Searcharxiv⌕ Search

arXiv subjects

Maarten de Rijke

Publications and source records attributed to Maarten de Rijke.

At least 163 records · Page 9Linked to original sources
arXiv2023

MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering

Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in a relational database or web page. Single table questions do not involve common table operations such as set operations, Cartesian products (joins), or nested queries. Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answering questions over multiple tables. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers. To enable effective training, we build a pre-training dataset comprising of 132,645 SQL queries and tabular answers. Further, we evaluate the generated tables by introducing table-specific metrics of varying strictness assessing various levels of granularity of the table structure. MultiTabQA outperforms state-of-the-art single table QA models adapted to a multi-table QA setting by finetuning on three datasets: Spider, Atis and GeoQuery.

cs.CL↗
arXiv2023

Query Performance Prediction: From Ad-hoc to Conversational Search

Query performance prediction (QPP) is a core task in information retrieval. The QPP task is to predict the retrieval quality of a search system for a query without relevance judgments. Research has shown the effectiveness and usefulness of QPP for ad-hoc search. Recent years have witnessed considerable progress in conversational search (CS). Effective QPP could help a CS system to decide an appropriate action to be taken at the next turn. Despite its potential, QPP for CS has been little studied. We address this research gap by reproducing and studying the effectiveness of existing QPP methods in the context of CS. While the task of passage retrieval remains the same in the two settings, a user query in CS depends on the conversational history, introducing novel QPP challenges. In particular, we seek to explore to what extent findings from QPP methods for ad-hoc search generalize to three CS settings: (i) estimating the retrieval quality of different query rewriting-based retrieval methods, (ii) estimating the retrieval quality of a conversational dense retrieval method, and (iii) estimating the retrieval quality for top ranks vs. deeper-ranked lists. Our findings can be summarized as follows: (i) supervised QPP methods distinctly outperform unsupervised counterparts only when a large-scale training set is available; (ii) point-wise supervised QPP methods outperform their list-wise counterparts in most cases; and (iii) retrieval score-based unsupervised QPP methods show high effectiveness in assessing the conversational dense retrieval method, ConvDR.

cs.IR↗
arXiv2023

Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment

Recommender systems that learn from implicit feedback often use large volumes of a single type of implicit user feedback, such as clicks, to enhance the prediction of sparse target behavior such as purchases. Using multiple types of implicit user feedback for such target behavior prediction purposes is still an open question. Existing studies that attempted to learn from multiple types of user behavior often fail to: (i) learn universal and accurate user preferences from different behavioral data distributions, and (ii) overcome the noise and bias in observed implicit user feedback. To address the above problems, we propose multi-behavior alignment (MBA), a novel recommendation framework that learns from implicit feedback by using multiple types of behavioral data. We conjecture that multiple types of behavior from the same user (e.g., clicks and purchases) should reflect similar preferences of that user. To this end, we regard the underlying universal user preferences as a latent variable. The variable is inferred by maximizing the likelihood of multiple observed behavioral data distributions and, at the same time, minimizing the Kullback-Leibler divergence (KL-divergence) between user models learned from auxiliary behavior (such as clicks or views) and the target behavior separately. MBA infers universal user preferences from multi-behavior data and performs data denoising to enable effective knowledge transfer. We conduct experiments on three datasets, including a dataset collected from an operational e-commerce platform. Empirical results demonstrate the effectiveness of our proposed method in utilizing multiple types of behavioral data to enhance the prediction of the target behavior.

cs.IR↗
arXiv2023

On the Impact of Outlier Bias on User Clicks

User interaction data is an important source of supervision in counterfactual learning to rank (CLTR). Such data suffers from presentation bias. Much work in unbiased learning to rank (ULTR) focuses on position bias, i.e., items at higher ranks are more likely to be examined and clicked. Inter-item dependencies also influence examination probabilities, with outlier items in a ranking as an important example. Outliers are defined as items that observably deviate from the rest and therefore stand out in the ranking. In this paper, we identify and introduce the bias brought about by outlier items: users tend to click more on outlier items and their close neighbors. To this end, we first conduct a controlled experiment to study the effect of outliers on user clicks. Next, to examine whether the findings from our controlled experiment generalize to naturalistic situations, we explore real-world click logs from an e-commerce platform. We show that, in both scenarios, users tend to click significantly more on outlier items than on non-outlier items in the same rankings. We show that this tendency holds for all positions, i.e., for any specific position, an item receives more interactions when presented as an outlier as opposed to a non-outlier item. We conclude from our analysis that the effect of outliers on clicks is a type of bias that should be addressed in ULTR. We therefore propose an outlier-aware click model that accounts for both outlier and position bias, called outlier-aware position-based model ( OPBM). We estimate click propensities based on OPBM ; through extensive experiments performed on both real-world e-commerce data and semi-synthetic data, we verify the effectiveness of our outlier-aware click model. Our results show the superiority of OPBM against baselines in terms of ranking performance and true relevance estimation.

cs.IR↗
arXiv2023

Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models

Neural ranking models (NRMs) have attracted considerable attention in information retrieval. Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks, which might be leveraged by black-hat search engine optimization practitioners. Recently, adversarial attacks against NRMs have been explored in the paired attack setting, generating an adversarial perturbation to a target document for a specific query. In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic. We define both static and dynamic settings for the task and focus on decision-based black-box attacks. We propose a novel framework to improve topic-oriented attack performance based on a surrogate ranking model. The attack problem is formalized as a Markov decision process (MDP) and addressed using reinforcement learning. Specifically, a topic-oriented reward function guides the policy to find a successful adversarial example that can be promoted in rankings to as many queries as possible in a group. Experimental results demonstrate that the proposed framework can significantly outperform existing attack strategies, and we conclude by re-iterating that there exist potential risks for applying NRMs in the real world.

cs.IR↗
arXiv2023

A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning

Knowledge-intensive language tasks (KILTs) benefit from retrieving high-quality relevant contexts from large external knowledge corpora. Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task. But a task-specific retriever usually has poor generalization ability to new domains and tasks, and it may be costly to deploy a variety of specialised retrievers in practice. We propose a unified generative retriever (UGR) that combines task-specific effectiveness with robust performance over different retrieval tasks in KILTs. To achieve this goal, we make two major contributions: (i) To unify different retrieval tasks into a single generative form, we introduce an n-gram-based identifier for relevant contexts at different levels of granularity in KILTs. And (ii) to address different retrieval tasks with a single model, we employ a prompt learning strategy and investigate three methods to design prompt tokens for each task. In this way, the proposed UGR model can not only share common knowledge across tasks for better generalization, but also perform different retrieval tasks effectively by distinguishing task-specific characteristics. We train UGR on a heterogeneous set of retrieval corpora with well-designed prompts in a supervised and multi-task fashion. Experimental results on the KILT benchmark demonstrate the effectiveness of UGR on in-domain datasets, out-of-domain datasets, and unseen tasks.

cs.IR↗
arXiv2023

Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization

Counterfactual learning to rank (CLTR) relies on exposure-based inverse propensity scoring (IPS), a LTR-specific adaptation of IPS to correct for position bias. While IPS can provide unbiased and consistent estimates, it often suffers from high variance. Especially when little click data is available, this variance can cause CLTR to learn sub-optimal ranking behavior. Consequently, existing CLTR methods bring significant risks with them, as naively deploying their models can result in very negative user experiences. We introduce a novel risk-aware CLTR method with theoretical guarantees for safe deployment. We apply a novel exposure-based concept of risk regularization to IPS estimation for LTR. Our risk regularization penalizes the mismatch between the ranking behavior of a learned model and a given safe model. Thereby, it ensures that learned ranking models stay close to a trusted model, when there is high uncertainty in IPS estimation, which greatly reduces the risks during deployment. Our experimental results demonstrate the efficacy of our proposed method, which is effective at avoiding initial periods of bad performance when little data is available, while also maintaining high performance at convergence. For the CLTR field, our novel exposure-based risk minimization method enables practitioners to adopt CLTR methods in a safer manner that mitigates many of the risks attached to previous methods.

cs.IR↗
arXiv2023

A Self-Correcting Sequential Recommender

Sequential recommendations aim to capture users' preferences from their historical interactions so as to predict the next item that they will interact with. Sequential recommendation methods usually assume that all items in a user's historical interactions reflect her/his preferences and transition patterns between items. However, real-world interaction data is imperfect in that (i) users might erroneously click on items, i.e., so-called misclicks on irrelevant items, and (ii) users might miss items, i.e., unexposed relevant items due to inaccurate recommendations. To tackle the two issues listed above, we propose STEAM, a Self-correcTing sEquentiAl recoMmender. STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items. It then uses the corrected item sequence to train a recommender and make the next item prediction.We design an item-wise corrector that can adaptively select one type of operation for each item in the sequence. The operation types are 'keep', 'delete' and 'insert.' In order to train the item-wise corrector without requiring additional labeling, we design two self-supervised learning mechanisms: (i) deletion correction (i.e., deleting randomly inserted items), and (ii) insertion correction (i.e., predicting randomly deleted items). We integrate the corrector with the recommender by sharing the encoder and by training them jointly. We conduct extensive experiments on three real-world datasets and the experimental results demonstrate that STEAM outperforms state-of-the-art sequential recommendation baselines. Our in-depth analyses confirm that STEAM benefits from learning to correct the raw item sequences.

cs.IR↗
arXiv2023

Learning to Tokenize for Generative Retrieval

Conventional document retrieval techniques are mainly based on the index-retrieve paradigm. It is challenging to optimize pipelines based on this paradigm in an end-to-end manner. As an alternative, generative retrieval represents documents as identifiers (docid) and retrieves documents by generating docids, enabling end-to-end modeling of document retrieval tasks. However, it is an open question how one should define the document identifiers. Current approaches to the task of defining document identifiers rely on fixed rule-based docids, such as the title of a document or the result of clustering BERT embeddings, which often fail to capture the complete semantic information of a document. We propose GenRet, a document tokenization learning method to address the challenge of defining document identifiers for generative retrieval. GenRet learns to tokenize documents into short discrete representations (i.e., docids) via a discrete auto-encoding approach. Three components are included in GenRet: (i) a tokenization model that produces docids for documents; (ii) a reconstruction model that learns to reconstruct a document based on a docid; and (iii) a sequence-to-sequence retrieval model that generates relevant document identifiers directly for a designated query. By using an auto-encoding framework, GenRet learns semantic docids in a fully end-to-end manner. We also develop a progressive training scheme to capture the autoregressive nature of docids and to stabilize training. We conduct experiments on the NQ320K, MS MARCO, and BEIR datasets to assess the effectiveness of GenRet. GenRet establishes the new state-of-the-art on the NQ320K dataset. Especially, compared to generative retrieval baselines, GenRet can achieve significant improvements on the unseen documents. GenRet also outperforms comparable baselines on MS MARCO and BEIR, demonstrating the method's generalizability.

cs.IR↗
arXiv2023

A Next Basket Recommendation Reality Check

The goal of a next basket recommendation (NBR) system is to recommend items for the next basket for a user, based on the sequence of their prior baskets. Recently, a number of methods with complex modules have been proposed that claim state-of-the-art performance. They rarely look into the predicted basket and just provide intuitive reasons for the observed improvements, e.g., better representation, capturing intentions or relations, etc. We provide a novel angle on the evaluation of next basket recommendation methods, centered on the distinction between repetition and exploration: the next basket is typically composed of previously consumed items (i.e., repeat items) and new items (i.e, explore items). We propose a set of metrics that measure the repeat/explore ratio and performance of NBR models. Using these new metrics, we analyze state-of-the-art NBR models. The results of our analysis help to clarify the extent of the actual progress achieved by existing NBR methods as well as the underlying reasons for the improvements. Overall, our work sheds light on the evaluation problem of NBR and provides useful insights into the model design for this task.

cs.IR↗
arXiv2023

Meta Matrix Factorization for Federated Rating Predictions

Federated recommender systems have distinct advantages in terms of privacy protection over traditional recommender systems that are centralized at a data center. However, previous work on federated recommender systems does not fully consider the limitations of storage, RAM, energy and communication bandwidth in a mobile environment. The scales of the models proposed are too large to be easily run on mobile devices. And existing federated recommender systems need to fine-tune recommendation models on each device, making it hard to effectively exploit collaborative filtering information among users/devices. Our goal in this paper is to design a novel federated learning framework for rating prediction (RP) for mobile environments. We introduce a federated matrix factorization (MF) framework, named meta matrix factorization (MetaMF). Given a user, we first obtain a collaborative vector by collecting useful information with a collaborative memory module. Then, we employ a meta recommender module to generate private item embeddings and a RP model based on the collaborative vector in the server. To address the challenge of generating a large number of high-dimensional item embeddings, we devise a rise-dimensional generation strategy that first generates a low-dimensional item embedding matrix and a rise-dimensional matrix, and then multiply them to obtain high-dimensional embeddings. We use the generated model to produce private RPs for the given user on her device. MetaMF shows a high capacity even with a small RP model, which can adapt to the limitations of a mobile environment. We conduct extensive experiments on four benchmark datasets to compare MetaMF with existing MF methods and find that MetaMF can achieve competitive performance. Moreover, we find MetaMF achieves higher RP performance over existing federated methods by better exploiting collaborative filtering among users/devices.

cs.IR↗
arXiv2023

Modeling Sequential Recommendation as Missing Information Imputation

Side information is being used extensively to improve the effectiveness of sequential recommendation models. It is said to help capture the transition patterns among items. Most previous work on sequential recommendation that uses side information models item IDs and side information separately, which may fail to fully model the relation between the items and their side information. Moreover, in real-world systems, not all values of item feature fields are available. This hurts the performance of models that rely on side information. Existing methods tend to neglect the context of missing item feature fields, and fill them with generic or special values, e.g., unknown, which might lead to sub-optimal performance. To address the limitation of sequential recommenders with side information, we define a way to fuse side information and alleviate the problem of missing side information by proposing a unified task, namely the missing information imputation (MII), which randomly masks some feature fields in a given sequence of items, including item IDs, and then forces a predictive model to recover them. By considering the next item as a missing feature field, sequential recommendation can be formulated as a special case of MII. We propose a sequential recommendation model, called missing information imputation recommender (MIIR), that builds on the idea of MII and simultaneously imputes missing item feature values and predicts the next item. We devise a dense fusion self-attention (DFSA) mechanism for MIIR to capture all pairwise relations between items and their side information. Empirical studies on three benchmark datasets demonstrate that MIIR, supervised by MII, achieves a significantly better sequential recommendation performance than state-of-the-art baselines.

cs.IR↗
arXiv2023

Generative Slate Recommendation with Reinforcement Learning

Recent research has employed reinforcement learning (RL) algorithms to optimize long-term user engagement in recommender systems, thereby avoiding common pitfalls such as user boredom and filter bubbles. They capture the sequential and interactive nature of recommendations, and thus offer a principled way to deal with long-term rewards and avoid myopic behaviors. However, RL approaches are intractable in the slate recommendation scenario - where a list of items is recommended at each interaction turn - due to the combinatorial action space. In that setting, an action corresponds to a slate that may contain any combination of items. While previous work has proposed well-chosen decompositions of actions so as to ensure tractability, these rely on restrictive and sometimes unrealistic assumptions. Instead, in this work we propose to encode slates in a continuous, low-dimensional latent space learned by a variational auto-encoder. Then, the RL agent selects continuous actions in this latent space, which are ultimately decoded into the corresponding slates. By doing so, we are able to (i) relax assumptions required by previous work, and (ii) improve the quality of the action selection by modeling full slates instead of independent items, in particular by enabling diversity. Our experiments performed on a wide array of simulated environments confirm the effectiveness of our generative modeling of slates over baselines in practical scenarios where the restrictive assumptions underlying the baselines are lifted. Our findings suggest that representation learning using generative models is a promising direction towards generalizable RL-based slate recommendation.

cs.IR↗
arXiv2023

Feature-Level Debiased Natural Language Understanding

Natural language understanding (NLU) models often rely on dataset biases rather than intended task-relevant features to achieve high performance on specific datasets. As a result, these models perform poorly on datasets outside the training distribution. Some recent studies address this issue by reducing the weights of biased samples during the training process. However, these methods still encode biased latent features in representations and neglect the dynamic nature of bias, which hinders model prediction. We propose an NLU debiasing method, named debiasing contrastive learning (DCT), to simultaneously alleviate the above problems based on contrastive learning. We devise a debiasing, positive sampling strategy to mitigate biased latent features by selecting the least similar biased positive samples. We also propose a dynamic negative sampling strategy to capture the dynamic influence of biases by employing a bias-only model to dynamically select the most similar biased negative samples. We conduct experiments on three NLU benchmark datasets. Experimental results show that DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance. We also verify that DCT can reduce biased latent features from the model's representation.

cs.CL↗
arXiv2023

Offline Evaluation for Reinforcement Learning-based Recommendation: A Critical Issue and Some Alternatives

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.

cs.IR↗
arXiv2022

Contrastive Learning Reduces Hallucination in Conversations

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking statements that are irrelevant or factually incorrect. To address this problem, we propose a contrastive learning scheme, named MixCL. A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs, and thus reduce their hallucination in conversations. We also examine negative sampling strategies of retrieved hard negatives and model-generated negatives. We conduct experiments on Wizard-of-Wikipedia, a public, open-domain knowledge-grounded dialogue benchmark, and assess the effectiveness of MixCL. MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality. We show that MixCL achieves comparable performance to state-of-the-art KB-based approaches while enjoying notable advantages in terms of efficiency and scalability.

cs.CL↗
arXiv2022

sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification

Multiclass multilabel classification is the task of attributing multiple labels to examples via predictions. Current models formulate a reduction of the multilabel setting into either multiple binary classifications or multiclass classification, allowing for the use of existing loss functions (sigmoid, cross-entropy, logistic, etc.). Multilabel classification reductions do not accommodate for the prediction of varying numbers of labels per example and the underlying losses are distant estimates of the performance metrics. We propose a loss function, sigmoidF1, which is an approximation of the F1 score that (1) is smooth and tractable for stochastic gradient descent, (2) naturally approximates a multilabel metric, and (3) estimates label propensities and label counts. We show that any confusion matrix metric can be formulated with a smooth surrogate. We evaluate the proposed loss function on text and image datasets, and with a variety of metrics, to account for the complexity of multilabel classification evaluation. sigmoidF1 outperforms other loss functions on one text and two image datasets and several metrics. These results show the effectiveness of using inference-time metrics as loss functions for non-trivial classification problems like multilabel classification.

cs.LG↗
arXiv2022

RADio -- Rank-Aware Divergence Metrics to Measure Normative Diversity in News Recommendations

In traditional recommender system literature, diversity is often seen as the opposite of similarity, and typically defined as the distance between identified topics, categories or word models. However, this is not expressive of the social science's interpretation of diversity, which accounts for a news organization's norms and values and which we here refer to as normative diversity. We introduce RADio, a versatile metrics framework to evaluate recommendations according to these normative goals. RADio introduces a rank-aware Jensen Shannon (JS) divergence. This combination accounts for (i) a user's decreasing propensity to observe items further down a list and (ii) full distributional shifts as opposed to point estimates. We evaluate RADio's ability to reflect five normative concepts in news recommendations on the Microsoft News Dataset and six (neural) recommendation algorithms, with the help of our metadata enrichment pipeline. We find that RADio provides insightful estimates that can potentially be used to inform news recommender system design.

cs.IR↗