[25th AIP Open Seminar] Talks by AI Safety and Reliability Unit

Wed, 19 May 2021 15:00 - 16:00 JST
Online Link visible to participants

Registration is closed

Get invited to future events

Free admission
Title 1(English)Title 2(Japanese)-The seats are available on a first-come-first-served basis. -When the seats are fully booked, we may stop accepting applications. -Simultaneous interpretation will not be available.


AI Safety and Reliability Unit ( at RIKEN AIP

Speaker: Hiromi ARAI

Title 1: Overview of AI Safety and Reliability Unit (45 min)
Abstract 1:
In this talk, we will give an overview of the AI Safety and Reliability Unit. Recently AI technologies raise novel ethical, legal, and policy challenges. To tackle these challenges, we investigate fairness, transparency, and privacy-preservation in machine learning and data utilization. We approach these problems by developing computational methods, conducting data analyses, and interdisciplinary researches. We will introduce the background of our research activities. Then we will present research activities of our team including privacy-preserving techniques, privacy policy analysis, and the risk of rationalization in machine learning model explanation.

Title 2: ヘイトスピーチ検出に向けた日本語データセット作成の試案(日本語) (15 min)
This talk will be delivered in Japanese
Abstract 2:
日本語におけるヘイトスピーチのデータセット作成に向けた試案作成の取り組みを紹介する。我々は発言が話題にしている対象者とその対象者に対する攻撃性の種類を判断させるような手続き的な暴言分類のアノテーションガイドラインを設計した。特に日本独自の歴史・地域性を踏まえたヘイトスピーチ理解と、人文社会科学におけるヘイトスピーチに関する理論的知見に依拠した物となっている.さらにSNS 上のヘイトスピーチの候補となるツイートを収集し、クラウドソーシングを用いたアノテーションを試験的に実施し,得られたデータセットの特徴を考察した結果を報告する。

All participants are required to agree with the AIP Open Seminar Series Code of Conduct.
Please see the URL below.

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.

About this community



Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community