Actively Learning to Rank Semantic Associations for Personalized Contextual Exploration of Knowledge Graphs

Bianchi, Federico; Palmonari, Matteo; Cremaschi, Marco; Fersini, Elisabetta

doi:10.1007/978-3-319-58068-5_8

Cited by 6 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A graph-based recommendation methodology based on a personalised PageRank algorithm has been proposed in [50]. The approach in [51] allows the user to rate semantic associations represented as chains of relations to reveal interesting and unknown connections between entities for personalised recommendations.…”

Section: Text-based Semantic Data Browsersmentioning

confidence: 99%

Using knowledge anchors to facilitate user exploration of data graphs

Al-Tawil

Dimitrova

Thakker

2020

View full text Add to dashboard Cite

This paper investigates how to facilitate users' exploration through data graphs. The prime focus is on knowledge utility, i.e. increasing a user's domain knowledge while exploring a data graph, which is crucial in the vast number of user-facing semantic web applications where the users are not experts in the domain. We introduce a highly unique exploration support mechanism underpinned by the subsumption theory for meaningful learning. A core algorithmic component for operationalising the subsumption theory for meaningful learning is the automatic identification of knowledge anchors in a data graph (KADG). We present several metrics for identifying KADG which are evaluated against familiar concepts in human cognitive structures. The second key component is a subsumption algorithm that utilises KADG for generating exploration paths for knowledge expansion. The implementation of the algorithm is applied in the context of a Semantic data browser in a music domain. The resultant exploration paths are evaluated in a task-driven experimental user study compared to free data graph exploration. The findings show that exploration paths, based on subsumption and using knowledge anchors, lead to significantly higher increase in the users' conceptual knowledge and better usability than free exploration of data graphs. The work opens a new avenue in semantic data exploration which investigates the link between learning and knowledge exploration. We provide the first framework that adopts educational theories to inform data graph exploration for knowledge expansion which extends the value of exploration and enables broader applications of data graphs in systems where the end users are not experts in the specific domain.

show abstract

Section: Text-based Semantic Data Browsersmentioning

confidence: 99%

Using knowledge anchors to facilitate user exploration of data graphs

Al-Tawil

Dimitrova

Thakker

2020

View full text Add to dashboard Cite

show abstract

“…Bianchi et al [41] focus on the problem of finding the most "interesting" semantic associations by defining a ranking function, which can take into account user preferences. The approach starts from a small sample of semantic associations that are rated by the user and then use it to iteratively learn a personalized ranking function.…”

Section: Discovering Semantic Associationsmentioning

confidence: 99%

Building relatedness explanations from knowledge graphs

Pirrò

2019

View full text Add to dashboard Cite

Knowledge graphs (KGs) are a key ingredient to complement search results, discover entities and their relations and support several knowledge discovery tasks. We face the problem of building relatedness explanations, that is, graphs that can explain how a pair of entities is related in a KG. Explanations can be used in a variety of tasks; from exploratory search to query answering. We formalize the notion of explanation and present two algorithms. The first, E4D (Explanations from Data), assembles explanations starting from all paths interlinking the source and target entity in the data. The second algorithm E4S (Explanations from Schema) builds explanations focused on a specific relatedness perspective expressed by providing a predicate. E4S first generates candidate explanation patterns at the level of schema; then, it assembles explanations by proceeding to their verification in the data. Given a set of paths, found by E4D or E4S, we describe different criteria to build explanations based on information-theory, diversity and their combination. As a concrete use-case of relatedness explanations, we introduce relatedness-based KG querying, which revisits the query-by-example paradigm from the perspective of relatedness explanations. We implemented all machineries in the RECAP tool, which is based on RDF and SPARQL. We discuss an evaluation of the explanation building algorithms and a comparison of RECAP with related systems on real-world data.

show abstract

“…Semantic association ranking is to rank the semantic relationship for a given entity pair. RankSVM [10] and actively learning [2] has been proposed for personalized ranking and minimizing labels collected from the user. None of those entity summarization and semantic association work, however, incorporate a context as part of the ranking consideration.…”

Section: Related Workmentioning

confidence: 99%

“…We observed that often the same facts were chosen but in different orders. So we asked raters to assign an informative level to each fact using one of the four ratings: Crticial(4), Informative(3), Uninformative (2) and Unrelated (1). Average scores over top-k positions are shown in Figure 9 with standard deviation ommited for clarity.…”

Section: Table Synthesismentioning

confidence: 99%

Contextual Fact Ranking and Its Applications in Table Synthesis and Compression

Huang

Liu

Korn

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Modern search engines increasingly incorporate tabular content, which consists of a set of entities each augmented with a small set of facts. The facts can be obtained from multiple sources: an entity's knowledge base entry, the infobox on its Wikipedia page, or its row within a WebTable. Crucially, the informativeness of a fact depends not only on the entity but also the specific context (e.g., the query). To the best of our knowledge, this paper is the first to study the problem of contextual fact ranking: given some entities and a context (i.e., succinct natural language description), identify the most informative facts for the entities collectively within the context. We propose to contextually rank the facts by exploiting deep learning techniques. In particular, we develop pointwise and pairwise ranking models, using textual and statistical information for the given entities and context derived from their sources. We enhance the models by incorporating entity type information from an IsA (hypernym) database. We demonstrate that our approaches achieve better performance than state-of-the-art baselines in terms of MAP, NDCG, and recall. We further conduct user studies for two specific applications of contextual fact ranking-table synthesis and table compression-and show that our models can identify more informative facts than the baselines.

show abstract

Actively Learning to Rank Semantic Associations for Personalized Contextual Exploration of Knowledge Graphs

Cited by 6 publications

References 20 publications

Using knowledge anchors to facilitate user exploration of data graphs

Using knowledge anchors to facilitate user exploration of data graphs

Building relatedness explanations from knowledge graphs

Contextual Fact Ranking and Its Applications in Table Synthesis and Compression

Contact Info

Product

Resources

About