A time series of conversations between twin babies with underdeveloped native language is shown in relation to eigenvalues, skeletal movement distance, fundamental frequency, and sound intensity level. The cross-correlation of these time series was examined.

In order to give chatbots characterized personality, stylistic features and speech intention response patterns were extracted from dialogues in works that have been successful in the character business were used. Based on the extracted results, an estimation system for speech intention was constructed, and speech was generated in a large-scale language model. Specifically, a system was constructed to estimate 13 types of intentions by performing fine tuning on the learned model. The classification accuracy was 74.67% when output that was confirmed by the analyst and deemed acceptable was included as a correct answer. The accuracy of generating appropriate responses to utterances was 75.90%. In the future, it is believed that it will be possible to generate more characterful speech by manipulating the character's response intention according to the intention estimation.

This study aims to introduce the concept of perceptual design as a metaphor to understand language communication and meaning, as an alternative to the traditional conduit metaphor. Even ecological phycologists rely on conventional models of language that assume the manipulation of internal representations. As an alternative to this, the ecological approach posits that communication is the achievement of perception and action through language as design process of perception, and thus internal representations are not essential (non-representational language model). The latter half of this study, using the Corpus of Spontaneous Japanese, this study demonstrates how linguistic expressions with different tense and aspect forms perceptualize different affordances.

To enhance the capabilities of LLMs in downstream tasks, appropriate prompts are essential, yet what constitutes appropriateness remains insufficiently debated. This paper categorizes natural language prompts into subtypes: (1) DP (Definition-based Prompt), (2) IP (Instance-based Prompt), and (3) RDP (Recursive Definition-based Prompt), and validates seven methods of knowledge injection using these three prompt types (D, I, RD, D+I, RD+I, D+RD, D+RD+I). Through a total of 350 experimental iterations, the results indicate: (1) I and RD show similar outcomes and demonstrate higher accuracy and stability than D. (2) Methods employing multiple prompt types consistently exhibit higher accuracy and stability compared to single prompt type methods. (3) D+I achieves the highest accuracy, while D+RD+I significantly excels in stability over D+I, showing overall superior performance. (4) RDP administration enhances stability, and a synergistic effect between DP and IP is observed. (5) IP yields better results than DP, whether used alone or in combination with RP. Based on these findings, this paper examines methods of knowledge injection and the role of domain experts.