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.
@article{arxiv.1804.09259,
title = {Commonsense mining as knowledge base completion? A study on the impact of novelty},
author = {Stanisław Jastrzębski and Dzmitry Bahdanau and Seyedarian Hosseini and Michael Noukhovitch and Yoshua Bengio and Jackie Chi Kit Cheung},
journal= {arXiv preprint arXiv:1804.09259},
year = {2018}
}
Comments
Published in Workshop on New Forms of Generalization in Deep Learning and Natural Language Processing (NAACL 2018)