Search Results for author: Kentaro Torisawa

Found 23 papers, 1 papers with code

BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks

1 code implementation ACL 2021 Jong-Hoon Oh, Ryu Iida, Julien Kloetzer, Kentaro Torisawa

We show that on the GLUE tasks, the combination of our pretrained CNN with ALBERT outperforms the original ALBERT and achieves a similar performance to that of SOTA.

Automatic Graph Partitioning for Very Large-scale Deep Learning

no code implementations30 Mar 2021 Masahiro Tanaka, Kenjiro Taura, Toshihiro Hanawa, Kentaro Torisawa

RaNNC also achieved better training throughputs than GPipe on both the enlarged BERT model pre-training (GPipe with hybrid parallelism) and the enlarged ResNet models (GPipe with model parallelism) in all of the settings we tried.

graph partitioning

Understanding User Utterances in a Dialog System for Caregiving

no code implementations LREC 2020 Yoshihiko Asao, Julien Kloetzer, Junta Mizuno, Dai Saiki, Kazuma Kadowaki, Kentaro Torisawa

A dialog system that can monitor the health status of seniors has a huge potential for solving the labor force shortage in the caregiving industry in aging societies.

DISAANA and D-SUMM: Large-scale Real Time NLP Systems for Analyzing Disaster Related Reports in Tweets

no code implementations WS 2016 Kentaro Torisawa

D-SUMM automatically summarizes a large number of disaster related reports concerning a specified area and helps rescue workers to understand disaster situations from a macro perspective.

Cannot find the paper you are looking for? You can Submit a new open access paper.