Papers by Toshiki Kawamoto

2 papers
Dialogue Systems Can Generate Appropriate Responses without the Use of Question Marks?– a Study of the Effects of “?” for Spoken Dialogue Systems – (2024.lrec-main)

Copied to clipboard

Challenge: Existing systems for spoken dialogues do not append question marks to recognized queries . lack of punctuation marks in spoken dialogue can negatively impact comprehension .
Approach: They investigate the impact of question marks on spoken dialogue systems . they analyze examples to determine which types of utterances have the impact .
Outcome: The proposed method shows that question marks have a significant impact on spoken dialogue systems.
Generating Repetitions with Appropriate Repeated Words (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies have focused on general response generation with neural network-based approaches, but none have addressed specific types of repetitions.
Approach: They propose a weighted label smoothing method for explicitly learning which words to repeat during fine-tuning and a repetition scoring method that can output more appropriate repetitions during decoding.
Outcome: The proposed method outperforms baselines in automatic and human evaluations on a pre-trained language model for generating repetitions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations