Frontiers | Bootstrapping Knowledge Graphs From Images and Text | Frontiers in Neurorobotics

Frontiers | Bootstrapping Knowledge Graphs From Images and Text | Frontiers in Neurorobotics

The problem of generating structured Knowledge Graphs (KGs) is difficult and open but relevant to a range of tasks related to decision making and information augmentation. A promising approach is to study generating KGs as a relational representation of inputs (e.g., textual paragraphs or natural images), where nodes represent the entities and edges represent the relations. This procedure is naturally a mixture of two phases: extracting primary relations from input, and completing the KG with reasoning. In this paper, we propose a hybrid KG builder that combines these two phases in a unified framework and generates KGs from scratch. Specifically, we employ a neural relation extractor resolving primary relations from input and a differentiable inductive logic programming (ILP) model that iteratively completes the KG. We evaluate our framework in both textual and visual domains and achieve comparable performance on relation extraction datasets based on Wikidata and the Visual Genome. The

1 mentions: @aaranged
Date: 2019/12/07 00:51

Referring Tweets

@aaranged Bootstrapping Knowledge Graphs From Images and Text / Guang Chen et al.

Related Entries

Read more New deep learning model can accurately identify sleep stages - University of Eastern Finland
0 users, 9 mentions 2020/02/03 15:50
Read more Oracle Announces Oracle Cloud Data Science Platform
0 users, 15 mentions 2020/02/12 15:50
Read more Stanza: Official Stanford NLP Python Library for Many Human Languages | MarkTechPost
0 users, 3 mentions 2020/04/01 04:38
Read more [2004.08798] Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learningopen sea...
0 users, 1 mentions 2020/04/24 06:52
Read more Facebook AI Open Sources DEtection TRansformer (DETR)
1 users, 29 mentions 2020/05/27 15:04