PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model

1 code implementation • 11 Oct 2023 • Tatsuya Ide, Eiki Murata, Daisuke Kawahara, Takato Yamazaki, Shengzhe Li, Kenta Shinzato, Toshinori Sato

In this paper, we propose PHALM, a method of building a knowledge graph from scratch, by prompting both crowdworkers and a large language model (LLM).

Language Modelling Large Language Model +1

Dialogue Systems Can Generate Appropriate Responses without the Use of Question Marks? -- Investigation of the Effects of Question Marks on Dialogue Systems

no code implementations • 7 Aug 2023 • Tomoya Mizumoto, Takato Yamazaki, Katsumasa Yoshikawa, Masaya Ohagi, Toshiki Kawamoto, Toshinori Sato

When individuals engage in spoken discourse, various phenomena can be observed that differ from those that are apparent in text-based conversation.

Sentence speech-recognition +2

Tourist Guidance Robot Based on HyperCLOVA

no code implementations • 19 Oct 2022 • Takato Yamazaki, Katsumasa Yoshikawa, Toshiki Kawamoto, Masaya Ohagi, Tomoya Mizumoto, Shuta Ichimura, Yusuke Kida, Toshinori Sato

This paper describes our system submitted to Dialogue Robot Competition 2022.

speech-recognition Speech Recognition

Building a Personalized Dialogue System with Prompt-Tuning

no code implementations • NAACL (ACL) 2022 • Tomohito Kasahara, Daisuke Kawahara, Nguyen Tung, Shengzhe Li, Kenta Shinzato, Toshinori Sato

Dialogue systems without consistent responses are not fascinating.