Paper Info
Title
Commonsense mining as knowledge base completion? A study on the impact of novelty.
Abstract
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by the recent work by Li et al., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method outperforms the previous state of the art on predicting more novel.
Year
DOI
Venue
2018
10.18653/v1/w18-1002
arXiv: Computation and Language
Field
DocType
Volume
Training set,Commonsense knowledge,Computer science,Artificial intelligence,Natural language processing,Novelty,Knowledge base
Journal
abs/1804.09259
Citations 
PageRank 
References 
0
0.34
9
Authors
6
Name
Order
Citations
PageRank
Jastrzębski Stanisław113114.12
Dzmitry Bahdanau22677117.03
Seyedarian Hosseini350.71
Michael Noukhovitch400.34
Yoshua Bengio5426773039.83
Jackie Chi Kit Cheung67016.92