Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Taiki Watanabe

dblp:212/0124 · DBLP profile ↗
← Back
3ranked-venue papers
3as first author
1since 2021 · last 2022
—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 2 first-authorSoftware engineering, systems software and programming languages · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Information extraction and text analysis · 100%

Topics — the 2 heaviest of 2, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Information extraction and text analysis › named entity recognition
chemical named entity recognition
0.412019
Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing · EMNLP/IJCNLP (1) 2019
Natural language and speech › Information extraction and text analysis
named entity recognition
0.412019
Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing · EMNLP/IJCNLP (1) 2019

Methods — techniques the papers use, named apart from their topics

paraphrasing · 0.4multi-task learning · 0.4
YearPublicationVenuePosition
2022 Air Finger Pressing Activity-Based Character Input System on a Virtual Keyboard
abstract
Non-touch-based keyboard became an urgent need in many situations where humans cannot directly touch the keyboard due to hygienic or security issues in human computer interaction. In this paper, a non-touch keyboard has been created using Leap Motion and Unity. The key layout is based on the qwerty type. There are five types of keyboards that we have created to provide support for both Japanese and English characters. The five types are default type, orthogonal type, round default type, round orthogonal type, and flick keyboard. In addition, a word prediction function has been implemented to assist user input. A word prediction function was added to the keyboard of the round orthogonal type, which has the highest input accuracy. It’s input accuracy was 96.84% and the character per minute (cpm) was 77.67. The flick keyboard recorded an input accuracy of 97.6% and a cpm of 56.485. This is comparable to other studies in terms of input accuracy and much higher in terms of cpm.
Taiki Watanabe, Md. Al Mehedi Hasan, Jungpil Shin 0001
SoMeT1
2019 Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing
abstract
Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura
EMNLP/IJCNLP (1)1
2019 Lightweight Modal Regression for Stand Alone Embedded Systems
Taiki Watanabe, Koichiro Yamauchi 0001
ICONIP (2)1