챗GPT 프롬프트 엔지니어링을 활용한 상식 추론결과에서 나타난 언어 자질들 분석
The Analysis on the Linguistic Features of Common Sense Inference Using Chat-GPT Prompt Engineering
1
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
The purpose of this paper is how linguistic features operate prompt engineering in common sense inference using OpenAI ChatGPT. The operation of AI based on the Large Language Models is widely known as prompt engineering, which induces the common sense inferences of GPT via reinforcement learning from human feedback. Prompt engineering per se is a query to induce desired responses from the generative AIs. It is essential in creating better services and results from generative power of AI tools. In this paper, we analyze what aspect of linguistic features bring out better performance queries for the common sense inference. We deeply look into the features based on the theoretical linguistics.
Abstract
The purpose of this paper is how linguistic features operate prompt engineering in common sense inference using OpenAI ChatGPT. The operation of AI based on the Large Language Models is widely known as prompt engineering, which induces the common sense inferences of GPT via reinforcement learning from human feedback. Prompt engineering per se is a query to induce desired responses from the generative AIs. It is essential in creating better services and results from generative power of AI tools. In this paper, we analyze what aspect of linguistic features bring out better performance queries for the common sense inference. We deeply look into the features based on the theoretical linguistics.
참고문헌 (43)
- Achimova, A, "Linguistic and Cognitive Aspects of Quantification", pp.13~29 (2016)
- Banarescu, L., "Abstract Meaning Representation for Sembanking", ACL Linguistic Annotation Workshop (2013)
- Brown, T., "Language Models are Few-Shot Learners", Proceedings of the 34th International Conference on Neural Information Processing Systems, pp.1877~1901 (2020)
- Butt, M, "Complex Predicates" (2011), Cambridge University Press
- Cann, R, "Formal Semantics" (1993), Cambridge University Press
- Ginzburg, J, "Resolving Questions I & II", Linguistics and Philosophy, 18, pp.459~527 (1995)
- Grimshaw, J, "Arguemnt Structue" (1990), The MIT Press
- Groenendijk, J., "Semantic Analysis of Wh-Complements", Linguistics and Philosophy, 5, pp.175~233 (1982)
- Studies on the Semantics of Questions and the Pragmatics of Answers, dissertation, "Groenendijk, J.", ~ (1984)
- Groenendijk, J., "The Handbook of Logic and Language" (1994), Elsevier Science
- Hamblin, C. L, "Questions", Australian Journal of Philosophy, 36, pp.159~168 (1958)
- Harris, Z. S, "Distributional structure", Word, 10(2-3), pp.146~162 (1954)
- Hearst, M, "Automatic Acquisition of Hyponyms from Large Text Corpora", COLING, 1992, pp.539~545 (1992)
- Hintikka, J., "The Semantics of Questions and The Questions of Semantics", Acta Philosophica Fennica, 28 (1976)
- Huang, L., "Cosmos QA", Proceedings of the 2019 Conference on EMNLP, pp.2391~2401 (2019)
- Jackendoff, R, "Toward an Explanatory Semantic Representation", Linguistic Inquiry, 7, pp.89~150 (1976)
- Jackendoff, R, "Semantic Structures" (1990), The MIT Press
- Karttunen, L, "Syntax and Semantics of Questions", Linguistics and Philosophy, 1, pp.3~44 (1977)
- Kjima, T., "Large language models are zero-shot reasoners", Proceedings of the NeurIPS (2022)
- LeCun, Y., "A path towards autonomous machine intelligence version 0. 9. 2, 2022-06-27", Open Review, pp.62~ (2022)
- Levesque, H., "The winograd schema challenge", 13th International Conference on the Principles of Knowledge Representation and Reasoning (2012)
- Levin, B, "English Verb Classes and Alternations" (1993), University of Chicago Press
- Levin, B., "The Handbook of Contemporary Semantic Theory", pp.487~507 (1996), Blackwell
- Levy, O., "Linguistic Regularities in Sparse and Explicit Word Representations", Proceedings of the Eighteenth Conference on Computational Language Learning, pp.171~180 (2016)
- Lin, B., "CommonGen", Findings of the ACL, pp.1823~1840 (2020)
- Liu, P., "Pre-train, Prompt, and Predict", Computing Survey, 55(9), pp.1~35 (2023)
- Mikolov, T., "Efficient estimation of word representations in vector space", arXiv preprint arXiv:1301.3781, ~ (2013)
- Ponti, E., "XCOPA", Proceedings of the 2020 Conference on EMNLP, pp.2362~2376 (2020)
- Pustejovsky, J, "The Generative Lexicon" (1995), Bradford Press
- Rajani, N., "Explain yourself!", Proceedings of the 57th Annual Meeting of ACL, pp.4932~4942 (2019)
- Rizzi, L, "Syntactic architecture and its consequences III: Inside syntax", pp.271~285 (2021), Language Science Press
- Simik, R, "Introduction to the semantics of questions" (2011), EGG summer school
- Talmor, A., "CommonsenseQA 2. 0", Proceedings of 35th Conference on Neural Information Processing Systems (2019)
- Trinh, T., "A simple method for commonsense reasoning", CoRR (2018)
- Turney, P, "Similarity of Semantic Relations", Journal of Computational Linguistics, 32, pp.379~416 (2006)
- Vaswani, A., "Attention is all you need", Advances in Neural Information Processing Systems, pp.30~ (2017)
- Wei, J., "Finetuned language models are zero-shot learners", Proceedings of LCLR 2022 (2021)