1,721,053 research outputs found
Self Contrastive Learning for Session-Based Recommendation
Get PDFSession-based recommendation, which aims to predict the next item of users’ interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item representations. However, these contrastive objectives: (1) serve a similar role as the cross-entropy loss while ignoring the item representation space optimisation; and (2) commonly require complicated modelling, including complex positive/negative sample constructions and extra data augmentation. In this work, we introduce Self-Contrastive Learning (SCL), which simplifies the application of CL and enhances the performance of state-of-the-art CL-based recommendation techniques. Specifically, SCL is formulated as an objective function that directly promotes a uniform distribution among item representations and efficiently replaces all the existing contrastive objective components of state-of-the-art models. Unlike previous works, SCL eliminates the need for any positive/negative sample construction or data augmentation, leading to enhanced interpretability of the item representation space and facilitating its extensibility to existing recommender systems. Through experiments on three benchmarks, we demonstrate that SCL consistently improves the performance of state-of-the-art models with statistical significance. Notably, our experiments show that SCL improves the performance of two best-performing models by 8.2% and 9.5% in P@10 (Precision) and 9.9% and 11.2% in MRR@10 (Mean Reciprocal Rank) on average across different benchmarks. Additionally, our analysis elucidates the improvement in terms of alignment and uniformity of representations, as well as the effectiveness of SCL with a low computational cost. Code is available at https://github.com/ZhengxiangShi/SelfContrastiveLearningRecSys
Evaluation metrics for measuring bias in search engine results
Get PDFSearch engines decide what we see for a given search query. Since many people are exposed to information through search engines, it is fair to expect that search engines are neutral. However, search engine results do not necessarily cover all the viewpoints of a search query topic, and they can be biased towards a specific view since search engine results are returned based on relevance, which is calculated using many features and sophisticated algorithms where search neutrality is not necessarily the focal point. Therefore, it is important to evaluate the search engine results with respect to bias. In this work we propose novel web search bias evaluation measures which take into account the rank and relevance. We also propose a framework to evaluate web search bias using the proposed measures and test our framework on two popular search engines based on 57 controversial query topics such as abortion, medical marijuana, and gay marriage. We measure the stance bias (in support or against), as well as the ideological bias (conservative or liberal). We observe that the stance does not necessarily correlate with the ideological leaning, e.g. a positive stance on abortion indicates a liberal leaning but a positive stance on Cuba embargo indicates a conservative leaning. Our experiments show that neither of the search engines suffers from stance bias. However, both search engines suffer from ideological bias, both favouring one ideological leaning to the other, which is more significant from the perspective of polarisation in our society
Matching legacy estimation of soil organic carbon changes from non-paired data with measured values in paired soil samples after two decades: a case study
No full textLegacy data are frequently unique sources of data for the estimation of past soil properties. With the rising concerns about greenhouse gases (GHG) emission and soil degradation due to intensive agriculture and climate change effects, soil organic carbon (SOC) concentration might change heavily over time. When SOC changes is estimated with legacy data, the use of soil samples collected in different plots (i.e., non-aligned data) may lead to biased results. The sampling schemes adopted to capture SOC variation usually involve the resampling of the original sample using a so called paired-site approach. In the present work, a regional (Sicily, south of Italy) soil database, consisting of N=302 georeferenced soil samples from arable land collected in 1993 [1], was used to select coinciding sites to test a former temporal variation (1993-2008) obtained by a comparison of models built with data sampled in non-coinciding locations [2]. A specific sampling strategy was developed to spot SOC concentration changes from 1994 to 2017 in the same plots at the 0-30 cm soil depth and tested. To spot SOC changes the minimum number of samples needed to have a reliable estimate of SOC variation after 23 years has been estimated. By applying an effect size based methodology, 30 out of 302 sites were resampled in 2017 to achieve a power of 80%, and an a=0.05. After the collection of the 30 samples, SOC concentration in the newly collected samples was determined in lab using the same method A Wilcoxon test applied to the variation of SOC from 1994 to 2017 suggested that there was not a statistical difference in SOC concentration after 23 years (Z = -0.556; 2-tailed asymptotic significance = 0.578). In particular, only 40% of resampled sites showed a higher (not always significant) SOC concentration than in 2017. This finding contrasts with a previous SOC concentration increase that was found in 2008 (75.8% increase when estimated as differences of 2 models built with non-aligned data) [2], when compared to 1994 observed data (Z = -9.119; 2-tailed asymptotic significance < 0.001). Such a result implies that the use of legacy data to estimate SOC concentration changes need soil resampling in the same locations to overcome the stochastic model errors. Further experiment is needed to identify the percentage of the sites to resample in order to align two legacy datasets in the same area
Preface: The First Workshop on User Modelling in Conversational Information Retrieval (UM-CIR)
Get PDF
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
On Biases in Information retrieval models and evaluation
Get PDFDer Einzug der modernen Informationstechnologie in unsere Gesellschaft führte in den letzten fünfzig Jahren zu einer rasant wachsenden Menge von digitalen Inhalten. Während das Informationsangebot stetig steigt, bleiben unsere Fähigkeiten zur Informationsverarbeitung unverändert. Aufgrund dieser Überladung mit Informationen kommt dem Information Retrieval (IR) die wichtige Rolle zu, Systeme zu entwickeln, die relevante Informationen von irrelevanten trennen können. Diese Trennung ist allerdings auf Grund der Komplexität des Verstehens was relevant ist und was nicht, eine schwierige Aufgabe. Um diese Komplexität zu bewältigen, wurde im IR ein empirischer Ansatz gewählt, der zur Entwicklung praktikabler Retrieval-Modelle geführt hat, die einen systematischen Fehler bzw. eine Neigung (Bias) in Richtung relevanter Information aufweisen. Neben diesem Bias treten allerdings auch andere Verzerrungen auf, die problematisch für den Retrieval-Vorgang sind. In dieser Arbeit werden diese problematischen Bias durch die Betrachtung von Retrieval-Systemen als Informationsfilter bzw. Sampling-Prozesse systematisch untersucht. Es werden Bias erforscht die üblicherweise in zwei Bereichen des IR auftreten: Retrieval-Modelle und Retrieval-Evaluierung. Zunächst wird das Retrieval-Bias von probabilistischen IR-Modellen analysiert und neue Dokument-Prioren entwickelt um die Retrieval-Leistung zu steigern. Im Anschluss wird das Zugänglichkeits-Bias von Retrieval-Modellen erörtert. Für boolesche Retrieval-Modelle wird ein eigens entwickeltes mathematisches Framework beschrieben. Hinsichtlich des Bias für Retrieval-Evaluierung werden Testdatensätze, welche mittels Pooling-Methode erstellt wurden und somit ein charakteristisches Bias enthalten, analysiert. Um die Zuverlässigkeit der Evaluierung zu verbessern, werden neue Pooling-Strategien beschrieben. Diese Strategien reduzieren das Bias bereits während der Erstellung eines Testdatensatzes. Schließlich wird für die Maßzahlen Precisionund Recall-at-Cutoff (P@n und R@n) ein neuer Pool-Bias-Schätzer entwickelt, welcher das Bias während der Systemevaluierung reduziert. Um die vorgeschlagenen Methoden dieser Arbeit zu evaluieren, wurden 15 Testdatensätze, vier IR-Metriken und drei Bias-Messverfahren herangezogen. Durch Experimente werden folgende Erkenntnisse gewonnen: durch das Verwenden von Dokument-Prioren basierend auf “Verboseness” wird die Retrieval-Genauigkeit von probabilistischen IR-Modellen gesteigert; das Zugänglichkeits-Bias von booleschen IR-Modellen verschlechtert sich für konjunktive Anfragen mit steigender Länge der Anfragen (für disjunktive Anfragen kann eine leichte Verbesserung festgestellt werden); das Testdatensatz-Bias kann bei der Erstellung des Testdatensatzes durch Pooling-Strategien, welche aus dem Bereich des Reinforcement Learning entlehnt sind (“Multi-Armed Bandit Problem”), verkleinert werden; und das Testdatensatz-Bias kann in der Evaluierung durch die Analyse der Pool-Beteiligung in den einzelnen Durchläufen reduziert werden. Speziell für den letzten Punkt wird gezeigt, dass das Bias für P@n durch die Quantifizierung des neuen Systems gegen die gepoolten Durchläufe und für R@n durch die Auslassung einzelner gepoolter Durchläufe reduziert wird. Diese Arbeit leistet einen wichtigen Beitrag zum Gebiet des IR, indem ein besseres Verständnis von Relevanz durch die Betrachtung von Bias in Retrieval-Modellen und Retrieval-Evaluierung erreicht wird. Die Identifizierung dieser Bias und deren Nutzung bzw. Reduktion führt zur Entwicklung von performanteren IR-Modellen und zu einer Verbesserung der derzeitigen Vorgehensweise hinsichtlich IR-Evaluierung.The advent of the modern information technology has benefited society as the digitisation of content increased over the last half-century. While the processing capability of our species has remained unchanged, the information available to us has been notably increasing. In this overload of information, Information Retrieval (IR) has been playing a prominent role by developing systems capable of separating relevant information from the rest. This separation, however, is a difficult task rooted in the complexity of understanding of what is and what is not relevant. To manage this complexity, IR has developed a strong empirical nature, which has led to the development of grounded retrieval models, resulting in the development of retrieval systems empirically designed to be biased towards relevant information. However, other biases have been observed, which counteract retrieval performance. In this thesis, the reduction of retrieval systems to filters of information, or sampling processes, has allowed us to systematically investigate these biases. We study biases manifesting in two aspects of IR research: retrieval models and retrieval evaluation. We start by identifying retrieval biases in probabilistic IR models and then develop new document priors to improve retrieval performance. Next, we discuss the accessibility bias of retrieval models, and for Boolean retrieval models we develop a mathematical framework of retrievability. For retrieval evaluation biases, we study how test collections are built using the pooling method and how this method introduces bias. Then, to improve the reliability of the evaluation, we first develop new pooling strategies to mitigate this bias at test collection build time and then, for two IR evaluation measures, Precision and Recall at cut-off (P@n and R@n), we develop new pool bias estimators to mitigate it at evaluation time. Through a large scale experimentation involving up to 15 test collections, four IR evaluation measures and three bias measures, we demonstrate that including document priors based on verboseness improves the performance of probabilistic retrieval models; that the accessibility bias of Boolean retrieval models quickly worsens for conjunctive queries with the increase of the query length (while slightly improving for disjunctive queries); that the test collection bias can be lowered at test collection build time by pooling strategies inspired by a well-known problem in reinforcement learning, the multi-armed bandit problem; and that this bias can also be improved at evaluation time by analysing the runs participating in the pool. For this last point in particular, we show that for P@n, bias reduction is done by quantifying the potential of the new system against the pooled runs, and for R@n, this is done instead by simulating the absence of a pooled run from the set of pooled runs. This thesis contributes to the IR field by giving a better understanding of relevance through the lens of biases in retrieval models and retrieval evaluation. The identification of these biases, and their exploitation or mitigation, leads to the development of better performing IR models and the improvement of the current IR evaluation practice
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
