ACL 2015 paper online

“Learning to Explain Entity Relationships in Knowledge Graphs,” an upcoming ACL 2015 paper by Nikos Voskarides, Edgar Meij, Manos Tsagkias, Maarten de Rijke and Wouter Weerkamp, is available online now.

In the paper we study the problem of explaining relationships between pairs of knowledge graph entities with human-readable descriptions. Our method extracts and enriches sentences that refer to an entity pair from a corpus and ranks the sentences according to how well they describe the relationship between the entities. We model this task as a learning to rank problem for sentences and employ a rich set of features. When evaluated on a large set of manually annotated sentences, we find that our method significantly improves over state-of-the-art baseline models.

SIGIR 2015 contributions online

Our contributions to SIGIR 2015 are online now:

  • Aleksandr Chuklin, Ilya Markov, and Maarten de Rijke. An introduction to click models for web search. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{chuklin-introduction-2015,
    Author = {Chuklin, Aleksandr and Markov, Ilya and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-26 22:20:46 +0000},
    Date-Modified = {2015-05-26 22:21:49 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {An introduction to click models for web search},
    Year = {2015}}
  • Aleksandr Chuklin, Ilya Markov, and Maarten de Rijke. Advanced click models and their applications to IR. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{chuklin-advanced-2015,
    Author = {Chuklin, Aleksandr and Markov, Ilya and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-26 04:59:04 +0000},
    Date-Modified = {2015-05-26 05:00:33 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Advanced click models and their applications to IR},
    Year = {2015}}
  • David van Dijk, Manos Tsagkias, and Maarten de Rijke. Early detection of topical expertise in community question answering. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{vandijk-early-2015,
    Author = {van Dijk, David and Tsagkias, Manos and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 10:06:46 +0000},
    Date-Modified = {2015-05-25 10:07:41 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Early detection of topical expertise in community question answering},
    Year = {2015}}
  • Artem Grotov, Shimon Whiteson, and Maarten de Rijke. Bayesian ranker comparison based on historical user interactions. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{grotov-bayesian-2015,
    Author = {Grotov, Artem and Whiteson, Shimon and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 09:48:01 +0000},
    Date-Modified = {2015-05-25 09:49:01 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Bayesian ranker comparison based on historical user interactions},
    Year = {2015}}
  • Jiyin He, Marc Bron, Arjen P. de Vries, Leif Azzopardi, and Maarten de Rijke. Untangling result list refinement and ranking quality: A model for evaluation and prediction. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{he-untangling-2015,
    Author = {He, Jiyin and Bron, Marc and de Vries, Arjen P. and Azzopardi, Leif and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 09:51:35 +0000},
    Date-Modified = {2015-05-26 22:07:34 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Untangling result list refinement and ranking quality: A model for evaluation and prediction},
    Year = {2015}}
  • Daan Odijk, Edgar Meij, Isaac Sijaranamual, and Maarten de Rijke. Dynamic query modeling for related content finding. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{odijk-dynamic-2015,
    Author = {Odijk, Daan and Meij, Edgar and Sijaranamual, Isaac and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 09:59:37 +0000},
    Date-Modified = {2015-05-25 10:00:35 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Dynamic query modeling for related content finding},
    Year = {2015}}
  • Ridho Reinanda, Edgar Meij, and Maarten de Rijke. Mining, ranking and recommending entity aspects. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{reinanda-mining-2015,
    Author = {Reinanda, Ridho and Meij, Edgar and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 09:57:33 +0000},
    Date-Modified = {2015-05-25 09:58:26 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Mining, ranking and recommending entity aspects},
    Year = {2015}}
  • Zhaochun Ren and Maarten de Rijke. Summarizing contrastive themes via hierarchical non-parametric processes. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{ren-summarizing-2015,
    Author = {Ren, Zhaochun and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 09:55:59 +0000},
    Date-Modified = {2015-05-25 09:56:43 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Summarizing contrastive themes via hierarchical non-parametric processes},
    Year = {2015}}
  • Anne Schuth, Robert-Jan Bruintjes, Fritjof Büttner, Joost van Doorn, Carla Groenland, Harrie Oosterhuis, Cong-Nguyen Tran, Bas Veeling, Jos van der Velde, Roger Wechsler, David Woudenberg, and Maarten de Rijke. Probabilistic Multileave for Online Retrieval Evaluation. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{schuth-probabilistic-2015,
    Author = {Schuth, Anne and Bruintjes, Robert-Jan and B{\"u}ttner, Fritjof and van Doorn, Joost and Groenland, Carla and Oosterhuis, Harrie and Tran, Cong-Nguyen and Veeling, Bas and van der Velde, Jos and Wechsler, Roger and Woudenberg, David and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 10:01:11 +0000},
    Date-Modified = {2015-05-25 10:03:54 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Probabilistic Multileave for Online Retrieval Evaluation},
    Year = {2015}}
  • Damiano Spina, Maria-Hendrike Peetz, and Maarten de Rijke. Active learning for entity filtering in microblog streams. In SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval. ACM, August 2015. Bibtex, PDF
    @inproceedings{spina-active-2015,
    Author = {Spina, Damiano and Peetz, Maria-Hendrike and de Rijke, Maarten},
    Booktitle = {SIGIR 2015: 38th international ACM SIGIR conference on Research and development in information retrieval},
    Date-Added = {2015-05-25 10:07:48 +0000},
    Date-Modified = {2015-05-25 10:08:45 +0000},
    Month = {August},
    Publisher = {ACM},
    Title = {Active learning for entity filtering in microblog streams},
    Year = {2015}}

DESI VI paper on semantic search for e-discovery online

“Who is Involved? Semantic Search for E-Discovery,” a synthesis of some of our recent e-discovery related work, by David van Dijk, David Graus, Zhaochun Ren, Hans Henseler and Maarten de Rijke will be presented at the ICAIL 2015 Workshop on Using Machine Learning and Other Advanced Techniques to Address Legal Problems in E-Discovery and Information Governance (DESI VI Workshop). It is available online now.

E-discovery projects typically start with an assessment of the collected electronic data in order to estimate the risk to prosecute or defend a legal case. This is not a review task but is appropriately called early case assessment, which is better known as exploratory search in the information retrieval community. This paper first describes text mining method- ologies that can be used for enhancing exploratory search. Based on these ideas we present a semantic search dashboard that includes entities that are relevant to investigators such as who knew who, what, where and when. We describe how this dashboard can be powered by results from our ongoing research in the “Semantic Search for E-Discovery” project on topic detection and clustering, semantic enrichment of user profiles, email recipient recommendation, expert finding and identity extraction from digital forensic evidence.

SIGIR 2015 tutorials on click models

Aleksandr Chuklin, Ilya Markov and I will be teaching an introductory and advanced tutorial on click models for web search at SIGIR 2015, on August 10, 2015.

The tutorial is based on a forthcoming book on click models for web search. Participants will have access to the book, slides, as well as code used for demo sessions during the tutorial. The advanced part of the tutorial will also feature a guest speaker who will talk about developing new click models.

We’ll announce more details as soon as we can.

Now playing: Jamie xx — Far Nearer

ICWSM 2015 paper on determining the presence of political parties in social circles online

“Determining the Presence of Political Parties in Social Circles” by Christophe Van Gysel, Bart Goethals and Maarten de Rijke is available online.

In the paper, we derive the political climate of the social circles of Twitter users using a weakly-supervised approach. By applying random walks over a sub-sample of Twitter’s social graph we infer a distribution indicating the presence of eight Flemish political parties in users’ social circles in the months before the 2014 elections. The graph structure is induced through a combination of connection and retweet features and combines information of over a million tweets and 14 million follower connections. We solely exploit the social graph structure and do not rely on tweet content. For validation we compare the affiliation of politically active Twitter users with the most-influential party in their network. On a validation set of around 700 politically active individuals we achieve F1 scores of 0:85 and greater. We asked the Twitter community to evaluate our classification performance. More than half of the 2 258 users who responded reported a score higher than 60 out of 100.

CfP: 1st Workshop on User Modeling in Heterogeneous Search Environments (HetUM 2015) in conjunction with CIKM 2015

1st Workshop on User Modeling in Heterogeneous Search Environments (HetUM 2015) in conjunction with CIKM 2015
CALL FOR PAPERS
https://sites.google.com/site/hetum2015/
19 October 2015, Melbourne, Australia

IMPORTANT DATES

Regular paper submission: 19 June 2015
Special track for re-submissions of CIKM papers: 8 July 2015
Notification of acceptance: 23 July 2015
Camera ready: 7 August 2015
Workshop: 19 October 2015

OVERVIEW
When users interact with information retrieval (IR) systems, they leave rich implicit feedback in the form of clicks, mouse movements, etc. This feedback contains valuable information about users and about IR systems. Analyzing and interpreting user interactions and modeling user search behavior has become an important research direction. It enables us to better understand users, perform user simulations, improve search algorithms and build quality metrics.

(more…)

We’re hiring: Fully funded PhD student and two postdocs

We’re looking for three strong candidates for a fully funded PhD student position in information retrieval, a three-year postdoc position in information retrieval, and a three-year postdoc position in media studies. This is a collaborative project, called MediaNow, between the Informatics Institute and Department of Media Studies of the University of Amsterdam and the Netherlands Institute for Sound and Vision. You can find out more about the project, plus links to the advertisements etc., at http://medianow.eu. The deadline for applications is April 12, 2015. Interviews are scheduled for May 1, 2015.

Fully funded PhD position in machine learning for information retrieval

We’re looking for a strong candidate for a fully funded four-year PhD position on a collaborative project with Microsoft Research Cambridge. The research will focus on the development of new algorithms for leveraging data reuse in order to efficiently evaluate and optimize the behavior of information retrieval systems. See this page for the advertisement, further requirements, and conditions. The deadline for applications is March 22, 2015.