Artificial intelligence & Information retrieval

Category: Uncategorized (Page 1 of 3)

Materials for tutorial on conversational recommendation

Materials to accompany the RecSys 2021 tutorial on conversational recommendation presented by Chongming Gao, Wenqiang Lei and myself are available now:

  • Slides: Chongming Gao, Wenqiang Lei, Maarten de Rijke. RecSys 2021 Tutorial on Conversational Recommendation: Formulation, Methods, and Evaluation, Fifteenth ACM Conference on Recommender Systems (RecSys 2021). PDF
  • Survey: Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, and Tat-Seng Chua. Advances and Challenges in Conversational Recommender Systems: A Survey. AI Open, 2:100–126, July 2021. PDF

New publications

New publications that are scheduled to appear this month:

  • Wanyu Chen, Pengjie Ren, Fei Cai, Fei Sun, and Maarten de Rijke. Improving End-to-End Sequential Recommendations with Intent-aware Diversification. In CIKM 2020: 29th ACM International Conference on Information and Knowledge Management, page 175–184. ACM, October 2020. Bibtex, PDF
    @inproceedings{chen-2020-improving,
    author = {Chen, Wanyu and Ren, Pengjie and Cai, Fei and Sun, Fei and de Rijke, Maarten},
    booktitle = {CIKM 2020: 29th ACM International Conference on Information and Knowledge Management},
    date-added = {2020-07-17 12:46:55 +0200},
    date-modified = {2020-10-20 07:31:14 +0200},
    month = {October},
    pages = {175--184},
    publisher = {ACM},
    title = {Improving End-to-End Sequential Recommendations with Intent-aware Diversification},
    year = {2020}}
  • Xiangsheng Li, Maarten de Rijke, Yiqun Liu, Jiaxin Mao, Weizhi Ma, Min Zhang, and Shaoping Ma. Learning Better Representations for Neural Information Retrieval with Graph Information. In CIKM 2020: 29th ACM International Conference on Information and Knowledge Management, page 795–804. ACM, October 2020. Bibtex, PDF
    @inproceedings{li-2020-learning,
    author = {Li, Xiangsheng and de Rijke, Maarten and Liu, Yiqun and Mao, Jiaxin and Ma, Weizhi and Zhang, Min and Ma, Shaoping},
    booktitle = {CIKM 2020: 29th ACM International Conference on Information and Knowledge Management},
    date-added = {2020-07-17 12:41:46 +0200},
    date-modified = {2020-10-20 07:31:34 +0200},
    month = {October},
    pages = {795--804},
    publisher = {ACM},
    title = {Learning Better Representations for Neural Information Retrieval with Graph Information},
    year = {2020}}
  • Zhiqiang Pan, Fei Cai, Wanyu Chen, Honghui Chen, and Maarten de Rijke. Star Graph Neural Networks for Session-based Recommendation. In CIKM 2020: 29th ACM International Conference on Information and Knowledge Management, page 1195–1204. ACM, October 2020. Bibtex, PDF
    @inproceedings{pan-2020-star,
    author = {Pan, Zhiqiang and Cai, Fei and Chen, Wanyu and Chen, Honghui and de Rijke, Maarten},
    booktitle = {CIKM 2020: 29th ACM International Conference on Information and Knowledge Management},
    date-added = {2020-07-17 12:44:13 +0200},
    date-modified = {2020-10-20 07:31:54 +0200},
    month = {October},
    pages = {1195--1204},
    publisher = {ACM},
    title = {Star Graph Neural Networks for Session-based Recommendation},
    year = {2020}}
  • Ridho Reinanda, Edgar Meij, and Maarten de Rijke. Knowledge Graphs: An Information Retrieval Perspective. Foundations and Trends in Information Retrieval, 14(4):289–444, October 2020. Bibtex, PDF
    @article{reinanda-2020-knowledge,
    author = {Reinanda, Ridho and Meij, Edgar and de Rijke, Maarten},
    date-added = {2018-07-20 09:10:39 +0000},
    date-modified = {2020-10-16 22:32:43 +0200},
    journal = {Foundations and Trends in Information Retrieval},
    month = {October},
    number = {4},
    pages = {289--444},
    title = {Knowledge Graphs: An Information Retrieval Perspective},
    volume = {14},
    year = {2020}}
  • Ali Vardasbi, Harrie Oosterhuis, and Maarten de Rijke. When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank. In CIKM 2020: 29th ACM International Conference on Information and Knowledge Management, page 1475–1484. ACM, October 2020. Bibtex, PDF
    @inproceedings{vardasbi-2020-inverse,
    author = {Vardasbi, Ali and Oosterhuis, Harrie and de Rijke, Maarten},
    booktitle = {CIKM 2020: 29th ACM International Conference on Information and Knowledge Management},
    date-added = {2020-07-17 12:38:45 +0200},
    date-modified = {2020-10-20 07:32:14 +0200},
    month = {October},
    pages = {1475--1484},
    publisher = {ACM},
    title = {When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank},
    year = {2020}}

Schiet nou toch eens op. De tijd dringt

Vandaag presenteerde de EU haar “white paper” over AI in Europa. Samenvatting van mijn commentaar:

  • Zet veel duidelijker en veel ambitieuzer in op AI-talent — daar staat of valt alles mee.
  • Waarom geeft de EU de hoop over consumentendata op? Is consumentendata nou niet precies waar je het vertrouwen wint of verliest?
  • Beleidsmakers zijn voor de kaders en regelgeving: zij moeten zich niet bemoeien met de inhoud van de AI-wetenschap en AI-innovatie — dat moet je overlaten aan wetenschappers en ondernemers.
  • Het idee van één enkel “lighthouse” als Europees AI-centrum is slecht doordacht, geld verslindend, en staat sociaal-economische impact van AI-technologie in de weg.
  • Waarom wordt er wel gesproken van een netwerk van excellentie (4 pagina’s) en een netwerk van vertrouwen (16 pagina’s!), maar niet van een netwerk van kansen en uitdagingen? Is dat niet waar het begint?
  • Bovenal: doe nu eens wat!

Zie De Volkskrant

Aan de slag!

Morgen, 8 oktober, presenteert VNO-NCW een `Nationale AI Coalitie’. Het Nederlandse bedrijfsleven steekt de komende zeven jaar ruim €1 mrd in kunstmatige intelligentie (AI). Van de overheid wordt ook een flinke bijdrage gevraagd. Het Financieele Dagblad besteedt aandacht aan de verwachte aankondigingen van deze week.


Genoeg gepraat. Genoeg gepolderd. Aan de slag.

UAI 2019 paper on safe online learning to re-rank via implicit click feedback online

BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback by Chang Li, Branislav Kveton, Tor Lattimore, Ilya Markov, Maarten de Rijke, Csaba Szepesvari, and Masrour Zoghi is online now at this location.

In the paper we study the problem of safe on-line learning to re-rank, where user feedback is used to improve the quality of displayed lists. Learning to rank has traditionally been studied in two settings. In the offline setting, rankers are typically learned from relevance labels created by judges. This approach has generally be- come standard in industrial applications of ranking, such as search. However, this approach lacks exploration and thus is limited by the information content of the offline training data. In the online setting, an algorithm can experiment with lists and learn from feedback on them in a sequential fashion. Bandit algorithms are well-suited for this setting but they tend to learn user preferences from scratch, which results in a high initial cost of exploration. This poses an additional challenge of safe exploration in ranked lists. We propose BubbleRank, a bandit algorithm for safe re-ranking that combines the strengths of both the offline and online settings. The algorithm starts with an initial base list and improves it online by gradually exchanging higher-ranked less attractive items for lower-ranked more attractive items. We prove an up- per bound on the n-step regret of BubbleRankthat degrades gracefully with the quality of the initial base list. Our theoretical findings are supported by extensive experiments on a large-scale real-world click dataset.

The paper will be presented at UAI 2019: Conference on Uncertainty in Artificial Intelligence, July 2019.

Using process mining for understanding the structure of interaction processes

Svitlana Vakulenko explains how we have recently used process mining techniques to understand the structure of interaction processes, which will in turn help us to improve information-seeking dialogue systems. We extract a new model of information-seeking dialogues, QRFA, for Query, Request, Feedback, Answer. The QRFA model better reflects conversation flows observed in real information-seeking conversations than models proposed previously. QRFA allows us to identify malfunctioning in dialogue system transcripts as deviations from the expected conversation flow described by the model via conformance analysis.

Read the full post.

Investeer in kennisbasis AI of word een toeschouwer

In een opiniestuk voor NRC Handelsblad en NRC Next beargumenteer ik dat artificiële intelligentie ons leven hoe dan ook zal veranderen en dat Nederland voor de keuze staat om vol mee te doen in de ontwikkeling van AI en het spel mee te bepalen, of om de bank te blijven zitten. Wie niet actief meedoet, heeft geen invloed – niet op het spel en al helemaal niet op de spelregels. Investeer in de AI-kennisbasis, investeer in talent. Kom van de bank!

Het hele stuk is hier te vinden.

Learning to answer questions by taking broader contexts into account

Mostafa Dehghani has posted an explanation of our recent work on TraCRNet (“tracker net”) to learn how to answer questions from multiple, possible long documents. TraCRNet uses the universal transformer and is able to go beyond understanding a set of input documents separately and combine their information in multiple steps. TraCRNet is highly parallellizable and far more robust against noisy input than previous proposals for addressing the question answering task.

See this page for the full post.

FACTS-IR Workshop @ SIGIR 2019

SIGIR 2019 will host a workshop to explore challenges in responsible information retrieval system development and deployment. The focus will be on determining actionable research agendas on five key dimensions of responsible information retrieval: fairness, accountability, confidentiality, transparency, and safety. Rather than just a mini-conference, this workshop will be an event during which participants will also be expected to work. The workshop aims to bring together a diverse set of researchers and practitioners interested in helping to develop the technical research agenda for responsible information retrieval.

The web site for the workshop is live now.

How to optimize ranking systems by directly interacting with users

Harrie Oosterhuis has written an accessible summary of our recent work on pairwise differentiable gradient descent (PDGD), an online learning to rank method that he published at CIKM 2018, with a follow-up paper to come at ECIR 2019 in April. With the introduction of the PDGD algorithm, ranking systems can now be optimized from user interactions far more effectively than previously possible. Additionally, PDGD can also optimize neural models to a greater effect, something previous methods couldn’t do. We expect that the development of ranking systems will benefit from this contribution on the long term. Not only because of improved performance, but also because the possibility to optimize more complex models opens the door to many different possibilities.

See this page for the full post.

« Older posts

© 2021 Maarten de Rijke

Theme by Anders NorenUp ↑