Augmenting TV Newscasts via Entity Expansion

Redondo-García, José Luis; Hildebrand, Michiel; Romero, Lilia Perez; Troncy, Raphaël

doi:10.1007/978-3-319-11955-7_69

Cited by 5 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need of a NSS for feeding second screen applications is a concept we have already investigated in some previous research work and prototypes [7], proving the benefit of browsing the "surrounding context" of a newscasts. The same idea 1 was presented in the Iberoamerican Biennial of Design (BID) 2 with great feedback from users and experts.…”

Section: Related Workmentioning

confidence: 99%

Generating Semantic Snapshots of Newscasts Using Entity Expansion

García

Rizzo

Romero

et al. 2015

Engineering the Web in the Big Data Era

Self Cite

View full text Add to dashboard Cite

Abstract. TV newscasts report about the latest event-related facts occurring in the world. Relying exclusively on them is, however, insufficient to fully grasp the context of the story being reported. In this paper, we propose an approach that retrieves and analyzes related documents from the Web to automatically generate semantic annotations that provide viewers and experts comprehensive information about the news. We detect named entities in the retrieved documents that further disclose relevant concepts that were not explicitly mentioned in the original newscast. A ranking algorithm based on entity frequency, popularity peak analysis, and domain experts' rules sorts those annotations to generate what we call Semantic Snapshot of a Newscast (NSS). We benchmark this method against a gold standard generated by domain experts and assessed via a user survey over five BBC newscasts. Results of the experiments show the robustness of our approach holding an Average Normalized Discounted Cumulative Gain of 66.6%.

show abstract

Section: Related Workmentioning

confidence: 99%

Generating Semantic Snapshots of Newscasts Using Entity Expansion

García

Rizzo

Romero

et al. 2015

Engineering the Web in the Big Data Era

Self Cite

View full text Add to dashboard Cite

show abstract

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

et al. 2017

View full text Add to dashboard Cite

Knowledge Graphs (KG) provide useful abstractions to represent large amount of relations that occur between entities of different types. Chains of such relations represented by semantic associations reveal connections between entities that may be interesting, and possibly unknown, to a user, thus resulting valuable for her to get insights into a given topic. For example, in contextual exploration of KGs, we may want to let a user explore a set of semantic associations that are deemed to be more interesting for her while she is reading an input text. Using wellknown techniques to bridge the gap between the input text and the KG a associations can be found and presented to the user. However, because of the large number of diverse associations that can be found, a critical challenge is to effectively rank the associations so as to present the ones that are estimated to be most interesting. In addition, since users may have different interests, this ranking function should be adapted to match users' preferences to personalize the exploration of KG information. In this paper We describe an active learning to rank model to let a user rate a small sample of associations, which is used to learn a ranking function that optimize the user preferences. To the best of our knowledge this is the first attempt to use active learning to rank techniques to explore semantic associations. Experiments conducted with several data sets show that the approach is able to improve the quality of the ranking function with a limited number of user interactions.

show abstract