JSAI2023

Presentation information

Organized Session

Organized Session » OS-6

[4H2-OS-6a] 言語とコミュニケーションの創発 ~記号創発システムから共創的言語進化まで~

Fri. Jun 9, 2023 12:00 PM - 1:40 PM Room H (B1)

オーガナイザ:上田 亮、谷口 忠大、鈴木 麗璽、中村 友昭、橋本 敬

1:00 PM - 1:20 PM

[4H2-OS-6a-04] Cross-Situational Word Learning through Attribute Discovery via Disentanglement

〇Yuta Matsui1, Akira Taniguchi1, Yoshinobu Hagiwara1, Tadahiro Taniguchi1 (1. Ritsumeikan University)

Keywords:Symbol Emergence in Robotics, Disentanglement, Cross-Situaltional Learning

This paper presents a computational model that mimics human word learning through cross-situational learning. Humans acquire word meanings by forming categories based on observed information about attributes like color and shape. The proposed model learns to understand attributes in images and establishes the relationship between attribute categories and words. To achieve this, we combine CSL-PGM, which facilitates cross-situation learning, with β-VAE, which enables unsupervised disentanglement of attributes. In our experiments, we trained the model on a dataset comprising images with five attributes and word sequences. Our model achieved a remarkable attribute comprehension rate of 99.9% for each word. In addition, the model outperformed existing multimodal generative models, achieving an 87.0% correct response rate for inferring images from word sequences.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password