Maarten de Rijke

Information retrieval

WWW 2019 paper on evaluation metrics for web image search online

Grid-based Evaluation Metrics for Web Image Search by Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Maarten de Rijke, Yunqiu Shao, Zixin Ye, Min Zhang, and Shaoping Ma is online now at this location.

Compared to general web search engines, web image search engines display results in a different way. In web image search, results are typically placed in a grid-based manner rather than a sequential result list. In this scenario, users can view results not only in a vertical direction but also in a horizontal direction. Moreover, pagination is usually not (explicitly) supported on image search search engine result pages (SERPs), and users can view results by scrolling down without having to click a “next page” button. These differences lead to different interaction mechanisms and user behavior patterns, which, in turn, create challenges to evaluation metrics that have originally been developed for general web search. While considerable effort has been invested in developing evaluation metrics for general web search, there have been relatively less effort to construct grid-based evaluation metrics.

To inform the development of grid-based evaluation metrics for web image search, we conduct a comprehensive analysis of user behavior so as to uncover how users allocate their attention in a grid-based web image search result interface. We obtain three findings: (1) “Middle bias”: Confirming previous studies, we find that image results in the horizontal middle positions may receive more attention from users than those in the leftmost or rightmost positions. (2) “Slower decay”: Unlike web search, users’ attention does not decrease monotonically or dramatically with the rank position in image search, especially within a row. (3) “Row skipping”: Users may ignore particular rows and directly jump to results at some distance. Motivated by these observations, we propose correspond- ing user behavior assumptions to capture users’ search interaction processes and evaluate their search performance. We show how to derive new metrics from these assumptions and demonstrate that they can be adopted to revise traditional list-based metrics like Discounted Cumulative Gain (DCG) and Rank-Biased Precision (RBP). To show the effectiveness of the proposed grid-based metrics, we compare them against a number of list-based metrics in terms of their correlation with user satisfaction. Our experimental results show that the proposed grid-based evaluation metrics better reflect user satisfaction in web image search.

The paper will be presented at The Web Conference 2019.

WWW 2019 paper on outfit recommendation online

Improving Outfit Recommendation with Co-supervision of Fashion Generation by Yujie Lin, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, and Maarten de Rijke is now available at this location.

The task of fashion recommendation includes two main challenges:visual understanding and visual matching. Visual understanding aims to extract effective visual features. Visual matching aims to model a human notion of compatibility to compute a match between fashion items. Most previous studies rely on recommendation loss alone to guide visual understanding and matching. Although the features captured by these methods describe basic characteristics (e.g., color, texture, shape) of the input items, they are not directly related to the visual signals of the output items (to be recommended). This is problematic because the aesthetic characteristics (e.g., style, design), based on which we can directly infer the output items, are lacking. Features are learned under the recommendation loss alone, where the supervision signal is simply whether the given two items are matched or not.

To address this problem, we propose a neural co-supervision learning framework, called the FAshion Recommendation Machine (FARM). FARM improves visual understanding by incorporating the supervision of generation loss, which we hypothesize to be able to better encode aesthetic information. FARM enhances visual matching by introducing a novel layer-to-layer matching mechanism to fuse aesthetic information more effectively, and meanwhile avoiding paying too much attention to the generation quality and ignoring the recommendation performance.

Extensive experiments on two publicly available datasets show that FARM outperforms state-of-the-art models on outfit recom- mendation, in terms of AUC and MRR. Detailed analyses of gener- ated and recommended items demonstrate that FARM can encode better features and generate high quality images as references to improve recommendation performance.

The paper will be presented at the The Web Conference 2019.

WWW 2019 paper on diversity of dialogue response generation online

Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss by Shaojie Jiang, Pengjie Ren, Christof Monz, and Maarten de Rijke is online now at this location.

Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic responses, which make the conversation less interesting. In this paper, we address the low-diversity problem by investigating its connection with model over-confidence reflected in predicted distributions. Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses. We then propose a Frequency-Aware Cross-Entropy (FACE) loss function that improves over the CE loss function by incorporating a weighting mechanism conditioned on token frequency. Extensive experiments on benchmark datasets show that the FACE loss function is able to substantially improve the diversity of existing state-of-the-art Seq2Seq response generation methods, in terms of both automatic and human evaluations.

The paper will be presented at The Web Conference 2019.

WWW 2019 paper on visual learning to rank online

ViTOR: Learning to Rank Webpages Based on Visual Features by Bram van den Akker, Ilya Markov, and Maarten de Rijke is available online now at this location.

The visual appearance of a webpage carries valuable information about the page’s quality and can be used to improve the performance of learning to rank (LTR). We introduce the Visual learning TO Rank (ViTOR) model that integrates state-of-the-art visual features extraction methods: (i) transfer learning from a pre-trained image classification model, and (ii) synthetic saliency heat maps generated from webpage snapshots. Since there is currently no public dataset for the task of LTR with visual features, we also introduce and release the ViTOR dataset, containing visually rich and diverse webpages. The ViTOR dataset consists of visual snapshots, non-visual features and relevance judgments for ClueWeb12 webpages and TREC Web Track queries. We experiment with the proposed ViTOR model on the ViTOR dataset and show that it significantly improves the performance of LTR with visual features.

The paper will be presented at The Web Conference 2019.

ECIR 2019 paper on information-seeking dialogues online

QRFA: A data-driven model of information-seeking dialogues by Svitlana Vakulenko, Kate Revoredo, Claudio Di Ciccio, and Maarten de Rijke is available online now at this location.

Understanding the structure of interaction processes helps us to improve information-seeking dialogue systems. Analyzing an interaction process boils down to discovering patterns in sequences of alternating utterances exchanged between a user and an agent. Process mining techniques have been successfully applied to analyze structured event logs, discovering the underlying process models or evaluating whether the observed behavior is in conformance with the known process. In this paper, we apply process mining techniques to discover patterns in conversational transcripts and extract a new model of information-seeking dialogues, QRFA, for Query, Request, Feedback, Answer. Our results are grounded in an empirical evaluation across multiple conversational datasets from different domains, which was never attempted before. We show that the QRFA model better reflects conversation flows observed in real information-seeking conversations than models proposed previously. Moreover, QRFA allows us to identify malfunctioning in dialogue system transcripts as deviations from the expected conversation flow described by the model via conformance analysis.

The paper will be presented at ECIR 2019.

ECIR 2019 paper on online learning to rank online

Optimizing ranking models in an online setting by Harrie Oosterhuis and Maarten de Rijke is available online now at this location.

Online Learning to Rank (OLTR) methods optimize ranking models by directly interacting with users, which allows them to be very efficient and responsive. All OLTR methods introduced during the past decade have extended on the original OLTR method: Dueling Bandit Gradient Descent (DBGD). Recently, a fundamentally different approach was introduced with the Pairwise Differen- tiable Gradient Descent (PDGD) algorithm. To date the only comparisons of the two approaches are limited to simulations with cascading click models and low levels of noise. The main outcome so far is that PDGD converges at higher levels of performance and learns considerably faster than DBGD-based methods. However, the PDGD algorithm assumes cascading user behavior, potentially giving it an unfair advantage. Furthermore, the robustness of both methods to high levels of noise has not been investigated. Therefore, it is unclear whether the reported advantages of PDGD over DBGD generalize to different experimental conditions. In this paper, we investigate whether the previous conclusions about the PDGD and DBGD comparison generalize from ideal to worst-case circumstances. We do so in two ways. First, we compare the theoretical properties of PDGD and DBGD, by taking a critical look at previously proven properties in the context of ranking. Second, we estimate an upper and lower bound on the performance of methods by simulating both ideal user behavior and extremely difficult behavior, i.e., almost-random non-cascading user models. Our findings show that the theoretical bounds of DBGD do not apply to any common ranking model and, furthermore, that the performance of DBGD is substantially worse than PDGD in both ideal and worst-case circumstances. These results reproduce previously published findings about the relative performance of PDGD vs. DBGD and generalize them to extremely noisy and non-cascading circumstances.

The paper will be presented at ECIR 2019.

WSDM 2019 paper on off-policy evaluation online

When people change their mind: Off-policy evaluation in non-stationary recommendation environments by Rolf Jagerman, Ilya Markov, and Maarten de Rijke is online now at this location.

We consider the novel problem of evaluating a recommendation policy offline in environments where the reward signal is non- stationary. Non-stationarity appears in many Information Retrieval (IR) applications such as recommendation and advertising, but its effect on off-policy evaluation has not been studied at all. We are the first to address this issue. First, we analyze standard off-policy estimators in non-stationary environments and show both theoretically and experimentally that their bias grows with time. Then, we propose new off-policy estimators with moving averages and show that their bias is independent of time and can be bounded. Furthermore, we provide a method to trade-off bias and variance in a principled way to get an off-policy estimator that works well in both non-stationary and stationary environments. We experiment on publicly available recommendation datasets and show that our newly proposed moving average estimators accurately capture changes in non-stationary environments, while standard off-policy estimators fail to do so.

The paper will be presented at WSDM 2019.

WSDM 2019 paper on open-domain question answering online

Learning to transform, combine, and reason in open-domain question answering by Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, and Maarten de Rijke is online now at this location.

Users seek direct answers to complex questions from large open-domain knowledge sources like the Web. Open-domain question answering has become a critical task to be solved for building systems that help address users’ complex information needs. Most open-domain question answering systems use a search engine to retrieve a set of candidate documents, select one or a few of them as context, and then apply reading comprehension models to ex- tract answers. Some questions, however, require taking a broader context into account, e.g., by considering low-ranked documents that are not immediately relevant, combining information from multiple documents, and reasoning over multiple facts from these documents to infer the answer. In this paper, we propose a model based on the Transformer architecture that is able to efficiently operate over a larger set of candidate documents by effectively combining the evidence from these documents during multiple steps of reasoning, while it is robust against noise from low-ranked non-relevant documents included in the set. We use our proposed model, called TraCRNet, on two public open-domain question answering datasets, SearchQA and Quasar-T, and achieve results that meet or exceed the state-of-the-art.

The paper will be presented at WSDM 2019.

AAAI 2019 paper on repeat aware recommendation online

RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation by Pengjie Ren, Zhumin Chen, Jing Li, Zhaochun Ren, Jun Ma, and Maarten de Rijke is online now at this location.

Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. Repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), where the same item is re-consumed repeatedly over time. However, no previous studies have emphasized repeat consumption with neural networks. An effective neural approach is needed to decide when to perform repeat recommendation. In this paper, we incorporate a repeat-explore mechanism into neural networks and propose a new model, called RepeatNet, with an encoder-decoder structure. RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user’s history and recommends them at the right time. We report on extensive experiments on three benchmark datasets. RepeatNet outperforms state-of-the-art baselines on all three datasets in terms of MRR and Recall. Furthermore, as the dataset size and the repeat ratio increase, the improvements of RepeatNet over the baselines also increase, which demonstrates its advantage in handling repeat recommendation scenarios.

The paper will be presented at AAAI 2019.

AAAI 2019 paper on dialogue generation online

Dialogue generation: From imitation learning to inverse reinforcement learning by Ziming Li, Julia Kiseleva, and Maarten de Rijke is online now at this location.

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the gen- erator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a re- cently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator train- ing. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.

The paper will be presented at AAAI 2019.

« Older posts

© 2019 Maarten de Rijke

Theme by Anders NorenUp ↑