Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects. Mullenbach, J., Gordon, J., Peng, N., & May, J. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6051–6057, Hong Kong, China, November, 2019. Association for Computational Linguistics.
Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects [link]Paper  doi  abstract   bibtex   
How do adjectives project from a noun to its parts? If a motorcycle is red, are its wheels red? Is a nuclear submarine's captain nuclear? These questions are easy for humans to judge using our commonsense understanding of the world, but are difficult for computers. To attack this challenge, we crowdsource a set of human judgments that answer the English-language question ``Given a whole described by an adjective, does the adjective also describe a given part?'' We build strong baselines for this task with a classification approach. Our findings indicate that, despite the recent successes of large language models on tasks aimed to assess commonsense knowledge, these models do not greatly outperform simple word-level models based on pre-trained word embeddings. This provides evidence that the amount of commonsense knowledge encoded in these language models does not extend far beyond that already baked into the word embeddings. Our dataset will serve as a useful testbed for future research in commonsense reasoning, especially as it relates to adjectives and objects
@inproceedings{mullenbach-etal-2019-nuclear,
    title = "Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects",
    author = "Mullenbach, James  and
      Gordon, Jonathan  and
      Peng, Nanyun  and
      May, Jonathan",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-1625",
    doi = "10.18653/v1/D19-1625",
    pages = "6051--6057",
    abstract = "How do adjectives project from a noun to its parts? If a motorcycle is red, are its wheels red? Is a nuclear submarine{'}s captain nuclear? These questions are easy for humans to judge using our commonsense understanding of the world, but are difficult for computers. To attack this challenge, we crowdsource a set of human judgments that answer the English-language question {``}Given a whole described by an adjective, does the adjective also describe a given part?{''} We build strong baselines for this task with a classification approach. Our findings indicate that, despite the recent successes of large language models on tasks aimed to assess commonsense knowledge, these models do not greatly outperform simple word-level models based on pre-trained word embeddings. This provides evidence that the amount of commonsense knowledge encoded in these language models does not extend far beyond that already baked into the word embeddings. Our dataset will serve as a useful testbed for future research in commonsense reasoning, especially as it relates to adjectives and objects",
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021