COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

By Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi. 2019

1,043 citations recorded by the source corpus.

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% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which 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.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Yejin Choi
  3. Percy Liang
  4. Luke S. Zettlemoyer
  5. Jianfeng Gao
  6. Noah A. Smith
  7. Hannaneh Hajishirzi
  8. Graham Neubig

In Molecular Biology

  1. Christopher D. Manning
  2. Percy Liang
  3. Xiang Ren
  4. Daniel Klein
  5. Phil Blunsom
  6. Mohit Bansal
  7. Noah A. Smith
  8. Iryna Gurevych

In Natural Language Processing

  1. Yejin Choi
  2. Mohit Bansal
  3. Luke S. Zettlemoyer
  4. Hannaneh Hajishirzi
  5. Noah A. Smith
  6. Graham Neubig
  7. Percy Liang
  8. Jianfeng Gao

In Knowledge Graphs & Representation

  1. Yejin Choi
  2. Ronan Le Bras
  3. Xiang Ren
  4. Jure Leskovec
  5. Mohit Bansal
  6. Adyasha Maharana
  7. Michihiro Yasunaga
  8. Chandra Bhagavatula

Citations in the corpus