be difficult for a system is important to improve retrieval effectiveness by implementing specific processing. There have been several attempts to predict difficulty, both automatically and manually; but without high accuracy at a pre-retrieval stage. In this paper, we focus rather on understanding Why a query is perceived by humans as difficult. We ran two separated but related experiments in which we asked humans to provide both a query difficulty prediction and reasons to explain their prediction. Results show that: (i) reasons can be categorized into 4 classes; (ii) reasons can be framed into closed questions to be answered on a Likert scale; and (iii) some reasons correlate in a coherent way with the human predicted numerical difficulty. On the basis of these results it is possible to derive hints to be provided to help users when formulating their queries and to avoid them to rely on their wrong perception of difficulty.

Abstract This article describes an information retrieval approach according to the two different search modes that exist: browsing an ontology (via categories) or defining a query in free language (via keywords). Various proposals offer approaches adapted to one of these two modes. We present a proposal leading to a system allowing the integration of both modes using the same search engine. This engine is adapted according to each possible search mode.

In this paper we present a system that allows a user to explore or mine a document collection. This system is based on domain and task knowledge modelled in the form of ontologies and allows direct access both to information as it is stored and to information that is built from it. The system has been developed in Java.

Abstract This paper presents a novel user interface that provides global visualizations of large document sets in order to help users to formulate the query that corresponds to their information needs and to access the corresponding documents. An important element of the approach we introduce is the use of concept hierarchies (CHs) in order to structure the document collection. Each CH corresponds to a facet of the documents users can be interested in. Users browse these CHs in order to specify and refine their information needs. Additionally the interface is based on OLAP principles and multi‐dimensional analysis operators are provided to users in order to allow them to explore a document collection.

No abstract available.