Integrating Machine Learning Data with Symbolic Knowledge from Collaboration Practices of Curators to Improve Conversational Systems

要旨

This paper describes how machine learning training data and symbolic knowledge from curators of conversational systems can be used together to improve the accuracy of those systems and to enable better curatorial tools. This is done in the context of a real-world practice of curators of conversational systems who often embed taxonomically-structured meta-knowledge into their documentation. The paper provides evidence that the practice is quite common among curators, that is used as part of their collaborative practices, and that the embedded knowledge can be mined by algorithms. Further, this meta-knowledge can be integrated, using neuro-symbolic algorithms, to the machine learning-based conversational system, to improve its run-time accuracy and to enable tools to support curatorial tasks. Those results point towards new ways of designing development tools which explore an integrated use of code and documentation by machines.

著者
Claudio Santos. Pinhanez
IBM Research Brazil, Sao Paulo, Brazil
Heloisa Candello
IBM Research, Sao Paulo, Brazil
Paulo Cavalin
IBM Research Brazil, Sao Paulo, Brazil
Mauro Carlos. Pichiliani
IBM Research Brazil, Sao Paulo, Brazil
Ana Paula Appel
IBM Research Brazil, Sao Paulo, Brazil
Victor Henrique Alves Ribeiro
IBM Research Brazil, Sao Paulo, Brazil
Julio Nogima
IBM Research Brazil, Sao Paulo, Brazil
Maira de Bayser
IBM Research Brazil, Sao Paulo, Brazil
Melina Guerra
IBM Research Brazil, Sao Paulo, Brazil
Henrique Ferreira
IBM Research Brazil, Sao Paulo, Brazil
Gabriel Malfatti
IBM Research Brazil, Sao Paulo, Brazil
DOI

10.1145/3411764.3445368

論文URL

https://doi.org/10.1145/3411764.3445368

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Engineering Interactive Applications

[B] Paper Room 05, 2021-05-14 01:00:00~2021-05-14 03:00:00 / [C] Paper Room 05, 2021-05-14 09:00:00~2021-05-14 11:00:00 / [A] Paper Room 05, 2021-05-13 17:00:00~2021-05-13 19:00:00
Paper Room 05
14 件の発表
2021-05-14 01:00:00
2021-05-14 03:00:00
日本語まとめ
読み込み中…