Maarten de Rijke

Information retrieval

Page 3 of 15

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.

Open Science

I’m a professor. My job description is very simple: to create new knowledge and to transfer it. To students, colleagues, and anyone else, really. To academia, industry, governments, and the rest of society. I do my job by working with a large team of very talented PhD students and postdocs from around the planet and by presenting our work as broadly as possible, to different types of audience and around the world.

Throughout my career my research has centered around the concept of information. Early on in my career I worked on representing and reasoning with information. For the past 15 years, I have focused on information retrieval – technology to connect people to information. It’s a great area to work in, the research problems are challenging, the area has global impact and attracts amazing talent from around the world. Access to information is a human right and information retrieval is the basis of a critical technology for providing that access.

In a few days, the main conference in my research area, SIGIR, the ACM international conference on research and development in information retrieval, will take place in Ann Arbor, Michigan, US. It promises to be a really good edition. The community is expanding, experimenting with new ideas, new directions, new formats. And developments in machine learning, in conversational agents, and related to societal implications of the technology that we develop are creating new energy and excitement. My team and I are scheduled to present a large number of papers, both full papers and short papers, we are also organizing a workshop, presenting a tutorial, I’m on a panel on future directions in information retrieval, in a lunch session on diversity, a student lunch session, in editorial board meetings for journals for which I have editorial responsibility, and, of course, there will be a large number of exciting high-quality paper presentations by colleagues. To top it off, the conference takes place on a university campus, which I much prefer as a conference location over a hotel. This promises to be a fantastic edition of SIGIR.

But I won’t be going.

In November 2017 I visited Iran. I gave two talks. A strategy talk on our experience in Amsterdam in bringing together data scientists from diverse institutions with diverse disciplinary backgrounds. And a science talk on the interface between data science and information retrieval. A two day trip with two talks plus the opportunity to meet some fantastic students. Of course, the trip to Iran meant that I was no longer authorized to travel to the US under the ESTA visa waiver program. I knew this in advance and so I applied for a DS-160 nonimmigrant visa on December 2, 2017, a few days after my return from Iran. Unfortunately, my visa application was refused. Further information from my end was requested (my CV), which I submitted in mid December 2017. Seven months have passed since I started the process. I have had to skip the WSDM 2018 conference, which took place in Los Angeles, and the FAT*2018 conference, which took place in New York. The latest status update of my visa application as of a few days ago was “no news yet, unfortunately,” which means that I will have to skip SIGIR 2018 as well.

What’s next?

There is no point in lowering myself to the standards of a policy that I oppose and to stop submitting papers to conferences that are being held in the US. Halting the conversation is never the answer. It’s neither helpful nor effective in promoting what is essential to my job as a professor. The pursuit of science “requires freedom of movement, association, expression and communication for scientists”. With a Dutch passport, I’m one of the lucky few: even after having my ESTA privilege revoked, I can still travel visa-free to 185 destinations. The majority of the PhD students and postdocs in my team are from China, Iran and Russia, all of which are countries ranked lower or even much lower on the Passport Index than the Netherlands. I regularly see how they face impenetrable walls in their education or career simply because of the country on their passport.

Scientific progress and human and environmental well-being are our collective responsibility. Open exchange of people and ideas are key to fulfilling such collective responsibilities. If you have the opportunity, please help to facilitate more open exchange, of talent and of knowledge. If you are in academia, share your publications, share your teaching materials, share your code, share your data, share your time. Support and encourage visits to your institution, based on scientific excellence only. If you’re from a country that’s ranked high on the Passport Index, go and visit other institutions around the planet and share your expertise. I believe that every bit helps. For my part, I’ll try to raise 100K Euro per year, over the next 10 years, to bring an information retrieval researcher to my university for a 12-month visiting position. Scientific excellence will be the entry ticket, not the country in someone’s passport.

[1] Justin Zobel. What We Talk About When We Talk About Information Retrieval. SIGIR Forum 51(3):18-26, 2017. PDF
[2] ICSU, Freedom, Responsibility and Universality of Science, 2014. PDF
[3] Henley & Partners, Passport Index, 2018. URL

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.

Five more vacancies for fully funded PhD students

We just opened five more vacancies for PhD students. The general area is AI for Retail, and the positions are part of the new AIRLab. Areas range from recommendation to federated search and conversational search to replenishment. Deadline: July 16, 2018. Please visit this page for all the details.

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.

Another IR vacancy

We just opened another vacancy, for a PhD student to work on dataset search. Come and join us to work in the area of AI & IR, together with great colleagues at Elsevier, VU Amsterdam and KNAW. See https://t.co/um5ldIQAZg for more details.

« Older posts Newer posts »

© 2019 Maarten de Rijke

Theme by Anders NorenUp ↑