Evlauation of Commonsense Knowledge in Children&#039;s book -Using Neural Language Model- (영어권 아동 도서의 일반 상식 평가 -신경망 언어 모델을 활용하여-)

Keonwoo Koo (구건우); LEE JAE MIN (이재민); Euhee Kim (김유희)

doi:10.33639/ptc.2023..41.013

Evlauation of Commonsense Knowledge in Children's book -Using Neural Language Model-

PHILOSOPHY·THOUGHT·CULTURE
2023, (41), pp.277~293
DOI : 10.33639/ptc.2023..41.013
Publisher : Research Institute for East-West Thought
Research Area : Humanities > Other Humanities
Received : December 20, 2022
Accepted : January 31, 2023
Published : January 31, 2023

Keonwoo Koo ¹, LEE JAE MIN ¹, Euhee Kim ²

¹동국대학교
²신한대학교

Accredited

ABSTRACT

Artificial intelligence has made significant progress in recent years through the development of deep learning, enabling it to match human performance in many areas. However, one of the major challenges facing AI is its lack of commonsense knowledge. While humans are able to unconsciously and intuitively infer general knowledge based on their experiences in the world, even the most advanced neural network language models, such as GPT-3, struggle to possess such knowledge. To address this limitation, researchers are conducting extensive studies to teach AI general knowledge about the world through the use of commonsense graphs. The goal of this research is to determine how much commonsense knowledge neural network language models can learn, and this is being evaluated through the CB-COMET model, which was trained on the Children's Book Dataset using ATOMIC-2020.

KEYWORDS

Artificial intelligence, commonsense (knowledge), language processing, neural language model

Citation status

* References for papers published after 2023 are currently being built.

[journal] Bender, E. M. / 2020 / Climbing towards NLU : on meaning, form, and understanding in the age of data / Association for Computational Linguistics : 5185~5198

[other] Bosselut, A. / 2019 / COMET : Commonsense transformers for automatic knowledge graph construction / ACL

[other] Choi, Y / 2022 / The Curious Case of Commonsense Intelligence / Daedalus

[confproc] Davis, E. / 2015 / Commonsense reasoning and commonsense knowledge in artificial intelligence / ACM 58 : 92103~

[other] He, M. / 2022 / Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization / arXiv preprint arXiv:2206.01532

[confproc] Hwang, J. D. / 2020 / COMET-ATOMIC 2020 : On Symbolic and Neural Commonsense Knowledge Graphs / AAAI

[confproc] Mostafazadeh, N. / 2016 / Corpus and cloze evaluation for deeper understanding of commonsense stories / NAACL

[other] Romero, J. / 2022 / Do Children Texts Hold The Key To Commonsense Knowledge? / arXiv preprint arXiv:2210. 04530

[confproc] Sap, M. / 2019 / Atomic : An atlas of machine commonsense for if-then reasoning / AAAI

[confproc] Speer, R. / 2017 / Conceptnet 5. 5 : An open multilingual graph of general knowledge / AAAI : 44444451~

[confproc] Yang, B. / 2015 / Embedding entities and relations for learning and inference in knowledge bases / ICLR

KJCKorea
Journal Central

PHILOSOPHY·THOUGHT·CULTURE 2023 KCI Impact Factor : 0.5

Evlauation of Commonsense Knowledge in Children's book -Using Neural Language Model-

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

PHILOSOPHY·THOUGHT·CULTURE 2023 KCI Impact Factor : 0.5

Evlauation of Commonsense Knowledge in Children's book -Using Neural Language Model-

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (11) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.