Weakly-supervised Contextualization of Knowledge Graph Facts

Knowledge graphs (KGs) model facts about the world; they consist of nodes (entities such as companies and people) that are connected by edges (relations such as founderOf ). Facts encoded in KGs are frequently used by search applications to augment result pages. When presenting a KG fact to the user, providing other facts that are pertinent to that main fact can enrich the user experience and support exploratory information needs. KG fact contextualization is the task of augmenting a given KG fact with additional and useful KG facts. The task is challenging because of the large size of KGs; discovering other relevant facts even in a small neighborhood of the given fact results in an enormous amount of candidates. We introduce a neural fact contextualization method (NFCM) to address the KG fact contextualization task. NFCM first generates a set of candidate facts in the neighborhood of a given fact and then ranks the candidate facts using a supervised learning to rank model. The ranking model combines features that we automatically learn from data and that represent the query-candidate facts with a set of hand-crafted features we devised or adjusted for this task. In order to obtain the annotations required to train the learning to rank model at scale, we generate training data automatically using distant supervision on a large entity-tagged text corpus. We show that ranking functions learned on this data are effective at contextualizing KG facts. Evaluation using human assessors shows that it significantly outperforms several competitive baselines.

  • [PDF] [DOI] N. Voskarides, E. Meij, R. Reinanda, A. Khaitan, M. Osborne, G. Stefanoni, P. Kambadur, and M. de Rijke, “Weakly-supervised contextualization of knowledge graph facts,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, New York, NY, USA, 2018, p. 765–774.
    [Bibtex]
    @inproceedings{SIGIR:2018:Voskarides,
    Acmid = {3210031},
    Address = {New York, NY, USA},
    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 = {The 41st {International ACM SIGIR Conference on Research} \& {Development in Information Retrieval}},
    Date-Added = {2018-07-26 18:23:41 +0000},
    Date-Modified = {2018-09-27 21:55:17 +0100},
    Doi = {10.1145/3209978.3210031},
    Isbn = {978-1-4503-5657-2},
    Keywords = {distant supervision, fact contextualization, knowledge graphs},
    Location = {Ann Arbor, MI, USA},
    Numpages = {10},
    Pages = {765--774},
    Publisher = {ACM},
    Series = {SIGIR '18},
    Title = {Weakly-supervised Contextualization of Knowledge Graph Facts},
    Url = {http://doi.acm.org/10.1145/3209978.3210031},
    Year = {2018},
    Bdsk-Url-1 = {http://doi.acm.org/10.1145/3209978.3210031},
    Bdsk-Url-2 = {https://doi.org/10.1145/3209978.3210031}}

Utilizing Knowledge Graphs for Text-Centric Information Retrieval

The past decade has witnessed the emergence of several publicly available and proprietary knowledge graphs (KGs). The depth and breadth of content in these KGs made them not only rich sources of structured knowledge by themselves, but also valuable resources for search systems. A surge of recent developments in entity linking and entity retrieval methods gave rise to a new line of research that aims at utilizing KGs for text-centric retrieval applications. This tutorial is the first to summarize and disseminate the progress in this emerging area to industry practitioners and researchers.

  • [PDF] [DOI] L. Dietz, A. Kotov, and E. Meij, “Utilizing knowledge graphs for text-centric information retrieval,” in The 41st international acm sigir conference on research & development in information retrieval, New York, NY, USA, 2018, p. 1387–1390.
    [Bibtex]
    @inproceedings{SIGIR:2018:Dietz-Tut,
    Acmid = {3210187},
    Address = {New York, NY, USA},
    Author = {Dietz, Laura and Kotov, Alexander and Meij, Edgar},
    Booktitle = {The 41st International ACM SIGIR Conference on Research \& Development in Information Retrieval},
    Date-Added = {2018-07-26 18:24:31 +0000},
    Date-Modified = {2018-07-26 18:31:50 +0000},
    Doi = {10.1145/3209978.3210187},
    Isbn = {978-1-4503-5657-2},
    Keywords = {entity linking, entity retrieval, information retrieval, knowledge graphs},
    Location = {Ann Arbor, MI, USA},
    Numpages = {4},
    Pages = {1387--1390},
    Publisher = {ACM},
    Series = {SIGIR '18},
    Title = {Utilizing Knowledge Graphs for Text-Centric Information Retrieval},
    Url = {http://doi.acm.org/10.1145/3209978.3210187},
    Year = {2018},
    Bdsk-Url-1 = {http://doi.acm.org/10.1145/3209978.3210187},
    Bdsk-Url-2 = {https://doi.org/10.1145/3209978.3210187}}

Overview of The First Workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis (KG4IR)

Knowledge graphs have been used throughout the history of information retrieval for a variety of tasks. Advances in knowledge acquisition and alignment technology in the last few years have given rise to a body of new approaches for utilizing knowledge graphs in text retrieval tasks. This report presents the motivation, output, and outlook of the first workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis which was co-located with SIGIR 2017 in Tokyo, Japan. We aim to assess where we stand today, what future directions are, and which preconditions could lead to further performance increases.

  • [PDF] [DOI] L. Dietz, C. Xiong, and E. Meij, “Overview of the first workshop on knowledge graphs and semantics for text retrieval and analysis (kg4ir),” Sigir forum, vol. 51, iss. 3, p. 139–144, 2018.
    [Bibtex]
    @article{Forum:2018:Dietz,
    Acmid = {3190601},
    Address = {New York, NY, USA},
    Author = {Dietz, Laura and Xiong, Chenyan and Meij, Edgar},
    Date-Added = {2018-07-26 18:22:37 +0000},
    Date-Modified = {2018-07-26 18:22:48 +0000},
    Doi = {10.1145/3190580.3190601},
    Issn = {0163-5840},
    Issue_Date = {December 2017},
    Journal = {SIGIR Forum},
    Month = 2,
    Number = {3},
    Numpages = {6},
    Pages = {139--144},
    Publisher = {ACM},
    Title = {Overview of The First Workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis (KG4IR)},
    Url = {http://doi.acm.org/10.1145/3190580.3190601},
    Volume = {51},
    Year = {2018},
    Bdsk-Url-1 = {http://doi.acm.org/10.1145/3190580.3190601},
    Bdsk-Url-2 = {https://doi.org/10.1145/3190580.3190601}}

The First Workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis (KG4IR)

Knowledge graphs have been used throughout the history of information retrieval for a variety of tasks. Advances in knowledge acquisition and alignment technology in the last few years have given rise to a body of new approaches for utilizing knowledge graphs in text retrieval tasks. This report presents the motivation, output, and outlook of the first workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis which was co-located with SIGIR 2017 in Tokyo, Japan. We aim to assess where we stand today, what future directions are, and which preconditions could lead to further performance increases. See https://kg4ir.github.io/ for more info.

  • [PDF] [DOI] L. Dietz, C. Xiong, and E. Meij, “The first workshop on knowledge graphs and semantics for text retrieval and analysis (kg4ir),” in Proceedings of the 40th international acm sigir conference on research and development in information retrieval, New York, NY, USA, 2017, p. 1427–1428.
    [Bibtex]
    @inproceedings{SIGIR:2017:Dietz,
    Acmid = {3084371},
    Address = {New York, NY, USA},
    Author = {Dietz, Laura and Xiong, Chenyan and Meij, Edgar},
    Booktitle = {Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval},
    Date-Added = {2018-07-26 18:17:39 +0000},
    Date-Modified = {2018-07-26 18:17:51 +0000},
    Doi = {10.1145/3077136.3084371},
    Isbn = {978-1-4503-5022-8},
    Keywords = {entities, information retrieval, knowledge graphs},
    Location = {Shinjuku, Tokyo, Japan},
    Numpages = {2},
    Pages = {1427--1428},
    Publisher = {ACM},
    Series = {SIGIR '17},
    Title = {The First Workshop on Knowledge Graphs and Semantics for Text Retrieval and Analysis (KG4IR)},
    Url = {http://doi.acm.org/10.1145/3077136.3084371},
    Year = {2017},
    Bdsk-Url-1 = {http://doi.acm.org/10.1145/3077136.3084371},
    Bdsk-Url-2 = {https://doi.org/10.1145/3077136.3084371}}
ECIR 2017

Generating descriptions of entity relationships

Large-scale knowledge graphs (KGs) store relationships between entities that are increasingly being used to improve the user experience in search applications. The structured nature of the data in KGs is typically not suitable to show to an end user and applications that utilize KGs therefore benefit from human-readable textual descriptions of KG relationships. We present a method that automatically generates textual descriptions of entity relationships by combining textual and KG information. Our method creates sentence templates for a particular relationship and then generates a textual description of a relationship instance by selecting the best template and filling it with appropriate entities. Experimental results show that a supervised variation of our method outperforms other variations as it captures the semantic similarity between a relationship instance and a template best, whilst providing more contextual information.

  • [PDF] N. Voskarides, E. Meij, and M. de Rijke, “Generating descriptions of entity relationships,” in Ecir 2017: 39th european conference on information retrieval, 2017.
    [Bibtex]
    @inproceedings{ECIR:2017:voskarides,
    Author = {Voskarides, Nikos and Meij, Edgar and de Rijke, Maarten},
    Booktitle = {ECIR 2017: 39th European Conference on Information Retrieval},
    Date-Added = {2017-01-10 21:27:37 +0000},
    Date-Modified = {2017-01-10 21:27:58 +0000},
    Month = {April},
    Publisher = {Springer},
    Series = {LNCS},
    Title = {Generating descriptions of entity relationships},
    Year = {2017}}
CIKM 2016

Document Filtering for Long-tail Entities

Filtering relevant documents with respect to entities is an essential task in the context of knowledge base construction and maintenance. It entails processing a time-ordered stream of documents that might be relevant to an entity in order to select only those that contain vital information. State-of-the-art approaches to document filtering for popular entities are entity-dependent: they rely on and are also trained on the specifics of differentiating features for each specific entity. Moreover, these approaches tend to use so-called extrinsic information such as Wikipedia page views and related entities which is typically only available only for popular head entities. Entity-dependent approaches based on such signals are therefore ill-suited as filtering methods for long-tail entities. Continue reading “Document Filtering for Long-tail Entities” »

Learning to Explain Entity Relationships in Knowledge Graphs

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.

  • [PDF] N. Voskarides, E. Meij, M. Tsagkias, M. de Rijke, and W. Weerkamp, “Learning to explain entity relationships in knowledge graphs,” in Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 1: long papers), 2015, p. 564–574.
    [Bibtex]
    @inproceedings{ACL:2015:Voskarides,
    Author = {Voskarides, Nikos and Meij, Edgar and Tsagkias, Manos and de Rijke, Maarten and Weerkamp, Wouter},
    Booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
    Date-Added = {2015-08-06 13:08:02 +0000},
    Date-Modified = {2015-08-06 13:08:14 +0000},
    Location = {Beijing, China},
    Pages = {564--574},
    Publisher = {Association for Computational Linguistics},
    Title = {Learning to Explain Entity Relationships in Knowledge Graphs},
    Url = {http://aclweb.org/anthology/P15-1055},
    Year = {2015},
    Bdsk-Url-1 = {http://aclweb.org/anthology/P15-1055}}

Entity Linking and Retrieval for Semantic Search (WSDM 2014)

This morning, we presented the last edition of our tutorial series on Entity Linking and Retrieval, entitled “Entity Linking and Retrieval for Semantic Search” (with Krisztian Balog and Daan Odijk) at WSDM 2014! This final edition of the series builds upon our earlier tutorials at WWW 2013 and SIGIR 2013. The focus of this edition lies on the practical applications of Entity Linking and Retrieval, in particular for semantic search: more and more search engine users are expecting direct answers to their information needs (rather than just documents). Semantic search and its recent applications are enabling search engines to organize their wealth of information around entities. Entity linking and retrieval is at the basis of these developments, providing the building stones for organizing the web of entities.

This tutorial aims to cover all facets of semantic search from a unified point of view and connect real-world applications with results from scientific publications. We provide a comprehensive overview of entity linking and retrieval in the context of semantic search and thoroughly explore techniques for query understanding, entity-based retrieval and ranking on unstructured text, structured knowledge repositories, and a mixture of these. We point out the connections between published approaches and applications, and provide hands-on examples on real-world use cases and datasets.

As before, all our tutorial materials are available for free online, see http://ejmeij.github.io/entity-linking-and-retrieval-tutorial/.