1 code implementation • World Wide Web Journal 2023 • Makoto Nakatsuji, Yuka Ozeki, Shuhei Tateishi, Yoshihisa Kano & QingPeng Zhang
Then, SemSol improves the accuracy of the response by exploiting the semantic information in a knowledge graph in accordance with the dialogue context.
Ranked #1 on Conversational Response Selection on Douban
no code implementations • 22 Apr 2020 • Makoto Nakatsuji, Sohei Okui
Machine reading comprehension methods that generate answers by referring to multiple passages for a question have gained much attention in AI and NLP communities.
no code implementations • 6 Dec 2019 • Makoto Nakatsuji
As a result, it can extract answers that suit the contexts of words used in the question as well as following the common usage of words across semantics.
no code implementations • 25 Nov 2019 • Makoto Nakatsuji, Sohei Okui
This paper tackles the goal of conclusion-supplement answer generation for non-factoid questions, which is a critical issue in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI), as users often require supplementary information before accepting a conclusion.