Graph-based techniques relying on neural networks and embeddings have gained attention as a way to develop Recommender Systems (RS) with several papers on the topic presented at SIGIR 2022 and 2023. Given the importance of ensuring that published research is methodologically sound and reproducible, in this paper, we analyze 10 graph-based RS papers, most of which were published at SIGIR 2022, and assess their impact on subsequent work published in SIGIR 2023. Our analysis reveals several critical points that require attention: (i) the prevalence of bad practices, such as erroneous data splits or information leakage between training and testing data, which call into question the validity of the results; (ii) frequent inconsistencies between the provided artifacts (source code and data) and their descriptions in the paper, causing uncertainty about what is actually being evaluated; and (iii) the preference for new or complex baselines that are weaker compared to simpler ones, creating the impression of continuous improvement even when, particularly for the Amazon-Book dataset, the state-of-the-art has significantly worsened. Due to these issues, we are unable to confirm the claims made in most of the papers that we examined and attempted to reproduce.

Recent advances in representation learning have enabled neural Information Retrieval (IR) systems to use learned dense representations for queries and documents to effectively handle semantics, language nuances, and vocabulary mismatch problems. In contrast to traditional IR systems that rely on word matching, dense IR models exploit query/document similarity in dense latent spaces to account for semantics. This requires substantial training data and comes with increased computational demands. Thus, it would be beneficial to predict how a system will perform for a given query to decide whether a dense IR model is the best option or alternatives should be used. Traditional Query Performance Prediction (QPP) models are designed for lexical IR approaches and perform sub-optimally when applied to dense neural IR systems. Therefore, there has been a renewed interest in QPP methods to improve their effectiveness for dense neural IR models. While the results of the new QPP methods are generally encouraging, there is ample room for improvement in absolute performance and stability. We argue that by using features more aligned with the underlying rationale of dense IR models, we can enhance the performance of QPP. In this respect, we propose the Projection-Displacement-Based QPP (PDQPP), which exploits the geometric properties of dense IR models, projects queries and retrieved documents onto subspaces defined by pseudo-relevant documents, and considers changes in retrieval scores within them as a proxy for retrieval coherence. Minor score changes suggest robust and coherent retrieval, while significant alterations indicate semantic divergence and potentially poor performance. Results over a wide range of experimental settings on both traditional (TREC Robust) and neural-oriented (TREC Deep Learning) test collections show that PDQPP mostly outperforms the state-of-the-art QPP baselines.

Dense Information Retrieval (IR) systems rely on neural networks to embed documents and queries within a latent low-dimensional space. Among the Dense IR approaches, bi-encoders are particularly popular, as they achieve state-of-the-art performance and allow for efficient encoding of documents and queries. Nevertheless, using this class of systems, by construction, all the documents and queries are represented using the same set of dimensions. In this article, we introduce the Manifold Clustering (MC) hypothesis which states that, for each query, there exists a query-dependent manifold of the original embedding space where the query and documents relevant to it cluster more effectively. We empirically validate the MC hypothesis showing that it is possible to find a query-dependent linear subspace of the original embedding space where high retrieval effectiveness is achieved. To find such subspaces, we propose the Dimension IMportance Estimators (DIMEs), a class of models that associate an importance score with each dimension of an embedding and can be used to project the dense representations only on the most important dimensions. We first demonstrate the effectiveness of the DIMEs by proposing an oracle DIME which employs annotated documents and induces performance improvements as big as +184% in terms of AP. To demonstrate the practical applicability of the DIMEs beyond the oracle, we also propose a set of DIMEs based on pseudo-relevance and active feedback that induce improvement as big as +49.6% in terms of AP and +55.9% in terms of nDCG@10. The effectiveness of such DIMEs not only empirically supports the MC hypothesis, but illustrates an actual strategy to outperform the state-of-the-art that does not require any form of retraining, fine-tuning or re-indexing and can be efficiently implemented at retrieval time.

Query Performance Prediction (QPP) aims to estimate the effectiveness of a retrieval system for a given query without requiring relevance judgments. While traditionally studied for sparse retrieval, recent advances in neural ranking, dense retrieval, and large language models (LLMs) have prompted a shift towards QPP methods that better reflect modern IR systems. This Special Issue on Query Performance Prediction Towards Novel Information Retrieval Paradigms presents recent advances along two complementary directions. The first focuses on LLM- and representation-based approaches that leverage query variants, semantic interactions, and comparative assessment to improve prediction for neural retrieval models. The second explores new formulations and application settings, including inverse learning, prediction of reliability in retrieval-augmented generation, and the incorporation of multimodal and neurophysiological signals. These works highlight emerging challenges in evaluating QPP in neural and generative settings by demonstrating that QPP is evolving into a broader framework for estimating uncertainty and reliability across complex IR pipelines. We believe that this Special Issue will foster further research towards robust and generalizable QPP methods for next-generation information access systems.

Protecting sensitive information within textual data strongly depends on the context in which the data is presented. However, current privacy-preserving obfuscation mechanisms based on epsilon-Differential Privacy (DP) produce an obfuscated private text, changing the original phrase term-by-term without considering the context in which such a term is placed. This paper introduces DP-COMET, an epsilon-DP obfuscation mechanism that evaluates a text's context before producing its private version. The mechanism defines a representation of the original text that considers the entire context within the text, producing an obfuscated version after adding noise to this representation and depending on the privacy parameter epsilon. We test DP-COMET on different Natural Language Processing (NLP) and Information Retrieval (IR) downstream tasks, and our findings show that our obfuscation mechanism not only achieves comparable performance results to traditional term-by-term mechanisms but also produces obfuscated texts less similar to the originals. To promote the reproducibility of DP-COMET, we make the code publicly available at https://github.com/Kekkodf/DP-COMET.

Large Language Models (LLMs) hugely impacted many research fields, including Information Retrieval (IR), where they are used for many sub-tasks, such as query rewriting and retrieval augmented generation. At the same time, the research community is investigating whether and how to use LLMs to support, or even replace, humans to generate relevance judgments. Indeed, generating relevance judgements automatically - or integrating an LLM in the annotation process - would allow us to improve the number of evaluation collections, also for scenarios where the annotation process is particularly challenging. To validate relevance judgements produced by an LLM they are compared with human-made relevance judgements, measuring the inter-assessor agreement between the human and the LLM.

Conversational Information Access systems have experienced widespread diffusion thanks to the natural and effortless interactions they enable with the user. In particular, they represent an effective interaction interface for conversational search (CS) and conversational recommendation (CR) scenarios. Despite their commonalities, CR and CS systems are often devised, developed, and evaluated as isolated components. Integrating these two elements would allow for handling complex information access scenarios, such as exploring unfamiliar recommended product aspects, enabling richer dialogues, and improving user satisfaction. As of today, the scarce availability of integrated datasets - focused exclusively on either of the tasks - limits the possibilities for evaluating by-design integrated CS and CR systems. To address this gap, we propose CoSRec, the first dataset for joint Conversational Search and Recommendation (CSR) evaluation. The CoSRec test set includes 20 high-quality conversations, with human-made annotations for the quality of conversations, and manually crafted relevance judgments for products and documents. Additionally, we provide supplementary training data comprising partially annotated dialogues and raw conversations to support diverse learning paradigms. CoSRec is the first resource to model CR and CS tasks in a unified framework, enabling the training and evaluation of systems that must shift between answering queries and making suggestions dynamically.

Contextual dense representation models for text marked a shift in text processing, enabling a richer semantic understanding of the text and more effective Information Retrieval. These models project pieces of text into a latent space, describing them in terms of shared latent concepts, which are not explicitly tied to the text's content. Previous work has shown that certain dimensions of such dense text representations can be irrelevant and detrimental to retrieval effectiveness depending on the information need specified in the query. Higher effectiveness can be achieved by performing retrieval within a linear subspace that excludes these dimensions. Dimension IMportance Estimators (DIMEs) are models designed to identify such harmful dimensions, refining the representations of queries and documents to retain only the useful ones. Current DIMEs rely either on pseudo-relevance feedback, which often delivers inconsistent effectiveness, or on explicit relevance feedback, which is challenging to collect. Inspired by counterfactual modelling, we introduce Counterfactual DIMEs (CoDIMEs), designed to leverage noisy implicit feedback to assess the importance of each dimension. The CoDIME framework presented here approximates the relationship between a document's click frequency and its interaction with a given query dimension through a linear model. Empirical evaluations demonstrate that CoDIME outperforms traditional pseudo-relevance feedback-based DIMEs and surpasses other unsupervised counterfactual methods that utilize implicit feedback.

When interacting with an Information Retrieval (IR) system, users might disclose personal information, such as medical details, through their queries. Thus, assessing the level of privacy granted to users when querying an IR system is essential to determine the confidentiality of submitted sensitive data. Query obfuscation protocols have traditionally been employed to obscure a user's real information need when retrieving documents. In these protocols, the query is modified employing ε-Differential Privacy (DP) obfuscation mechanisms, which alter query terms according to a predefined privacy budget ε. While this budget ensures formal mathematical guarantees, it provides only limited guarantees of the privacy experienced by the user and calls for empirical privacy evaluation to be carried out. Such privacy assessments employ lexical and semantic similarity measures between the original and obfuscated queries. In this study, we explore the role of Large Language Models (LLMs) in privacy evaluation, simulating a scenario where users employ such models to determine whether their input has been effectively privatized. Our primary research objective is to determine whether LLMs provide a novel perspective on privacy estimation and if their assessments serve as a proxy for traditional similarity metrics, such as the Jaccard and cosine similarity derived from Transformer-based sentence embeddings. Our findings reveal a positive correlation between LLMs-generated privacy scores and cosine similarity computed using different Transformer architectures. This suggests that LLM assessments act as a proxy for similarity-based measures.

Traditional Information Retrieval (IR) effectiveness metrics assume that a relevant document satisfies the information need as a whole. Nevertheless, if the information need is faceted or contains subtopics, this notion of relevance cannot model documents relevant only to one or a few subtopics. Furthermore, faceted documents in a ranked list may focus on the same subtopics, and their content may overlap while neglecting other subtopics. Hence, a search result, where topranked documents deal with different subtopics should be preferred over a result where documents are thematically limited and provide overlapping information. The Multi-Dimensional Cumulated Utility (MDCU) metric, recently formulated theoretically by Järvelin and Sormunen, extends the evaluation of novelty and diversity by considering content overlapping among documents. While Järvelin and Sormunen described the theory of MDCU and illustrated its application on a toy example, they did not investigate its empirical use. In this paper, we show the practical feasibility and validity of the MDCU by applying it to publicly available TREC test collections. Furthermore, we analyse its relation with the well-established α-nDCG, and finally, we provide a Python implementation of the MDCU, fostering its adoption as an evaluation framework. Our results indicate a positive correlation between α-nDCG and MDCU, suggesting that both measures correctly identify similar trends when evaluating the IR systems. Finally, compared to α-nDCG, MDCU exhibits a stronger statistical power and identifies up to 9 times more statistically significantly different pairs of systems.

Experimental evaluation steers the development of Information Retrieval (IR) systems, and large-scale evaluation campaigns provide the field with a common infrastructure to conduct comparable evaluation exercises. Over the years, tools and platforms have been developed to manage and automate these activities, enhance the reproducibility of conducted experiments and facilitate data sharing. In this context, Evaluation-as-a-Service (EaaS) emerged as an approach to avoid distributing experimental collections, which may contain copyrighted or sensitive data, and instead execute containerised code on that data on remote servers. We propose Kubernetes Infrastructure for Managed Evaluation and Resource Access (KIMERA) as the next step from EaaS into Evaluation-in-the-Cloud (EitC), allowing researchers to directly code and execute their systems through their browsers, requiring only an internet connection. Moreover, recent advancements, such as Large Language Models, or new computing paradigms, such as quantum computers, require external third party services and computational resources. In this respect, KIMERA streamlines and simplifies access to such services on-demand via their APIs. More in detail, KIMERA relies on state-of-the-art containerization and orchestration tools, such as Docker and Kubernetes, to provide a robust, scalable, secure, and fault-tolerant IR evaluation platform. KIMERA monitors and stores all the participants' submissions, accurately keeping track of the resource usage, allowing for evaluating both the efficiency and the effectiveness of the deployed methods. Moreover, all participants can be assigned workspaces sharing the same resources (i.e., CPU and RAM), thus enhancing reproducibility and comparability among systems. Finally, KIMERA has been designed with modularity and extensibility in mind, allowing it to be easily adapted to new use cases and usage scenarios. KIMERA has been developed and adopted in the context of the QuantumCLEF lab, to allow for mixed experiments, comparing approaches running on traditional hardware and on real quantum annealers provided by external companies. KIMERA has also been used as a learning resource to provide Quantum Computing tutorials for IR at major conferences, such as ECIR and SIGIR. The source code of KIMERA is openly available at https://github.com/MjPaxter/KIMERA.

Privacy is critical when dealing with user-generated text, as common in Natural Language Processing (NLP) and Information Retrieval (IR) tasks. Documents, queries, posts, and reviews might pose a risk of inadvertently disclosing sensitive information. Such exposure of private data is a significant threat to user privacy, as it may reveal information that users prefer to keep confidential. The leading framework to protect user privacy when handling textual information is represented by the ε-Differential Privacy (DP). However, the research community lacks a unified framework for comparing different DP mechanisms. This study introduces pyPANTERA, an open-source Python package developed for text obfuscation. The package is designed to incorporate State-of-the-Art DP mechanisms within a unified framework for obfuscating data. pyPANTERA is not only designed as a modular and extensible library for enriching DP techniques, thereby enabling the integration of new DP mechanisms in future research, but also to allow reproducible comparison of the current State-of-the-Art mechanisms. Through extensive evaluation, we demonstrate the effectiveness of pyPANTERA, making it an essential resource for privacy researchers and practitioners. The source code of the library and for the experiments is available at: https://github.com/Kekkodf/pypantera **REMOVE 2nd URL**://github.com/Kekkodf/pypantera.

We examine the context of significance tests in offline retrieval experiments. Our Information Retrieval (IR) community is notable for its experimental rigour: the use of statistical significance is grows across our publications. However, we show that ignoring the context of a test risks Type I errors, leading to potential publication bias. We examine two contexts: multiple testing and the types of the retrieval systems being compared. Our results show that multiple testing corrections are critical for experimental work. In addition, we find that past research on the reliability of test collections maybe flawed owing to the type of systems examined. The latter result has not been shown before. Together our results suggest substantial numbers of Type I errors in offline IR experiments. We detail a methodology to alleviate the errors.

The field of Quantum Computing (QC) has gained significant popularity in recent years, due to its potential to provide benefits in terms of efficiency and effectiveness when employed to solve certain computationally intensive tasks. In both Information Retrieval (IR) and Recommender Systems (RS) we are required to build methods that apply complex processing on large and heterogeneous datasets, it is natural therefore to wonder whether QC could also be applied to boost their performance. The tutorial aims to provide first an introduction to QC for an audience that is not familiar with the technology, then to show how to apply the QC paradigm of Quantum Annealing (QA) to solve practical problems that are currently faced by IR and RS systems. During the tutorial, participants will be provided with the fundamentals required to understand QC and to apply it in practice by using a real D-Wave quantum annealer through APIs.

Recent advances in Information Retrieval have shown the effectiveness of embedding queries and documents in a latent high-dimensional space to compute their similarity. While operating on such high-dimensional spaces is effective, in this paper, we hypothesize that we can improve the retrieval performance by adequately moving to a query-dependent subspace. More in detail, we formulate the Manifold Clustering (MC) Hypothesis: projecting queries and documents onto a subspace of the original representation space can improve retrieval effectiveness. To empirically validate our hypothesis, we define a novel class of Dimension IMportance Estimators (DIME). Such models aim to determine how much each dimension of a high-dimensional representation contributes to the quality of the final ranking and provide an empirical method to select a subset of dimensions where to project the query and the documents. To support our hypothesis, we propose an oracle DIME, capable of effectively selecting dimensions and almost doubling the retrieval performance. To show the practical applicability of our approach, we then propose a set of DIMEs that do not require any oracular piece of information to estimate the importance of dimensions. These estimators allow us to carry out a dimensionality selection that enables performance improvements of up to +11.5% (moving from 0.675 to 0.752 nDCG@10) compared to the baseline methods using all dimensions. Finally, we show that, with simple and realistic active feedback, such as the user's interaction with a single relevant document, we can design a highly effective DIME, allowing us to outperform the baseline by up to +0.224 nDCG@10 points (+58.6%, moving from 0.384 to 0.608).

The present study leverages a recent opportunity we had to create a new English web search test collection for the NTCIR-16 We Want Web (WWW-4) task, which concluded in June 2022. More specifically, through the test collection construction effort, we examined two factors that may affect the relevance assessments of depth- k pools, which in turn may affect the relative evaluation of different IR systems. The first factor is the document ordering strategy for the assessors, namely, prioritisation (PRI) and randomisation (RND). PRI is a method that has been used in NTCIR tasks for over a decade; it ranks the pooled documents by a kind of pseudorelevance for the assessors. The second factor is assessor type, i.e., Gold or Bronze. Gold assessors are the topic creators and therefore they “know” which documents are (highly) relevant and which are not; Bronze assessors are not the topic creators and may lack sufficient knowledge about the topics. We believe that our study is unique in that the authors of this article served as the Gold assessors when creating the WWW-4 test collection, which enabled us to closely examine why Bronze assessments differ from the Gold ones. Our research questions examine assessor efficiency ( RQ1 ), inter-assessor agreement ( RQ2 ), system ranking similarity with different qrels files ( RQ3 ), system ranking robustness to the choice of test topics ( RQ4 ), and the reasons why Bronze assessors tend to be more liberal than Gold assessors ( RQ5 ). The most remarkable of our results are as follows: First, in the comparisons for RQ1 through RQ4 , it turned out that what may matter more than the document ordering strategy (PRI vs. RND) and the assessor type (Gold vs. Bronze) is how well-motivated and/or well-trained the Bronze assessors are. Second, regarding RQ5 , of the documents originally judged nonrelevant by the Gold assessors contrary to the Bronze assessors in our experiments, almost one half were truly relevant according to the Gold assessors’ own reconsiderations. This result suggests that even Gold assessors are far from perfect; budget permitting, it may be beneficial to hire highly motivated Bronze assessors in addition to Gold assessors so they can complement each other.

Creating test collections for offline retrieval evaluation requires human effort to judge documents' relevance. This expensive activity motivated much work in developing methods for constructing benchmarks with fewer assessment costs. In this respect, adjudication methods actively decide both which documents and the order in which experts review them, in order to better exploit the assessment budget or to lower it. Researchers evaluate the quality of those methods by measuring the correlation between the known gold ranking of systems under the full collection and the observed ranking of systems under the lower-cost one. This traditional analysis ignores whether and how the low-cost judgements impact on the statistically significant differences among systems with respect to the full collection. We fill this void by proposing a novel methodology to evaluate how the low-cost adjudication methods preserve the pairwise significant differences between systems as the full collection. In other terms, while traditional approaches look for stability in answering the question "is system A better than system B?", our proposed approach looks for stability in answering the question "is system A significantly better than system B?", which is the ultimate questions researchers need to answer to guarantee the generalisability of their results. Among other results, we found that the best methods in terms of ranking of systems correlation do not always match those preserving statistical significance.

The Conversational Search (CS) paradigm allows for an intuitive interaction between the user and the system through natural language sentences and it is increasingly being adopted in various scenarios. However, its widespread experimentation has led to the birth of a multitude of conversational search systems with custom implementations and variants of information retrieval models. This exacerbates the reproducibility crisis already observed in several research areas, including Information Retrieval (IR). To address this issue, we propose DECAF: a modular and extensible conversational search framework designed for fast prototyping and development of conversational agents. Our framework integrates all the components that characterize a modern conversational search system and allows for the seamless integration of Machine Learning (ML) and Large Language Models (LLMs)-based techniques. Furthermore, thanks to its uniform interface, DECAF allows for experiments characterized by a high degree of reproducibility. DECAF contains several state-of-the-art components including query rewriting, search functions under BoW and dense paradigms, and re-ranking functions. Our framework is tested on two well-known conversational collections: TREC CAsT 2019 and TREC CAsT 2020 and the results can be used by future practitioners as baselines. Our contributions include the identification of a series of state-of-the-art components for the conversational search task and the definition of a modular framework for its implementation.

Thanks to recent advances in IR and NLP, the way users interact with search engines is evolving rapidly, with multi-turn conversations replacing traditional one-shot textual queries. Given its interactive nature, Conversational Search (CS) is one of the scenarios that can benefit the most from Query Performance Prediction (QPP) techniques. QPP for the CS domain is a relatively new field and lacks proper framing. In this study, we address this gap by proposing a framework for the application of QPP in the CS domain and use it to evaluate the performance of predictors. We characterize what it means to predict the performance in the CS scenario, where information needs are not independent queries but a series of closely related utterances. We identify three main ways to use QPP models in the CS domain: as a diagnostic tool, as a way to adjust the system's behaviour during a conversation, or as a way to predict the system's performance on the next utterance. Due to the lack of established evaluation procedures for QPP in the CS domain, we propose a protocol to evaluate QPPs for each of the use cases. Additionally, we introduce a set of spatial-based QPP models designed to work the best in the conversational search domain, where dense neural retrieval models are the most common approaches and query cutoffs are typically small. We show how the proposed QPP approaches improve significantly the predictive performance over the state-of-the-art in different scenarios and collections.

Science is facing a so-called reproducibility crisis, where researchers struggle to repeat experiments and to get the same or comparable results. This represents a fundamental problem in any scientific discipline because reproducibility lies at the very basis of the scientific method. A central methodological question is how to measure reproducibility and interpret different measures. In Information Retrieval (IR), current practices to measure reproducibility rely mainly on comparing averaged scores. If the reproduced score is close enough to the original one, the reproducibility experiment is deemed successful, although the identical scores can still rely on entirely different result lists. Therefore, this paper focuses on measures to quantify reproducibility in IR and their behavior. We present a critical analysis of IR reproducibility measures by synthetically generating runs in a controlled experimental setting, which allows us to control the amount of reproducibility error. These synthetic runs are generated by a deterioration algorithm based on swaps and replacements of documents in ranked lists. We investigate the behavior of different reproducibility measures with these synthetic runs in three different scenarios. Moreover, we propose a normalized version of Root Mean Square Error (RMSE) to quantify reproducibility better. Experimental results show that a single score is not enough to decide whether an experiment is successfully reproduced because such a score depends on the type of effectiveness measure and the performance of the original run. This study highlights how challenging it can be to reproduce experimental results and quantify the amount of reproducibility.

Being able to compare Information Retrieval(IR) systems correctly is pivotal to improving their quality. Among the most popular tools for statistical significance testing, we list t-test and ANOVA that belong to the linear models family. Therefore, given the relevance of linear models for IR evaluation, a great effort has been devoted to studying how to improve them to better compare IR systems.

Feature selection is a common step in many ranking, classification, or prediction tasks and serves many purposes. By removing redundant or noisy features, the accuracy of ranking or classification can be improved and the computational cost of the subsequent learning steps can be reduced. However, feature selection can be itself a computationally expensive process. While for decades confined to theoretical algorithmic papers, quantum computing is now becoming a viable tool to tackle realistic problems, in particular special-purpose solvers based on the Quantum Annealing paradigm. This paper aims to explore the feasibility of using currently available quantum computing architectures to solve some quadratic feature selection algorithms for both ranking and classification.

We examine three statistical significance tests -- a recently proposed ANOVA model and two baseline tests -- using a suite of measures to determine which is better suited for offline evaluation. We apply our analysis to both the runs of a whole TREC track and also to the runs submitted by six participant groups. The former reveals test behavior in the heterogeneous settings of a large-scale offline evaluation initiative; the latter, almost overlooked in past work (to the best of our knowledge), reveals what happens in the much more restricted case of variants of a single system, i.e. the typical context in which companies and research groups operate. We find the ANOVA test strikingly consistent in large-scale settings, but worryingly inconsistent in some participant experiments. Of greater concern, the participant only experiments show one of our baseline tests (a test widely used in research) can produce a substantial number of inconsistent results. We discuss the implications of this inconsistency for possible publication bias.

Abstract Query performance prediction (QPP) has been studied extensively in the IR community over the last two decades. A by-product of this research is a methodology to evaluate the effectiveness of QPP techniques. In this paper, we re-examine the existing evaluation methodology commonly used for QPP, and propose a new approach. Our key idea is to model QPP performance as a distribution instead of relying on point estimates. To obtain such distribution, we exploit the scaled Absolute Ranking Error (sARE) measure, and its mean the scaled Mean Absolute Ranking Error (sMARE). Our work demonstrates important statistical implications, and overcomes key limitations imposed by the currently used correlation-based point-estimate evaluation approaches. We also explore the potential benefits of using multiple query formulations and ANalysis Of VAriance (ANOVA) modeling in order to measure interactions between multiple factors. The resulting statistical analysis combined with a novel evaluation framework demonstrates the merits of modeling QPP performance as distributions, and enables detailed statistical ANOVA models for comparative analyses to be created.

Several recent studies have explored the interaction effects between topics, systems, corpora, and components when measuring retrieval effectiveness. However, all of these previous studies assume that a topic or information need is represented by a single query. In reality, users routinely reformulate queries to satisfy an information need. In recent years, there has been renewed interest in the notion of “query variations” which are essentially multiple user formulations for an information need. Like many retrieval models, some queries are highly effective while others are not. This is often an artifact of the collection being searched which might be more or less sensitive to word choice. Users rarely have perfect knowledge about the underlying collection, and so finding queries that work is often a trial-and-error process. In this work, we explore the fundamental problem of system interaction effects between collections, ranking models, and queries. To answer this important question, we formalize the analysis using ANalysis Of VAriance (ANOVA) models to measure multiple components effects across collections and topics by nesting multiple query variations within each topic. Our findings show that query formulations have a comparable effect size of the topic factor itself, which is known to be the factor with the greatest effect size in prior ANOVA studies. Both topic and formulation have a substantially larger effect size than any other factor, including the ranking algorithms and, surprisingly, even query expansion. This finding reinforces the importance of further research in understanding the role of query rewriting in IR related tasks.

Conversational agents are drawing a lot of attention in the information retrieval (IR) community also thanks to the advancements in language understanding enabled by large contextualized language models. IR researchers have long ago recognized the importance o fa sound evaluation of new approaches. Yet, the development of evaluation techniques for conversational search is still an underlooked problem. Currently, most evaluation approaches rely on procedures directly drawn from ad-hoc search evaluation, treating utterances in a conversation as independent events, as if they were just separate topics, instead of accounting for the conversation context. We overcome this issue by proposing a framework for defining evaluation measures that are aware of the conversation context and the utterance semantic dependencies. In particular, we model the conversations as Direct Acyclic Graphs (DAG), where self-explanatory utterances are root nodes, while anaphoric utterances are linked to sentences that contain their missing semantic information. Then,we propose a family of hierarchical dependence-aware aggregations of the evaluation metrics driven by the conversational graph. In our experiments, we show that utterances from the same conversation are 20% more correlated than utterances from different conversations. Thanks to the proposed framework, we are able to include such correlation in our aggregations, and be more accurate when determining which pairs of conversational systems are deemed significantly different.

Evaluation of the quality of data integration processes is usually performed via manual onerous data inspections. This task is particularly heavy in real business scenarios, where the large amount of data makes checking all the tuples infeasible and the frequent updates, i.e. changes in the sources and/or new sources, impose to repeat the evaluation over and over. Our idea is to address this issue by providing the experts with an unsupervised measure, based on word frequencies, which quantifies how much a dataset is representative of another dataset, giving an indication of how good is the integration process and whether deviations are happening and a manual inspection is needed. We also conducted some preliminary experiments, using shared datasets, that show the effectiveness of the proposed measures in typical data integration scenarios.

Replicability and reproducibility of experimental results are primary concerns in all the areas of science and IR is not an exception. Besides the problem of moving the field towards more reproducible experimental practices and protocols, we also face a severe methodological issue: we do not have any means to assess when reproduced is reproduced. Moreover, we lack any reproducibility-oriented dataset, which would allow us to develop such methods.

We improve the measurement accuracy of retrieval system performance by better modeling the noise present in test collection scores. Our technique draws its inspiration from two approaches: one, which exploits the variable measurement accuracy of topics; the other, which randomly splits document collections into shards. We describe and theoretically analyze an ANOVA model able to capture the effects of topics, systems, and document shards as well as their interactions. Using multiple TREC collections, we empirically confirm theoretical results in terms of improved estimation accuracy and robustness of found significant differences. The improvements compared to widely used test collection measurement techniques are substantial. We speculate that our technique works because we do not assume that the topics of a test collection measure performance equally.

The importance of repeatability, replicability, and reproducibility is broadly recognized in the computational sciences, both in supporting desirable scientific methodology as well as sustaining empirical progress. This workshop tackles the replicability challenge for ad hoc document retrieval, via a common Docker interface specification to support images that capture systems performing ad hoc retrieval experiments on standard test collections.

Interval scales are assumed by several basic descriptive statistics, such as mean and variance, and by many statistical significance tests which are daily used in IR to compare systems. Unfortunately, so far, there has not been any systematic and formal study to discover the actual scale properties of IR measures. Therefore, in this paper, we develop a theory ofInformation Retrieval (IR)evaluation measures, based on the representational theory of measurements, to determine whether and when IR measures are interval scales. We found that common set-based retrieval measures—namely Precision, Recall, and F-measure—always are interval scales in the case of binary relevance while this happens also in the case of multi-graded relevance only when the relevance degrees themselves are on a ratio scale and we define a specific partial order among systems. In the case of rank-based retrieval measures—namely AP, gRBP, DCG, and ERR—only gRPB is an interval scale when we choose a specific value of the parameter$p$and define a specific total order among systems while all the other IR measures are not interval scales. Besides the formal framework itself and the proof of the scale properties of several commonly used IR measures, the paper also defines some brand new set-based and rank-based IR evaluation measures which ensure to be interval scales.

Despite the bulk of research studying how to more accurately compare the performance of IR systems, less attention is devoted to better understanding the different factors that play a role in such performance and how they interact. This is the case of shards, i.e., partitioning a document collection into sub-parts, which are used for many different purposes, ranging from efficiency to selective search or making test collection evaluation more accurate. In all these cases, there is empirical knowledge supporting the importance of shards, but we lack actual models that allow us to measure the impact of shards on system performance and how they interact with topics and systems. We use the general linear mixed model framework and present a model that encompasses the experimental factors of system, topic, shard, and their interaction effects. This detailed model allows us to more accurately estimate differences between the effect of various factors. We study shards created by a range of methods used in prior work and better explain observations noted in prior work in a principled setting and offer new insights. Notably, we discover that the topic*shard interaction effect, in particular, is a large effect almost globally across all datasets, an observation that, to our knowledge, has not been measured before.

In this paper we explore the use of Continuation Methods and Curriculum Learning techniques in the area of Learning to Rank. The basic idea is to design the training process as a learning path across increasingly complex training instances and objective functions. We propose to instantiate continuation methods in Learning to Rank by changing the IR measure to optimize during training, and we present two different curriculum learning strategies to identify easy training examples. Experimental results show that simple continuation methods are more promising than curriculum learning ones since they allow for slightly improving the performance of state-of-the-art λ-MART models and provide a faster convergence speed.

Information retrieval (IR) systems are the prominent means for searching and accessing huge amounts of unstructured information on the web and elsewhere. They are complex systems, constituted by many different components interacting together, and evaluation is crucial to both tune and improve them. Nevertheless, in the current evaluation methodology, there is still no way to determine how much each component contributes to the overall performances and how the components interact together. This hampers the possibility of a deep understanding of IR system behavior and, in turn, prevents us from designing ahead which components are best suited to work together for a specific search task. In this paper, we move the evaluation methodology one step forward by overcoming these barriers and beginning to devise an “anatomy” of IR systems and their internals. In particular, we propose a methodology based on the General Linear Mixed Model (GLMM) and analysis of variance (ANOVA) to develop statistical models able to isolate system variance and component effects as well as their interaction, by relying on a grid of points (GoP) containing all the combinations of the analyzed components. We apply the proposed methodology to the analysis of two relevant search tasks—news search and web search—by using standard TREC collections. We analyze the basic set of components typically part of an IR system, namely, stop lists, stemmers, and n‐grams, and IR models. In this way, we derive insights about English text retrieval.

Ranking query results effectively by considering user past behaviour and preferences is a primary concern for IR researchers both in academia and industry. In this context, LtR is widely believed to be the most effective solution to design ranking models that account for user-interaction features that have proved to remarkably impact on IR effectiveness. In this paper, we explore the possibility of integrating the user dynamic directly into the LtR algorithms. Specifically, we model with Markov chains the behaviour of users in scanning a ranked result list and we modify Lambdamart, a state-of-the-art LtR algorithm, to exploit a new discount loss function calibrated on the proposed Markovian model of user dynamic. We evaluate the performance of the proposed approach on publicly available LtR datasets, finding that the improvements measured over the standard algorithm are statistically significant.

Understanding the factors comprising IR system effectiveness is of primary importance to compare different IR systems. Effectiveness is traditionally broken down, using ANOVA, into a topic and a system effect but this leaves out a key component of our evaluation paradigm: the collections of documents. We break down effectiveness into topic, system and sub-corpus effects and compare it to the traditional break down, considering what happens when different evaluation measures come into play. We found that sub-corpora are a significant effect. The consideration of which allows us to be more accurate in estimating what systems are significantly different. We also found that the sub-corpora affect different evaluation measures in different ways and this may impact on what systems are considered significantly different.

We propose theAssessor-driven Weighted Averages for Retrieval Evaluation (AWARE)probabilistic framework, a novel methodology for dealing with multiple crowd assessors that may be contradictory and/or noisy. By modeling relevance judgements and crowd assessors as sources of uncertainty, AWARE takes the expectation of a generic performance measure, like Average Precision, composed with these random variables. In this way, it approaches the problem of aggregating different crowd assessors from a new perspective, that is, directly combining the performance measures computed on the ground truth generated by the crowd assessors instead of adopting some classification technique to merge the labels produced by them. We propose several unsupervised estimators that instantiate the AWARE framework and we compare them with state-of-the-art approaches, that is,Majoriity Vote and Expectation Maximization, on TREC collections. We found that AWARE approaches improve in terms of their capability of correctly ranking systems and predicting their actual performance scores.

Information Retrieval (IR)is well-known for the great number of adopted evaluation measures, with new ones popping up more and more frequently. In this context, correlation analysis is the tool used to study the evaluation measures and to let us understand if two measures rank systems similarly, if they grasp different aspects of system performances or actually reflect different user models, if a new measure is well motivated or not. To this end, the two most commonly used correlation coefficients are the Kendall’s τ correlation and the AP correlation τAP. The goal of the article is to investigate the properties of the tool, that is, correlation analysis, we use to study evaluation measures. In particular, we investigate three research questions about these two correlation coefficients: (i) what is the effect of the number of systems and topics? (ii) what is the effect of removing low-performing systems? (iii) what is the effect of the experimental collections? To answer these research questions, we propose a methodology based onGeneral Linear Mixed Model (GLMM)andANalysis Of VAriance (ANOVA)to isolate the effects of the number of topics, number of systems, and experimental collections and to let us observe expected correlation values, net from these effects, which are stable and reliable. We learned that the effect of the number of topics is more prominent than the effect of the number of systems. Even if it produces different absolute values, the effect of removing low-performing systems does not seem to provide information substantially different from not removing them, especially when comparing a whole set of evaluation measures. Finally, we found out that both document corpora and topic sets affect the correlation among evaluation measures, the effect of the latter being more prominent. Moreover, there is a substantial interaction between evaluation measures, corpora and topic sets, meaning that the correlation between different evaluation measures can be substantially increased or decreased depending on the different corpora and topics at hand.

The purpose of this half-day workshop is to bring together academic and industry interactive information retrieval (IIR) researchers with an interest in evaluation methodologies. The workshop articulates contemporary challenges in the investigation of IIR and invites user- and system-oriented researchers to work collaboratively to address these challenges by combining user- and system-centered methodologies in meaningful ways. We anticipate that this workshop will initiate productive knowledge exchange and partnerships that can respond to the increasing user, task, system, and contextual complexity of the IIR field.

We present the innovative visual analytics approach of the VATE system, which eases and makes more effective the experimental evaluation process by introducing the what-if analysis. The what-if analysis is aimed at estimating the possible effects of a modification to an IR system to select the most promising fixes before implementing them, thus saving a considerable amount of effort. VATE builds on an analytical framework which models the behavior of the systems in order to make estimations, and integrates this analytical framework into a visual part which, via proper interaction and animations, receives input and provides feedback to the user.

Topic variance has a greater effect on performances than system variance but it cannot be controlled by system developers who can only try to cope with it. On the other hand, system variance is important on its own, since it is what system developers may affect directly by changing system components and it determines the differences among systems. In this paper, we face the problem of studying system variance in order to better understand how much system components contribute to overall performances. To this end, we propose a methodology based on General Linear Mixed Model (GLMM) to develop statistical models able to isolate system variance, component effects as well as their interaction by relying on a Grid of Points (GoP) containing all the combinations of analysed components. We apply the proposed methodology to the analysis of TREC Ad-hoc data in order to show how it works and discuss some interesting outcomes of this new kind of analysis. Finally, we extend the analysis to different evaluation measures, showing how they impact on the sources of variance.

We present a novel measure for ranking evaluation, called Twist (τ). It is a measure for informational intents, which handles both binary and graded relevance. τ stems from the observation that searching is currently a that searching is currently taken for granted and it is natural for users to assume that search engines are available and work well. As a consequence, users may assume the utility they have in finding relevant documents, which is the focus of traditional measures, as granted. On the contrary, they may feel uneasy when the system returns nonrelevant documents because they are then forced to do additional work to get the desired information, and this causes avoidable effort. The latter is the focus of τ, which evaluates the effectiveness of a system from the point of view of the effort required to the users to retrieve the desired information. We provide a formal definition of τ, a demonstration of its properties, and introduce the notion of effort/gain plots, which complement traditional utility‐based measures. By means of an extensive experimental evaluation, τ is shown to grasp different aspects of system performances, to not require extensive and costly assessments, and to be a robust tool for detecting differences between systems.

We propose a family of new evaluation measures, called Markov Precision (MP), which exploits continuous-time and discrete-time Markov chains in order to inject user models into precision. Continuous-time MP behaves like time-calibrated measures, bringing the time spent by the user into the evaluation of a system; discrete-time MP behaves like traditional evaluation measures. Being part of the same Markovian framework, the time-based and rank-based versions of MP produce values that are directly comparable.

This paper introduces the main characteristics of the digital cultural collections that constitute the use cases presently in use in the CULTURA environment. A section on related work follows giving an account on efforts on the management of digital annotations that are pertinent and that have been considered. Afterwards the innovative annotation features of the CULTURA portal for digital humanities are described; those features are aimed at improving the interaction of non-specialist users and general public with digital cultural heritage content. The annotation functions consist of two modules: the FAST annotation service as back-end and the CAT Web front-end integrated in the CULTURA portal. The annotation features have been, and are being, tested with different types of users and useful feedback is being collated, with the overall aim of generalising the approach to diverse document collections and not only the area of cultural heritage.

The workshop focuses on the three areas of interest to CIKM to discuss how to envisage and design evaluation infrastructures able to store, manage, and make accessible the scientific data and knowledge of interest for advancing the evaluation of information retrieval and access tools.

The paper addresses the problem of representing, managing and exchanging hierarchically structured data in the context of Digital Library (DL) systems in order to enhance the access and exchange DL resources on the Web. We propose the NEsted SeTs for Object hieRarchies (NESTOR) framework, which relies on two set data models — the “Nested Set Model (NS-M)” and the “Inverse Nested Set Model (INS-M)” — to enable the representation of hierarchical data structures by means of a proper organization of nested sets. In particular, we show how NESTOR can be effectively exploited to enhance Open Archives Initiative Protocol for Metadata Harvesting (OAI-PMH) for better access and exchange of hierarchical resources on the Web.

This article is a study of the themes and issues concerning the annotation of digital contents, such as textual documents, images, and multimedia documents in general. These digital contents are automatically managed by different kinds of digital library management systems and more generally by different kinds of information management systems. Even though this topic has already been partially studied by other researchers, the previous research work on annotations has left many open issues. These issues concern the lack of clarity about what an annotation is, what its features are, and how it is used. These issues are mainly due to the fact that models and systems for annotations have only been developed for specific purposes. As a result, there is only a fragmentary picture of the annotation and its management, and this is tied to specific contexts of use and lacks-general validity. The aim of the article is to provide a unified and integrated picture of the annotation, ranging from defining what an annotation is to providing a formal model. The key ideas of the model are: the distinction between the meaning and the sign of the annotation, which represent the semantics and the materialization of an annotation, respectively; the clear formalization of the temporal dimension involved with annotations; and the introduction of a distributed hypertext between digital contents and annotations. Therefore, the proposed formal model captures both syntactic and semantic aspects of the annotations. Furthermore, it is built on previously existing models and may be seen as an extension of them.