144 results on '"de Rijke, Maarten"'
Search Results
2. Listwise Generative Retrieval Models via a Sequential Learning Process.
- Author
-
Tang, Yubao, Zhang, Ruqing, Guo, Jiafeng, de Rijke, Maarten, Chen, Wei, and Cheng, Xueqi
- Abstract
The article focuses on improving generative retrieval (GR) models by introducing a listwise approach that optimizes relevance at the document list level, unlike existing models that use pointwise approaches. It mentions by treating the generation of a ranked document list as a sequence learning process, the proposed method maximizes the generation likelihood of each document given the preceding documents in the list, addressing the sub-optimality of pointwise approaches.
- Published
- 2024
- Full Text
- View/download PDF
3. Few-shot Learning for Heterogeneous Information Networks.
- Author
-
Fang, Yang, Zhao, Xiang, Xiao, Weidong, and de Rijke, Maarten
- Abstract
The article introduces a dual meta-learning (DML) technique to enhance semi-supervised text classification, improving both teacher and student classifiers iteratively. Topics include the challenge of noisy pseudo-labels in semi-supervised text classification, the proposed meta-learning methods for noise correction and pseudo supervision, and the experimental validation demonstrating the effectiveness of the DML framework.
- Published
- 2024
- Full Text
- View/download PDF
4. Domain Generalization in Time Series Forecasting.
- Author
-
Deng, Songgaojun, Sprangers, Olivier, Li, Ming, Schelter, Sebastian, and de Rijke, Maarten
- Subjects
GENERALIZATION ,FORECASTING ,DEEP learning ,TIME series analysis - Abstract
Domain generalization aims to design models that can effectively generalize to unseen target domains by learning from observed source domains. Domain generalization poses a significant challenge for time series data, due to varying data distributions and temporal dependencies. Existing approaches to domain generalization are not designed for time series data, which often results in suboptimal or unstable performance when confronted with diverse temporal patterns and complex data characteristics. We propose a novel approach to tackle the problem of domain generalization in time series forecasting. We focus on a scenario where time series domains share certain common attributes and exhibit no abrupt distribution shifts. Our method revolves around the incorporation of a key regularization term into an existing time series forecasting model: domain discrepancy regularization. In this way, we aim to enforce consistent performance across different domains that exhibit distinct patterns. We calibrate the regularization term by investigating the performance within individual domains and propose the domain discrepancy regularization with domain difficulty awareness. We demonstrate the effectiveness of our method on multiple datasets, including synthetic and real-world time series datasets from diverse domains such as retail, transportation, and finance. Our method is compared against traditional methods, deep learning models, and domain generalization approaches to provide comprehensive insights into its performance. In these experiments, our method showcases superior performance, surpassing both the base model and competing domain generalization models across all datasets. Furthermore, our method is highly general and can be applied to various time series models. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Report on the Search Futures Workshop at ECIR 2024.
- Author
-
Azzopardi, Leif, Clarke, Charles L. A., Kantor, Paul, Mitra, Bhaskar, Trippas, Johanne R., Ren, Zhaochun, Aliannejadi, Mohammad, Arabzadeh, Negar, Chandrasekar, Raman, de Rijke, Maarten, Eustratiadis, Panagiotis, Hersh, William, Huang, Jin, Kanoulas, Evangelos, Kareem, Jasmin, Li, Yongkang, Lupart, Simon, Mekonnen, Kidist Amde, Roegiest, Adam, and Soboroff, Ian
- Subjects
LANGUAGE models ,GENERATIVE artificial intelligence ,INFORMATION retrieval ,CIVIL rights ,LANGUAGE ability - Abstract
The First Search Futures Workshop, in conjunction with the Fourty-sixth European Conference on Information Retrieval (ECIR) 2024, looked into the future of search to ask questions such as: • How can we harness the power of generative AI to enhance, improve and re-imagine Information Retrieval (IR)? • What are the principles and fundamental rights that the field of Information Retrieval should strive to uphold? • How can we build trustworthy IR systems in light of Large Language Models and their ability to generate content at super human speeds? • What new applications and affordances does generative AI offer and enable, and can we go back to the future, and do what we only dreamed of previously? The workshop started with seventeen lightning talks from a diverse set speakers. Instead of conventional paper presentations, the lightning talks provided a rapid and concise overview of ideas, allowing speakers to share critical points or novel concepts quickly. This format was designed to encourage discussion and introduce a wide range of topics within a short period, thereby maximising the exchange of ideas and ensuring that participants could gain insights into various future search areas without the deep dive typically required in longer presentations. This report, co-authored by the workshop's organisers and its participants, summarises the talks and discussions. This report aims to provide the broader IR community with the insights and ideas discussed and debated during the workshop - and to provide a platform for future discussion. Date: 24 March 2024. Website: https://searchfutures.github.io/. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Understanding and Predicting User Satisfaction with Conversational Recommender Systems.
- Author
-
SIRO, CLEMENCIA, ALIANNEJADI, MOHAMMAD, and DE RIJKE, MAARTEN
- Abstract
The article investigates user satisfaction in conversational recommender systems (CRSs) and proposes a method for understanding and predicting it. It explores the impact of various dialogue aspects on user satisfaction, including relevance, interestingness, understanding, task completion, interest arousal, and efficiency. It is reported that unlike previous methods relying on turn-level satisfaction ratings, the proposed approach considers broader dialogue aspects.
- Published
- 2024
- Full Text
- View/download PDF
7. Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems.
- Author
-
WEIWEI SUN, SHUYU GUO, SHUO ZHANG, PENGJIE REN, ZHUMIN CHEN, DE RIJKE, MAARTEN, and ZHAOCHUN REN
- Abstract
The article focuses on improving the evaluation of task-oriented dialogue systems (TDSs) through the use of user simulators. Topics include the limitations of current TDS evaluation methods, the challenges of employing user simulators for TDS evaluation, and the proposed solution which involves a metaphorical user simulator (MetaSim) and a tester-based evaluation framework.
- Published
- 2024
- Full Text
- View/download PDF
8. A Next Basket Recommendation Reality Check.
- Author
-
MING LI, JULLIEN, SAMI, ARIANNEZHAD, MOZHDEH, and DE RIJKE, MAARTEN
- Abstract
The article focuses on evaluating Next Basket Recommendation (NBR) methods for suggesting items in users future shopping baskets. It discusses the distinction between repeat and explore items in recommendations, introduces novel metrics for NBR evaluation, and highlights the variations in method performance across different datasets and scenarios, shedding light on the challenges and opportunities in this area of research.
- Published
- 2023
- Full Text
- View/download PDF
9. PRADA: Practical Black-box Adversarial Attacks against Neural Ranking Models.
- Author
-
CHEN WU, RUQING ZHANG, JIAFENG GUO, DE RIJKE, MAARTEN, YIXING FAN, and XUEQI CHENG
- Abstract
The article's focus lies in examining the vulnerability of neural ranking models (NRMs) to adversarial attacks, particularly emphasizing the Word Substitution Ranking Attack (WSRA) task, aiming to enhance a target document's ranking by subtly altering its text. It covers topics such as proposing a novel PRADA method for generating adversarial examples, conducting experiments on web search datasets, and highlighting the importance of identifying NRM vulnerabilities to enhance model robustness.
- Published
- 2023
- Full Text
- View/download PDF
10. Evaluating the Robustness of Click Models to Policy Distributional Shift.
- Author
-
DEFFAYET, ROMAIN, RENDERS, JEAN-MICHEL, and DE RIJKE, MAARTEN
- Abstract
The article primarily addresses the evaluation of click models used in search engines and their sensitivity to changes in ranking policies, known as policy distributional shift (PDS). It explores the impact of PDS on click models and proposes a new evaluation protocol to assess their robustness in various downstream tasks, such as click-through rate prediction and offline bandits, providing insights and guidelines for handling policy changes in click model deployments.
- Published
- 2023
- Full Text
- View/download PDF
11. Improving Transformer-based Sequential Recommenders through Preference Editing.
- Author
-
MUYANG MA, PENGJIE REN, ZHUMIN CHEN, ZHAOCHUN REN, HUASHENG LIANG, JUN MA, and DE RIJKE, MAARTEN
- Abstract
One of the key challenges in sequential recommendation is how to extract and represent user preferences. Traditional methods rely solely on predicting the next item. But user behavior may be driven by complex preferences. Therefore, these methods cannot make accurate recommendations when the available information user behavior is limited. To explore multiple user preferences, we propose a transformer-based sequential recommendation model, named MrTransformer (Multi-preference Transformer). For training MrTransformer, we devise a preference-editing-based self-supervised learning (SSL) mechanism that explores extra supervision signals based on relations with other sequences. The idea is to force the sequential recommendation model to discriminate between common and unique preferences in different sequences of interactions. By doing so, the sequential recommendation model is able to disentangle user preferences into multiple independent preference representations so as to improve user preference extraction and representation. We carry out extensive experiments on five benchmark datasets. MrTransformer with preference editing significantly outperforms state-of-the-art sequential recommendation methods in terms of Recall, MRR, and NDCG. We find that long sequences of interactions from which user preferences are harder to extract and represent benefit most from preference editing. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
12. Scalable Representation Learning for Dynamic Heterogeneous Information Networks via Metagraphs.
- Author
-
YANG FANG, XIANG ZHAO, PEIXIN HUANG, WEIDONG XIAO, and DE RIJKE, MAARTEN
- Subjects
INFORMATION networks ,TIMESTAMPS ,INFORMATION retrieval ,DYNAMIC models - Abstract
Content representation is a fundamental task in information retrieval. Representation learning is aimed at capturing features of an information object in a low-dimensional space. Most research on representation learning for heterogeneous information networks (HINs) focuses on static HINs. In practice, however, networks are dynamic and subject to constant change. In this article, we propose a novel and scalable representation learning model, M-DHIN, to explore the evolution of a dynamic HIN. We regard a dynamic HIN as a series of snapshots with different time stamps. We first use a static embedding method to learn the initial embeddings of a dynamic HIN at the first time stamp. We describe the features of the initial HIN via metagraphs, which retains more structural and semantic information than traditional path-oriented static models. We also adopt a complex embedding scheme to better distinguish between symmetric and asymmetric metagraphs. Unlike traditional models that process an entire network at each time stamp, we build a so-called change dataset that only includes nodes involved in a triadic closure or opening process, as well as newly added or deleted nodes. Then, we utilize the above metagraph-based mechanism to train on the change dataset. As a result of this setup, M-DHIN is scalable to large dynamic HINs since it only needs to model the entire HIN once while only the changed parts need to be processed over time. Existing dynamic embedding models only express the existing snapshots and cannot predict the future network structure. To equip M-DHIN with this ability, we introduce an LSTM-based deep autoencoder model that processes the evolution of the graph via an LSTM encoder and outputs the predicted graph. Finally, we evaluate the proposed model, M-DHIN, on real-life datasets and demonstrate that it significantly and consistently outperforms state-of-the-art models. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
13. Offline Evaluation for Reinforcement Learning-Based Recommendation: A Critical Issue and Some Alternatives.
- Author
-
Deffayet, Romain, Thonet, Thibaut, Renders, Jean-Michel, and de Rijke, Maarten
- Subjects
REINFORCEMENT learning ,RECOMMENDER systems ,RESEARCH evaluation - Abstract
In this paper, we argue that the paradigm commonly adopted for offline evaluation of sequential recommender systems is unsuitable for evaluating reinforcement learning-based recommenders. We find that most of the existing offline evaluation practices for reinforcement learning-based recommendation are based on a next-item prediction protocol, and detail three shortcomings of such an evaluation protocol. Notably, it cannot reflect the potential benefits that reinforcement learning (RL) is expected to bring while it hides critical deficiencies of certain offline RL agents. Our suggestions for alternative ways to evaluate RL-based recommender systems aim to shed light on the existing possibilities and inspire future research on reliable evaluation protocols. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
14. Hyperspherical Variational Co-embedding for Attributed Networks.
- Author
-
JINYUAN FANG, SHANGSONG LIANG, ZAIQIAO MENG, and DE RIJKE, MAARTEN
- Subjects
VIRTUAL networks ,SOCIAL networks ,INFORMATION retrieval - Abstract
Network-based information has been widely explored and exploited in the information retrieval literature. Attributed networks, consisting of nodes, edges aswell as attributes describing properties of nodes, are a basic type of network-based data, and are especially useful for many applications. Examples include user profiling in social networks and item recommendation in user-item purchase networks. Learning useful and expressive representations of entities in attributed networks can provide more effective building blocks to down-stream network-based tasks such as link prediction and attribute inference. Practically, input features of attributed networks are normalized as unit directional vectors. However, most network embedding techniques ignore the spherical nature of inputs and focus on learning representations in a Gaussian or Euclidean space, which, we hypothesize, might lead to less effective representations. To obtain more effective representations of attributed networks, we investigate the problem of mapping an attributed networkwith unit normalized directional features into a non-Gaussian and non-Euclidean space. Specifically, we propose a hyperspherical variational co-embedding for attributed networks (HCAN), which is based on generalized variational auto-encoders for heterogeneous data with multiple types of entities. HCAN jointly learns latent embeddings for both nodes and attributes in a unified hyperspherical space such that the affinities between nodes and attributes can be captured effectively. We argue that this is a crucial feature in many real-world applications of attributed networks. Previous Gaussian network embedding algorithms break the assumption of uninformative prior, which leads to unstable results and poor performance. In contrast, HCAN embeds nodes and attributes as von Mises-Fisher distributions, and allows one to capture the uncertainty of the inferred representations. Experimental results on eight datasets show that HCAN yields better performance in a number of applications compared with nine state-of-the-art baselines. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
15. Multi-interest Diversification for End-to-end Sequential Recommendation.
- Author
-
WANYU CHEN, PENGJIE REN, FEI CAI, FEI SUN, and DE RIJKE, MAARTEN
- Subjects
MAXIMUM entropy method ,COMPUTATIONAL complexity ,ENTROPY ,LATENT semantic analysis - Abstract
A preliminary version of this article appeared in the proceedings of CIKM 2020 [10]. In this extension, we (1) propose another interest extractor, i.e., dynamic routing, in the implicit interest mining module, and another type of disagreement regularization, i.e., output disagreement regularization, in our interest-aware, diversity promoting loss; (2) investigate the performance of our multi-interest, diversified, sequential recommendation model with different interest extractors in implicit interest mining, i.e., multi-head attention vs. dynamic routing; (3) investigate the performance of multi-interest, diversified, sequential recommendation with various latent interests numbers; (4) explore the influence of the parameter λ on the performance of multi-interest, diversified, sequential recommendation; (5) investigate the performance of multiinterest, diversified, sequential recommendation with different types of disagreement regularization; (6) investigate the impact of maximum entropy regularization on the performance of multi-interest, diversified, sequential recommendation; (7) provide a case study to show the recommendations generated by multi-interest, diversified, sequential recommendation; (8) analyze the computational complexity of the baseline model as well as our proposal; and (9) survey more related work and conduct a more detailed analysis of the approach and experimental results. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
16. Conversations with Search Engines: SERP-based Conversational Response Generation.
- Author
-
PENGJIE REN, ZHUMIN CHEN, ZHAOCHUN REN, KANOULAS, EVANGELOS, MONZ, CHRISTOF, and DE RIJKE, MAARTEN
- Subjects
INFORMATION needs ,NATURAL languages ,QUESTION answering systems ,SEARCH engines ,CROWDSOURCING - Abstract
In this article, we address the problem of answering complex information needs by conducting conversations with search engines, in the sense that users can express their queries in natural language and directly receive the information they need from a short system response in a conversationalmanner. Recently, there have been some attempts towards a similar goal, e.g., studies on Conversational Agents (CAs) and Conversational Search (CS). However, they either do not address complex information needs in search scenarios or they are limited to the development of conceptual frameworks and/or laboratory-based user studies. We pursue two goals in this article: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines, and (2) the development of a state-of-the-art pipeline for conversations with search engines, Conversations with Search Engines (CaSE), using this dataset. SaaC is built based on a multi-turn conversational search dataset, where we further employ workers from a crowdsourcing platform to summarize each relevant passage into a short, conversational response. CaSE enhances the state-of-the-art by introducing a supporting token identification module and a prior-aware pointer generator, which enables us to generate more accurate responses. We carry out experiments to show that CaSE is able to outperform strong baselines. We also conduct extensive analyses on the SaaC dataset to show where there is room for further improvement beyond CaSE. Finally, we release the SaaC dataset and the code for CaSE and all models used for comparison to facilitate future research on this topic. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
17. A Large-scale Analysis of Mixed Initiative in Information-Seeking Dialogues for Conversational Search.
- Author
-
VAKULENKO, SVITLANA, KANOULAS, EVANGELOS, and DE RIJKE, MAARTEN
- Subjects
ARTIFICIAL intelligence ,ACQUISITION of data - Abstract
Conversational search is a relatively young area of research that aims at automating an information-seeking dialogue. In this article, we help to position it with respect to other research areas within conversational artificial intelligence (AI) by analysing the structural properties of an information-seeking dialogue. To this end, we perform a large-scale dialogue analysis of more than 150K transcripts from 16 publicly available dialogue datasets. These datasets were collected to inform different dialogue-based tasks including conversational search. We extract different patterns of mixed initiative from these dialogue transcripts and use them to compare dialogues of different types. Moreover, we contrast the patterns found in information-seeking dialogues that are being used for research purposes with the patterns found in virtual reference interviews that were conducted by professional librarians. The insights we provide (1) establish close relations between conversational search and other conversational AI tasks and (2) uncover limitations of existing conversational datasets to inform future data collection tasks. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
18. PROMISE retreat report : prospects and opportunities for information access evaluation
- Author
-
Agosti, Maristella, Berendsen, Richard, Bogers, Toine, Braschler, Martin, Buitelaar, Paul, Choukri, Khalid, Di Nunzio, Giorgio Maria, Ferro, Nicola, Forner, Pamela, Hanbury, Allan, Friberg Heppin, Karin, Hansen, Preben, Järvelin, Anni, Larsen, Birger, Lupu, Mihai, Masiero, Ivano, Müller, Henning, Peruzzo, Simone, Petras, Vivien, Piroi, Florina, de Rijke, Maarten, Santucci, Giuseppe, Silvello, Gianmaria, Toms, Elaine, Agosti, Maristella, Berendsen, Richard, Bogers, Toine, Braschler, Martin, Buitelaar, Paul, Choukri, Khalid, Di Nunzio, Giorgio Maria, Ferro, Nicola, Forner, Pamela, Hanbury, Allan, Friberg Heppin, Karin, Hansen, Preben, Järvelin, Anni, Larsen, Birger, Lupu, Mihai, Masiero, Ivano, Müller, Henning, Peruzzo, Simone, Petras, Vivien, Piroi, Florina, de Rijke, Maarten, Santucci, Giuseppe, Silvello, Gianmaria, and Toms, Elaine
- Published
- 2018
19. CLEF 2010 conference on multilingual and multimodal information access evaluation
- Author
-
Agosti, Maristella, Braschler, Martin, Choukri, Khalid, Ferro, Nicola, Harman, Donna, Peters, Carol, Pianta, Emanuele, de Rijke, Maarten, Smeaton, Alan, Agosti, Maristella, Braschler, Martin, Choukri, Khalid, Ferro, Nicola, Harman, Donna, Peters, Carol, Pianta, Emanuele, de Rijke, Maarten, and Smeaton, Alan
- Published
- 2018
20. Safe Exploration for Optimizing Contextual Bandits.
- Author
-
JAGERMAN, ROLF, MARKOV, ILYA, and DE RIJKE, MAARTEN
- Subjects
CONTEXTUAL learning ,INFORMATION retrieval ,ALGORITHMS ,ONLINE education ,RANKING (Statistics) - Abstract
Contextual bandit problems are a natural fit for many information retrieval tasks, such as learning to rank, text classification, recommendation, and so on. However, existing learning methods for contextual bandit problems have one of two drawbacks: They either do not explore the space of all possible document rankings (i.e., actions) and, thus, may miss the optimal ranking, or they present suboptimal rankings to a user and, thus, may harm the user experience. We introduce a new learning method for contextual bandit problems, Safe Exploration Algorithm (SEA), which overcomes the above drawbacks. SEA starts by using a baseline (or production) ranking system (i.e., policy), which does not harm the user experience and, thus, is safe to execute but has suboptimal performance and, thus, needs to be improved. Then SEA uses counterfactual learning to learn a new policy based on the behavior of the baseline policy. SEA also uses high-confidence off-policy evaluation to estimate the performance of the newly learned policy. Once the performance of the newly learned policy is at least as good as the performance of the baseline policy, SEA starts using the new policy to execute new actions, allowing it to actively explore favorable regions of the action space. This way, SEA never performs worse than the baseline policy and, thus, does not harm the user experience, while still exploring the action space and, thus, being able to find an optimal policy. Our experiments using text classification and document retrieval confirm the above by comparing SEA (and a boundless variant called BSEA) to online and offline learning methods for contextual bandit problems. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
21. The Potential of Learned Index Structures for Index Compression.
- Author
-
Oosterhuis, Harrie, Culpepper, J. Shane, and de Rijke, Maarten
- Published
- 2018
- Full Text
- View/download PDF
22. Early detection of topical expertise in community question and answering
- Author
-
van Dijk, David, Tsagkias, Manos, de Rijke, Maarten, Gwizdka, J., Jose, J., Mostafa, J., Wilson, M., Information and Language Processing Syst (IVI, FNWI), and Lectoraat E-Discovery
- Subjects
Focus (computing) ,Information retrieval ,Computer science ,020204 information systems ,0202 electrical engineering, electronic engineering, information engineering ,Feature (machine learning) ,Question answering ,Early detection ,020201 artificial intelligence & image processing ,02 engineering and technology ,Expertise finding ,Baseline (configuration management) - Abstract
We focus on detecting potential topical experts in community question answering platforms early on in their lifecycle. We use a semi-supervised machine learning approach. We extract three types of feature: (i) textual, (ii) behavioral, and (iii) time-aware, which we use to predict whether a user will become an expert in the longterm. We compare our method to a machine learning method based on a state-of-the-art method in expertise retrieval. Results on data from Stack Overflow demonstrate the utility of adding behavioral and time-aware features to the baseline method with a net improvement in accuracy of 26% for very early detection of expertise.
- Published
- 2015
23. Report on the international workshop on natural language processing for recommendations (NLP4REC 2020) workshop held at WSDM 2020.
- Author
-
Huang, Xiao, Ren, Pengjie, Ren, Zhaochun, Sun, Fei, He, Xiangnan, Yin, Dawei, and de Rijke, Maarten
- Subjects
RECOMMENDER systems ,NATURAL language processing ,INDUSTRIAL research - Abstract
This paper summarizes the outcomes of the International Workshop on Natural Language Processing for Recommendations (NLP4REC 2020), held in Houston, USA, on February 7, 2020, during WSDM 2020. The purpose of this workshop was to explore the potential research topics and industrial applications in leveraging natural language processing techniques to tackle the challenges in constructing more intelligent recommender systems. Specific topics included, but were not limited to knowledge-aware recommendation, explainable recommendation, conversational recommendation, and sequential recommendation. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
24. Challenges and research opportunities in eCommerce search and recommendations.
- Author
-
Tsagkias, Manos, King, Tracy Holloway, Kallumadi, Surya, Murdock, Vanessa, and de Rijke, Maarten
- Subjects
ELECTRONIC commerce ,RECOMMENDER systems ,ONLINE shopping ,HUMAN-computer interaction ,PRODUCT improvement ,UNIVERSITY research - Abstract
With the rapid adoption of online shopping, academic research in the eCommerce domain has gained traction. However, significant research challenges remain, spanning from classic eCommerce search problems such as matching textual queries to multi-modal documents and ranking optimization for two-sided marketplaces to human-computer interaction and recommender systems for discovery and browsing. These research areas are important for understanding customer behavior, driving engagement, and improving product discoverability and conversion. In this article we identify the challenges and highlight research opportunities to improve the eCommerce customer experience. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
25. FACTS-IR: Fairness, Accountability, Confidentiality, Transparency, and Safety in Information Retrieval.
- Author
-
Olteanu, Alexandra, Garcia-Gathright, Jean, de Rijke, Maarten, Ekstrand, Michael D., Roegiest, Adam, Lipani, Aldo, Beutel, Alex, Lucic, Ana, Stoica, Ana-Andreea, Das, Anubrata, Biega, Asia, Voorn, Bart, Hauff, Claudia, Spina, Damiano, Lewis, David, Oard, Douglas W., Yilmaz, Emine, Hasibi, Faegheh, Kazai, Gabriella, and McDonald, Graham
- Subjects
INFORMATION retrieval ,INFORMATION storage & retrieval systems ,FAIRNESS ,CONFIDENTIAL communications ,SYSTEMS development - Abstract
The purpose of the SIGIR 2019 workshop on Fairness, Accountability, Confidentiality, Transparency, and Safety (FACTS-IR) was to explore challenges in responsible information retrieval system development and deployment. To this end, the workshop aimed to crowdsource from the larger SIGIR community and draft an actionable research agenda on five key dimensions of responsible information retrieval: fairness, accountability, confidentiality, transparency, and safety. Such an agenda can guide others in the community that are interested in pursuing FACTS-IR research, as well as inform potential funders about relevant research avenues. The workshop brought together a diverse set of researchers and practitioners interested in contributing to the development of a technical research agenda for responsible information retrieval. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
26. Joint Neural Collaborative Filtering for Recommender Systems.
- Author
-
WANYU CHEN, FEI CAI, HONGHUI CHEN, and DE RIJKE, MAARTEN
- Subjects
RECOMMENDER systems ,COST functions ,FILTERS & filtration - Abstract
We propose a Joint Neural Collaborative Filtering (J-NCF) method for recommender systems. The J-NCF model applies a joint neural network that couples deep feature learning and deep interaction modeling with a rating matrix. Deep feature learning extracts feature representations of users and items with a deep learning architecture based on a user-item rating matrix. Deep interaction modeling captures non-linear user-item interactions with a deep neural network using the feature representations generated by the deep feature learning process as input. J-NCF enables the deep feature learning and deep interaction modeling processes to optimize each other through joint training, which leads to improved recommendation performance. In addition, we design a new loss function for optimization that takes both implicit and explicit feedback, pointwise and pair-wise loss into account. Experiments on several real-world datasets show significant improvements of J-NCF over state-of-the-art methods, with improvements of up to 8.24% on the MovieLens 100K dataset, 10.81% on the MovieLens 1M dataset, and 10.21% on the Amazon Movies dataset in terms of HR@10. NDCG@10 improvements are 12.42%, 14.24%, and 15.06%, respectively. We also conduct experiments to evaluate the scalability and sensitivity of J-NCF. Our experiments show that the J-NCF model has a competitive recommendation performance with inactive users and different degrees of data sparsity when compared to state-of-the-art baselines. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
27. Personalised Reranking of Paper Recommendations Using Paper Content and User Behavior.
- Author
-
XINYI LI, YIFAN CHEN, PETTIT, BENJAMIN, and DE RIJKE, MAARTEN
- Subjects
SEARCH engines ,EMAIL ,NEWSLETTERS ,RESEARCH ,MANUFACTURING processes - Abstract
Academic search engines have been widely used to access academic papers, where users' information needs are explicitly represented as search queries. Some modern recommender systems have taken one step further by predicting users' information needswithout the presence of an explicit query. In this article,we examine an academic paper recommender that sends out paper recommendations in email newsletters, based on the users' browsing history on the academic search engine. Specifically, we look at users who regularly browse papers on the search engine, and we sign up for the recommendation newsletters for the first time. We address the task of reranking the recommendation candidates that are generated by a production system for such users. We face the challenge that the users on whom we focus have not interacted with the recommender system before, which is a common scenario that every recommender system encounters when new users sign up. We propose an approach to reranking candidate recommendations that utilizes both paper content and user behavior. The approach is designed to suit the characteristics unique to our academic recommendation setting. For instance, content similarity measures can be used to find the closest match between candidate recommendations and the papers previously browsed by the user. To this end, we use a knowledge graph derived from paper metadata to compare entity similarities (papers, authors, and journals) in the embedding space. Since the users on whom we focus have no prior interactions with the recommender system, we propose a model to learn a mapping from users' browsed articles to user clicks on the recommendations. We combine both content and behavior into a hybrid reranking model that outperforms the production baseline significantly, providing a relative 13% increase in Mean Average Precision and 28% in Precision@1. Moreover, we provide a detailed analysis of the model components, highlighting where the performance boost comes from. The obtained insights reveal useful components for the reranking process and can be generalized to other academic recommendation settings as well, such as the utility of graph embedding similarity. Also, recent papers browsed by users provide stronger evidence for recommendation than historical ones. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
28. Sentence Relations for Extractive Summarization with Deep Neural Networks.
- Author
-
PENGJIE REN, ZHUMIN CHEN, ZHAOCHUN REN, FURU WEI, LIQIANG NIE, JUN MA, and DE RIJKE, MAARTEN
- Subjects
ARTIFICIAL neural networks ,DATABASES ,ALGORITHMS ,DATA analysis ,SEMANTICS - Abstract
Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively. We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attentionmechanism to simulate people's reading abilitywith the main idea (title) in mind. QSRSum evaluates the relevance of each sentencewith given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognizewhich parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations. We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
29. Report on the DATA.
- Author
-
Koesten, Laura, Mayr, Philipp, Groth, Paul, Simperl, Elena, and de Rijke, Maarten
- Subjects
DATA analysis ,FORUMS ,INFORMATION retrieval ,ELECTRONIC data processing ,INTERNET searching - Abstract
The increasing availability of structured data on the web makes searching for data an important and timely topic. This report presents the motivation, output, and research challenges of the second DATA:SEARCH workshop which was held in conjunction with SIGIR 2018, in Ann Arbor, Michigan. This workshop explored challenges in data search, with a particular focus on data on the web. The aim was to share and establish links between different perspectives on search and discovery for different kinds of structured data, which can potentially inform the design of a wide range of information retrieval technologies. The DATA:SEARCH workshop tries to bring together communities interested in making the web of data more discoverable, easier to search and more user friendly. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
30. What Should We Teach in Information Retrieval?
- Author
-
Markov, Ilya and de Rijke, Maarten
- Subjects
INFORMATION retrieval ,SEARCH engines ,ACCESS to information ,INTERNET searching ,WORLD Wide Web - Abstract
Modern Information Retrieval (IR) systems, such as search engines, recommender systems, and conversational agents, are best thought of as interactive systems. And their development is best thought of as a two-stage development process: offline development followed by continued online adaptation and development based on interactions with users. In this opinion paper, we take a closer look at existing IR textbooks and teaching materials, and examine to which degree they cover the offline and online stages of the IR system development process. We notice that current teaching materials in IR focus mostly on search and on the offline development phase. Other scenarios of interacting with information are largely absent from current IR teaching materials, as is the (interactive) online development phase. We identify a list of scenarios and a list of topics that we believe are essential to any modern set of IR teaching materials that claims to fully cover IR system development. In particular, we argue for more attention, in basic IR teaching materials, to scenarios such as recommender systems, and to topics such as query and interaction mining and understanding, online evaluation, and online learning to rank. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
31. Report on the Second SIGIR Workshop on Neural Information Retrieval (Neu-IR'17).
- Author
-
Craswell, Nick, Croft, W. Bruce, de Rijke, Maarten, Guo, Jiafeng, and Mitra, Bhaskar
- Subjects
BENCHMARKING (Management) ,REPRODUCIBLE research ,INSTITUTIONAL repositories ,SCHOLARS ,EVALUATION - Abstract
The second SIGIR workshop on neural information retrieval (Neu-IR?17) took place on August 11, 2017, in Tokyo, Japan. Following the successful 2016 edition, the workshop continued to serve as a forum for academic and industrial researchers to present new work on neural methods for retrieval. In addition, a special track was organized focusing on resources for evaluation and reproducibility, including proposals for public benchmarking datasets and shared model repositories. A total of 19 papers?which included five special track papers? were presented in the form of oral or poster presentations. Organizers of four of the TREC 2017 tracks were invited to present at the workshop on how these IR tasks may be suitable for evaluating recent data-hungry neural approaches. The full-day workshop?with more than 170 registrants?concluded with an engaging panel discussion. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
32. Report on the SIGIR 2017 Workshop on eCommerce (ECOM17).
- Author
-
Degenhardt, Jon, Kallumadi, Surya, Lin, Yiu-Chang, de Rijke, Maarten, Si, Luo, Trotman, Andrew, Venkatesh, Sindhuja, and Yinghui, Xu
- Subjects
ELECTRONIC commerce ,INFORMATION retrieval ,BENCHMARKING (Management) ,ORATORS ,SUBSET selection - Abstract
The SIGIR 2017 Workshop on eCommerce (ECOM17), was a full day workshop that took place on Friday, August 11, 2017 in Tokyo, Japan. The purpose of the workshop was to serve as a platform for publication and discussion of Information Retrieval and NLP research and their applications in the domain of eCommerce. The workshop program was designed to bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to product search and recommendation in the eCommerce domain. Another goal of the workshop was to examine the building of a benchmark data set to facilitate research into this topic. The workshop drew contributions from both industry as well as academia, in total the workshop received a total of twenty one submissions, and accepted thirteen papers. In addition to presentation of a subset of accepted submissions, the workshop had two keynotes by invited speakers from the industry, a poster session where all the accepted submissions were presented, a breakout session, a panel discussion, and a group discussion. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
33. Report on the 2017 ACM SIGIR International Conference Theory of Information Retrieval (ICTIR?17).
- Author
-
Fang, Hui, Kamps, Jaap, Kanoulas, Evangelos, de Rijke, Maarten, and Yilmaz, Emine
- Subjects
COMPUTERS ,INFORMATION retrieval ,DISCIPLINE ,HUMAN information processing ,MACHINE learning - Abstract
This is a report on ICTIR'17, which continued its tradition of being the premier forum for presentation of research on theoretical aspects of Information Retrieval (IR). This includes theory in a broad sense, including conceptual papers that explore key concepts, theoretical papers that model concepts and/or relations between concepts, and papers that study theory in experimental or industrial settings. The importance of information access and information processing in industry and academia is growing in a revolutionary way, making the discussion on fundamental and long term aspects, and their relation to short term success and failure, more urgent than ever before. To highlight the increasingly strong connections between Information Retrieval and its neighboring disciplines, ICTIR'17 explicitly welcomed papers in IR areas that overlap with Human Information Access, Machine Learning, Natural Language Processing and Perception. ICTIR'17 in Amsterdam was a memorable conference. For those who like numbers: we had 142 attendees (biggest ICTIR ever), and 97 submissions with 52 accepted (largest ICTIR ever), 450/250 euro registration for everything (cheapest ICTIR ever), and for the first time in history the organization and keynotes of a leading IR conference where majority female (but selected for being outstanding researchers, of course). [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
34. Diversifying Query Auto-Completion.
- Author
-
FEI CAI, REINANDA, RIDHO, and DE RIJKE, MAARTEN
- Subjects
QUERY (Information retrieval system) ,SEMANTICS ,AUTOMATIC control systems ,COMPUTER science ,INTERNET searching - Abstract
Query auto-completion assists web search users in formulating queries with a few keystrokes, helping them to avoid spelling mistakes and to produce clear query expressions, and so on. Previous work on query autocompletion mainly centers around returning a list of completions to users, aiming to push queries that are most likely intended by the user to the top positions but ignoring the redundancy among the query candidates in the list. Thus, semantically related queries matching the input prefix are often returned together. This may push valuable suggestions out of the list, given that only a limited number of candidates can be shown to the user, which may result in a less than optimal search experience. In this article, we consider the task of diversifying query auto-completion, which aims to return the correct query completions early in a ranked list of candidate completions and at the same time reduce the redundancy among query auto-completion candidates. We develop a greedy query selection approach that predicts query completions based on the current search popularity of candidate completions and on the aspects of previous queries in the same search session. The popularity of completion candidates at query time can be directly aggregated from query logs. However, query aspects are implicitly expressed by previous clicked documents in the search context. To determine the query aspect, we categorize clicked documents of a query using a hierarchy based on the open directory project. Bayesian probabilistic matrix factorization is applied to derive the distribution of queries over all aspects. We quantify the improvement of our greedy query selection model against a state-of-the-art baseline using two large-scale, real-world query logs and show that it beats the baseline in terms of well-known metrics used in query auto-completion and diversification. In addition, we conduct a side-by-side experiment to verify the effectiveness of our proposal. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
35. Personalized search result diversification via structured learning.
- Author
-
Liang, Shangsong, Ren, Zhaochun, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
36. A syntax-aware re-ranker for microblog retrieval.
- Author
-
Severyn, Aliaksei, Moschitti, Alessandro, Tsagkias, Manos, Berendsen, Richard, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
37. Recipient recommendation in enterprises using communication graphs and email content.
- Author
-
Graus, David, van Dijk, David, Tsagkias, Manos, Weerkamp, Wouter, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
38. Evaluating intuitiveness of vertical-aware click models.
- Author
-
Chuklin, Aleksandr, Zhou, Ke, Schuth, Anne, Sietsma, Floor, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
39. Personalized document re-ranking based on Bayesian probabilistic matrix factorization.
- Author
-
Cai, Fei, Liang, Shangsong, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
40. Fusion helps diversification.
- Author
-
Liang, Shangsong, Ren, Zhaochun, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
41. Hierarchical multi-label classification of social text streams.
- Author
-
Ren, Zhaochun, Peetz, Maria-Hendrike, Liang, Shangsong, van Dolen, Willemijn, and de Rijke, Maarten
- Published
- 2014
- Full Text
- View/download PDF
42. Relative confidence sampling for efficient on-line ranker evaluation.
- Author
-
Zoghi, Masrour, Whiteson, Shimon A., de Rijke, Maarten, and Munos, Remi
- Published
- 2014
- Full Text
- View/download PDF
43. Report on the SIGIR 2016 Workshop on Neural Information Retrieval (Neu-IR).
- Author
-
Craswell, Nick, Croft, W. Bruce, Jiafeng Guo, Mitra, Bhaskar, and de Rijke, Maarten
- Subjects
INFORMATION retrieval ,INFORMATION storage & retrieval systems ,MACHINE learning ,ARTIFICIAL neural networks ,BEST practices - Abstract
The SIGIR 2016 workshop on Neural Information Retrieval (Neu-IR) took place on 21 July, 2016 in Pisa. The goal of the Neu-IR (pronounced "New IR") workshop was to serve as a forum for academic and industrial researchers, working at the intersection of information retrieval (IR) and machine learning, to present new work and early results, compare notes on neural network toolkits, share best practices, and discuss the main challenges facing this line of research. In total, 19 papers were presented, including oral and poster presentations. The workshop program also included a session on invited "lightning talks" to encourage participants to share personal insights and negative results with the community. The workshop was well-attended with more than 120 registrations. [ABSTRACT FROM AUTHOR]
- Published
- 2016
44. Data-Driven Information Retrieval.
- Author
-
Agosti, Maristella, Alonso, Omar, de Rijke, Maarten, and Perego, Raffaele
- Subjects
INFORMATION retrieval ,INFORMATION storage & retrieval systems ,DATA transmission systems ,ARTIFICIAL intelligence ,MACHINE learning - Published
- 2016
45. A Comparative Analysis of Interleaving Methods for Aggregated Search.
- Author
-
CHUKLIN, ALEKSANDR, SCHUTH, ANNE, KE ZHOU, and DE RIJKE, MAARTEN
- Subjects
CODING theory ,DATA compression ,DIGITAL electronics ,INFORMATION storage & retrieval systems ,ELECTRONIC information resources - Abstract
A result page of a modern search engine often goes beyond a simple list of "10 blue links." Many specific user needs (e.g., News, Image, Video) are addressed by so-called aggregated or vertical search solutions: specially presented documents, often retrieved from specific sources, that stand out from the regular organic Web search results. When it comes to evaluating ranking systems, such complex result layouts raise their own challenges. This is especially true for so-called interleaving methods that have arisen as an important type of online evaluation: by mixing results from two different result pages, interleaving can easily break the desired Web layout in which vertical documents are grouped together, and hence hurt the user experience. We conduct an analysis of different interleaving methods as applied to aggregated search engine result pages. Apart from conventional interleaving methods, we propose two vertical-aware methods: one derived from the widely used Team-Draft Interleaving method by adjusting it in such a way that it respects vertical document groupings, and another based on the recently introduced Optimized Interleaving framework. We show that our proposed methods are better at preserving the user experience than existing interleaving methods while still performing well as a tool for comparing ranking systems. For evaluating our proposed vertical-aware interleaving methods, we use real-world click data as well as simulated clicks and simulated ranking systems. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
46. Inside the world's playlist.
- Author
-
Weerkamp, Wouter, Tsagkias, Manos, and de Rijke, Maarten
- Published
- 2013
- Full Text
- View/download PDF
47. Modeling clicks beyond the first result page.
- Author
-
Chuklin, Aleksandr, Serdyukov, Pavel, and de Rijke, Maarten
- Published
- 2013
- Full Text
- View/download PDF
48. Evaluating aggregated search using interleaving.
- Author
-
Chuklin, Aleksandr, Schuth, Anne, Hofmann, Katja, Serdyukov, Pavel, and de Rijke, Maarten
- Published
- 2013
- Full Text
- View/download PDF
49. Finding knowledgeable groups in enterprise corpora.
- Author
-
Liang, Shangsong and de Rijke, Maarten
- Published
- 2013
- Full Text
- View/download PDF
50. Personalized time-aware tweets summarization.
- Author
-
Ren, Zhaochun, Liang, Shangsong, Meij, Edgar, and de Rijke, Maarten
- Published
- 2013
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.