Category: Publications (page 2 of 8)

CIKM 2018 paper on Differentiable Unbiased Online Learning to Rank online

Differentiable Unbiased Online Learning to Rank by Harrie Oosterhuis and Maarten de Rijke is available online now at this location.

Online Learning to Rank (OLTR) methods optimize rankers based on user interactions. State-of-the-art OLTR methods are built specifically for linear models. Their approaches do not extend well to non-linear models such as neural networks. We introduce an entirely novel approach to OLTR that constructs a weighted differentiable pairwise loss after each interaction: Pairwise Differentiable Gradient Descent (PDGD). PDGD breaks away from the traditional approach that relies on interleaving or multileaving and extensive sampling of models to estimate gradients. Instead, its gradient is based on inferring preferences between document pairs from user clicks and can optimize any differentiable model. We prove that the gradient of PDGD is unbiased w.r.t. user document pair preferences. Our experiments on the largest publicly available Learning to Rank (LTR) datasets show considerable and significant improvements under all levels of interaction noise. PDGD outperforms existing OLTR methods both in terms of learning speed as well as final convergence. Furthermore, unlike previous OLTR methods, PDGD also allows for non-linear models to be optimized effectively. Our results show that using a neural network leads to even better performance at convergence than a linear model. In summary, PDGD is an efficient and unbiased OLTR approach that provides a better user experience than previously possible.

The paper will be presented at CIKM 2018 in October 2018.

CIKM 2018 paper on Calibration: A Simple Way to Improve Click Models online

Calibration: A Simple Way to Improve Click Models by Alexey Borisov, Julia Kiseleva, Ilya Markov, and Maarten de Rijke is available online now at this location.

In the paper we show that click models trained with suboptimal hyperparameters suffer from the issue of bad calibration. This means that their predicted click probabilities do not agree with the observed proportions of clicks in the held-out data. To repair this discrepancy, we adapt a non-parametric calibration method called isotonic regression. Our experimental results showthat isotonic regression significantly improves click models trained with suboptimal hyperparameters in terms of perplexity, and that it makes click models less sensitive to the choice of hyperparameters. Interestingly, the relative ranking of existing click models in terms of their predictive performance changes depending on whether or not their predictions are calibrated. Therefore, we advocate that calibration becomes a mandatory part of the click model evaluation protocol.

The paper will be presented at CIKM 2018 in October 2018.

CIKM 2018 paper on Attentive Encoder-based Extractive Text Summarization online

Attentive Encoder-based Extractive Text Summarization by Chong Feng, Fei Cai, Honghui Chen, and Maarten de Rijke is available online now at this location.

In previous work on text summarization, encoder-decoder architectures and attention mechanisms have both been widely used. Attention-based encoder-decoder approaches typically focus on taking the sentences preceding a given sentence in a document into account for document representation, failing to capture the relationships between a sentence and sentences that follow it in a document in the encoder. We propose an attentive encoder-based summarization (AES) model to generate article summaries. AES can generate a rich document representation by considering both the global information of a document and the relationships of sentences in the document. A unidirectional recurrent neural network (RNN) and a bidirectional RNN are considered to construct the encoders, giving rise to unidirectional attentive encoder-based summarization (Uni-AES) and bidirectional attentive encoder-based summarization (Bi-AES), respectively. Our experimental results show that Bi-AES outperforms Uni-AES. We obtain substantial improvements over a relevant start-of-the-art baseline.

The paper will be presented at CIKM 2018 in October 2018.

CIKM 2018 paper on Integrating Text Matching and Product Substitutability within Product Search online

Mix ‘n Match: Integrating Text Matching and Product Substitutability within Product Search by Christophe Van Gysel, Maarten de Rijke, and Evangelos Kanoulas is available online now at this location.

Two products are substitutes if both can satisfy the same consumer need. Intrinsic incorporation of product substitutability—where substitutability is integrated within latent vector space models—is in contrast to the extrinsic re-ranking of result lists. The fusion of text matching and product substitutability objectives allows latent vector space models to mix and match regularities contained within text descriptions and substitution relations. We introduce a method for intrinsically incorporating product substitutability within latent vector space models for product search that are estimated using gradient descent; it integrates flawlessly with state-of-the-art vector space models. We compare our method to existing methods for incorporating structural entity relations, where product substitutability is incorporated extrinsically by re-ranking. Our method outperforms the best extrinsic method on four benchmarks. We investigate the effect of different levels of text matching and product similarity objectives, and provide an analysis of the effect of incorporating product substitutability on product search ranking diversity. Incorporating product substitutability information improves search relevance at the cost of diversity.

The paper will be presented at CIKM 2018 in October 2018.

RecSys 2018 paper on preference elicitation as an optimization problem online

The following RecSys 2018 paper on preference elicitation as an optimization problem is online now:

  • Anna Sepliarskaia, Julia Kiseleva, Filip Radlinski, and Maarten de Rijke. Preference elicitation as an optimization problem. In RecSys 2018: The ACM Conference on Recommender Systems, page 172–180. ACM, October 2018. Bibtex, PDF
    @inproceedings{sepliarskaia-preference-2018,
    Author = {Sepliarskaia, Anna and Kiseleva, Julia and Radlinski, Filip and de Rijke, Maarten},
    Booktitle = {RecSys 2018: The ACM Conference on Recommender Systems},
    Date-Added = {2018-07-10 09:40:05 +0000},
    Date-Modified = {2018-10-27 09:29:19 +0200},
    Month = {October},
    Pages = {172--180},
    Publisher = {ACM},
    Title = {Preference elicitation as an optimization problem},
    Year = {2018}}

The new user coldstart problem arises when a recommender system does not yet have any information about a user. A common solution to it is to generate a profile by asking the user to rate a number of items. Which items are selected determines the quality of the recommendations made, and thus has been studied extensively. We propose a new elicitation method to generate a static preference questionnaire (SPQ) that poses relative preference questions to the user. Using a latent factor model, we show that SPQ improves personalized recommendations by choosing a minimal and diverse set of questions. We are the first to rigorously prove which optimization task should be solved to select each question in static questionnaires. Our theoretical results are confirmed by extensive experimentation. We test the performance of SPQ on two real-world datasets, under two experimental conditions: simulated, when users behave according to a latent factor model (LFM), and real, in which only real user judgments are revealed as the system asks questions. We show that SPQ reduces the necessary length of a questionnaire by up to a factor of three compared to state-of-the-art preference elicitation methods. Moreover, solving the right optimization task, SPQ also performs better than baselines with dynamically generated questions.

ISWC 2018 paper on measuring semantic coherence of a conversation online

The following ISWC 2018 paper on measuring semantic coherence of a conversation is online now:

  • Svitlana Vakulenko, Maarten de Rijke, Michael Cochez, Vadim Savenkov, and Axel Polleres. Measuring semantic coherence of a conversation. In ISWC 2018: 17th International Semantic Web Conference, page 634–651. Springer, October 2018. Bibtex, PDF
    @inproceedings{vakulenko-measuring-2018,
    Author = {Vakulenko, Svitlana and de Rijke, Maarten and Cochez, Michael and Savenkov, Vadim and Polleres, Axel},
    Booktitle = {ISWC 2018: 17th International Semantic Web Conference},
    Date-Added = {2018-05-26 04:41:16 +0000},
    Date-Modified = {2018-10-27 09:32:14 +0200},
    Month = {October},
    Pages = {634--651},
    Publisher = {Springer},
    Title = {Measuring semantic coherence of a conversation},
    Year = {2018}}

Conversational systems have become increasingly popular as a way for people to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during a conversation. We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus.

Now on arXiv: Explainable Fashion Recommendation with Joint Outfit Matching and Comment Generation

Yujie Lin, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, and I published “Explainable Fashion Recommendation with Joint Outfit Matching and Comment Generation” on arXiv. Most previous work on fashion recommendation focuses on designing visual features to enhance recommendations. Existing work neglects user comments of fashion items, which have been proved effective in generating explanations along with better recommendation results. We propose a novel neural network framework, neural fashion recommendation (NFR), that simultaneously provides fashion recommendations and generates abstractive comments. NFR consists of two parts: outfit matching and comment generation. For outfit matching, we propose a convolutional neural network with a mutual attention mechanism to extract visual features of outfits. The visual features are then decoded into a rating score for the matching prediction. For abstractive comment generation, we propose a gated recurrent neural network with a cross-modality attention mechanism to transform visual features into a concise sentence. The two parts are jointly trained based on a multi-task learning framework in an end-to-end back-propagation paradigm. Extensive experiments conducted on an existing dataset and a collected real-world dataset show NFR achieves significant improvements over state-of-the-art baselines for fashion recommendation. Meanwhile, our generated comments achieve impressive ROUGE and BLEU scores in comparison to human-written comments. The generated comments can be regarded as explanations for the recommendation results. We release the dataset and code to facilitate future research. You can find the paper here.

Three more papers on arXiv

We’ve just put three more papers on arXiv.

Earlier in June, Sapna Negi, Paul Buitelaar, and I put “Open Domain Suggestion Mining: Problem Definition and Datasets” on arXiv. In the paper we propose a formal definition for the task of suggestion mining in the context of a wide range of open domain applications. Human perception of the term suggestion is subjective and this effects the preparation of hand labeled datasets for the task of suggestion mining. Existing work either lacks a formal problem definition and annotation procedure, or provides domain and application specific definitions. Moreover, many previously used manually labeled datasets remain proprietary. We first present an annotation study, and based on our observations propose a formal task definition and annotation procedure for creating benchmark datasets for suggestion mining. With this study, we also provide publicly available labeled datasets for suggestion mining in multiple domains. You can find the paper here.

Then, in mid June, Branislav Kveton, Chang Li, Tor Lattimore, Ilya Markov, Csaba Szepesvari, Masrour Zoghi, and I put “BubbleRank: Safe Online Learning to Rerank” on arXiv. We study the problem of online learning to re-rank, where users provide feedback to improve the quality of displayed lists. Learning to rank has been traditionally studied in two settings. In the offline setting, rankers are typically learned from relevance labels of judges. These approaches have become the industry standard. However, they lack exploration, and thus are limited by the information content of offline data. In the online setting, an algorithm can propose a list and learn from the feedback on it in a sequential fashion. Bandit algorithms developed for this setting actively experiment, and in this way overcome the biases of offline data. But they also tend to ignore offline data, which results in a high initial cost of exploration. We propose BubbleRank, a bandit algorithm for re-ranking that combines the strengths of both settings. The algorithm starts with an initial base list and improves it gradually by swapping higher-ranked less attractive items for lower-ranked more attractive items. We prove an upper bound on the n-step regret of BubbleRank that degrades gracefully with the quality of the initial base list. Our theoretical findings are supported by extensive numerical experiments on a large real-world click dataset. The paper can be found here.

And, third, Svitlana Vakulenko, Michael Cochez, Vadim Savenkov, Axel Polleres, and I put “Measuring Semantic Coherence of a Conversation” on arXiv. Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during a conversation. We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus. The paper can be found here.

SIGIR 2018 papers online

The SIGIR 2018 papers that I contributed to are online now:

  • Alexey Borisov, Martijn Wardenaar, Ilya Markov, and Maarten de Rijke. A click sequence model for web search. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 45–54. ACM, July 2018. Bibtex, PDF
    @inproceedings{borisov-click-2018,
    Author = {Borisov, Alexey and Wardenaar, Martijn and Markov, Ilya and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-12 05:45:13 +0000},
    Date-Modified = {2018-08-25 17:13:02 +0200},
    Month = {July},
    Pages = {45--54},
    Publisher = {ACM},
    Title = {A click sequence model for web search},
    Year = {2018}}
  • Wanyu Chen, Fei Cai, Honghui Chen, and Maarten de Rijke. Attention-based hierarchical neural query suggestion. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 1093–1096. ACM, July 2018. Bibtex, PDF
    @inproceedings{chen-attention-based-2018,
    Author = {Chen, Wanyu and Cai, Fei and Chen, Honghui and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-11 23:31:34 +0000},
    Date-Modified = {2018-08-25 17:14:43 +0200},
    Month = {July},
    Pages = {1093--1096},
    Publisher = {ACM},
    Title = {Attention-based hierarchical neural query suggestion},
    Year = {2018}}
  • Paul Groth, Laura Koesten, Philipp Mayr, Maarten de Rijke, and Elena Simperl. DATA:SEARCH’18 – Searching data on the web. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, pages 1419-1422. ACM, July 2018. Bibtex, PDF
    @inproceedings{groth-data-2018,
    Author = {Groth, Paul and Koesten, Laura and Mayr, Philipp and de Rijke, Maarten and Simperl, Elena},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-05-05 10:58:53 +0000},
    Date-Modified = {2018-08-25 17:17:04 +0200},
    Month = {July},
    Pages = {1419-1422},
    Publisher = {ACM},
    Title = {DATA:SEARCH'18 -- Searching data on the web},
    Year = {2018}}
  • Harrie Oosterhuis and Maarten de Rijke. Ranking for relevance and display preferences in complex presentation layouts. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 845–854. ACM, July 2018. Bibtex, PDF
    @inproceedings{oosterhuis-ranking-2018,
    Author = {Oosterhuis, Harrie and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-12 05:41:46 +0000},
    Date-Modified = {2018-08-25 17:13:58 +0200},
    Month = {July},
    Pages = {845--854},
    Publisher = {ACM},
    Title = {Ranking for relevance and display preferences in complex presentation layouts},
    Year = {2018}}
  • Zhaochun Ren, Xiangnan He, Dawei Yin, and Maarten de Rijke. Information discovery in e-commerce. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 1379–1382. ACM, July 2018. Bibtex, PDF
    @inproceedings{ren-information-2018,
    Author = {Ren, Zhaochun and He, Xiangnan and Yin, Dawei and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-05-05 10:53:55 +0000},
    Date-Modified = {2018-08-25 17:16:43 +0200},
    Month = {July},
    Pages = {1379--1382},
    Publisher = {ACM},
    Title = {Information discovery in e-commerce},
    Year = {2018}}
  • Christophe Van Gysel and Maarten de Rijke. Pytrec_eval: An extremely fast Python interface to trec_eval. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 873–876. ACM, July 2018. Bibtex, PDF
    @inproceedings{vangysel-pytrec-2018,
    Author = {Van Gysel, Christophe and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-11 22:02:31 +0000},
    Date-Modified = {2018-08-25 17:14:19 +0200},
    Month = {July},
    Pages = {873--876},
    Publisher = {ACM},
    Title = {Pytrec\_eval: An extremely fast Python interface to trec\_eval},
    Year = {2018}}
  • Nikos Voskarides, Edgar Meij, Ridho Reinanda, Abhinav Khaitan, Miles Osborne, Giorgio Stefanoni, Kambadur Prabhanjan, and Maarten de Rijke. Weakly-supervised contextualization of knowledge graph facts. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 765–774. ACM, July 2018. Bibtex, PDF
    @inproceedings{voskarides-weakly-supervised-2018,
    Author = {Voskarides, Nikos and Meij, Edgar and Reinanda, Ridho and Khaitan, Abhinav and Osborne, Miles and Stefanoni, Giorgio and Kambadur Prabhanjan and de Rijke, Maarten},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-12 05:42:50 +0000},
    Date-Modified = {2018-08-25 17:13:40 +0200},
    Month = {July},
    Pages = {765--774},
    Publisher = {ACM},
    Title = {Weakly-supervised contextualization of knowledge graph facts},
    Year = {2018}}
  • Xiaohui Xie, Jiaxin Mao, Maarten de Rijke, Ruizhe Zhang, Min Zhang, and Shaoping Ma. Constructing an interaction behavior model for web image search. In SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval, page 425–434. ACM, July 2018. Bibtex, PDF
    @inproceedings{xie-constructing-2018,
    Author = {Xie, Xiaohui and Mao, Jiaxin and de Rijke, Maarten and Zhang, Ruizhe and Zhang, Min and Ma, Shaoping},
    Booktitle = {SIGIR 2018: 41st international ACM SIGIR conference on Research and Development in Information Retrieval},
    Date-Added = {2018-04-11 22:25:25 +0000},
    Date-Modified = {2018-08-25 17:13:23 +0200},
    Month = {July},
    Pages = {425--434},
    Publisher = {ACM},
    Title = {Constructing an interaction behavior model for web image search},
    Year = {2018}}

Now on arXiv: Finding influential training samples for gradient boosted decision trees

Boris Sharchilev, Yury Ustinovsky, Pavel Serdyukov, and I have released a new pre-print on “finding influential training samples for gradient boosted decision trees” on arXiv. In the paper we address the problem of finding influential training samples for a particular case of tree ensemble-based models, e.g., Random Forest (RF) or Gradient Boosted Decision Trees (GBDT). A natural way of formalizing this problem is studying how the model’s predictions change upon leave-one-out retraining, leaving out each individual training sample. Recent work has shown that, for parametric models, this analysis can be conducted in a computationally efficient way. We propose several ways of extending this framework to non-parametric GBDT ensembles under the assumption that tree structures remain fixed. Furthermore, we introduce a general scheme of obtaining further approximations to our method that balance the trade-off between performance and computational complexity. We evaluate our approaches on various experimental setups and use-case scenarios and demonstrate both the quality of our approach to finding influential training samples in comparison to the baselines and its computational efficiency. You can find the paper here.

« Older posts Newer posts »

© 2020 Maarten de Rijke

Theme by Anders NorenUp ↑