Commonsense mining as knowledge base completion? A study on the impact of novelty

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.

[1]  Hugo Liu,et al.  ConceptNet — A Practical Commonsense Reasoning Tool-Kit , 2004 .

[2]  Magnus Sahlgren,et al.  The Word-Space Model: using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces , 2006 .

[3]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[4]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[5]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[6]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

[7]  Danqi Chen,et al.  Reasoning With Neural Tensor Networks for Knowledge Base Completion , 2013, NIPS.

[8]  Christopher D. Manning,et al.  Philosophers are Mortal: Inferring the Truth of Unseen Facts , 2013, CoNLL.

[9]  Omer Levy,et al.  Do Supervised Distributional Methods Really Learn Lexical Inference Relations? , 2015, NAACL.

[10]  Xueqi Cheng,et al.  Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations , 2015, ACL.

[11]  Xinlei Chen,et al.  Never-Ending Learning , 2012, ECAI.

[12]  Xiang Li,et al.  Commonsense Knowledge Base Completion , 2016, ACL.

[13]  Tomas Mikolov,et al.  Fast Linear Model for Knowledge Graph Embeddings , 2017, AKBC@NIPS.

[14]  Rudolf Kadlec,et al.  Knowledge Base Completion: Baselines Strike Back , 2017, Rep4NLP@ACL.

[15]  Yejin Choi,et al.  Verb Physics: Relative Physical Knowledge of Actions and Objects , 2017, ACL.

[16]  Pasquale Minervini,et al.  Convolutional 2D Knowledge Graph Embeddings , 2017, AAAI.