-
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
We propose a neural machine-reading model that constructs dynamic knowle...
10/12/2018 ∙ by Rajarshi Das, et al. ∙
0
∙
share
read it
-
Traversing Knowledge Graphs in Vector Space
Path queries on a knowledge graph can be used to answer compositional qu...
06/03/2015 ∙ by Kelvin Guu, et al. ∙ 0
∙
share
read it
-
Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations
Knowledge graphs are a versatile framework to encode richly structured d...
08/01/2017 ∙ by Benjamin J. Lengerich, et al. ∙ 0
∙
share
read it
-
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
Knowledge graph embedding has been an active research topic for knowledg...
11/11/2018 ∙ by Chao Shang, et al. ∙ 4
∙
share
read it
-
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
We present ATOMIC, an atlas of everyday commonsense reasoning, organized...
10/31/2018 ∙ by Maarten Sap, et al. ∙ 0
∙
share
read it
-
Commonsense mining as knowledge base completion? A study on the impact of novelty
Commonsense knowledge bases such as ConceptNet represent knowledge in th...
04/24/2018 ∙ by Stanisław Jastrzębski, et al. ∙ 0
∙
share
read it
-
Building Knowledge Graphs About Political Agents in the Age of Misinformation
This paper presents the construction of a Knowledge Graph about relation...
01/29/2019 ∙ by Daniel Schwabe, et al. ∙ 0
∙
share
read it
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
06/12/2019 ∙ by Antoine Bosselut, et al. ∙
25
∙
share
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5 approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.
READ FULL TEXT