no code implementations • RANLP 2021 • Satoshi Hiai, Kazutaka Shimada, Taiki Watanabe, Akiva Miura, Tomoya Iwakura
In addition, our method shows approximately three times faster extraction speed than the BERT-based models on the ChemProt corpus and reduces the memory size to one sixth of the BERT ones.
no code implementations • RANLP 2021 • Takumi Himeno, Kazutaka Shimada
Our purpose in this paper is to predict a link structure between nodes that consist of utterances in a conversation: classification of each node pair into “linked” or “not-linked.” One approach to predict the structure is to utilize machine learning models.
no code implementations • RANLP 2021 • Hiyori Yoshikawa, Tomoya Iwakura, Kimi Kaneko, Hiroaki Yoshida, Yasutaka Kumano, Kazutaka Shimada, Rafal Rzepka, Patrycja Swieczkowska
To address the issue, we propose a method to estimate the domain expertise of each annotator before the annotation process using information easily available from the annotators beforehand.
no code implementations • 7 Feb 2024 • Niraj Pahari, Kazutaka Shimada
However, using the native script for each language can generate better representations of the text owing to the pre-trained knowledge.
no code implementations • 28 Feb 2022 • Keita Nonaka, Kazutaka Yamanouchi, Tomohiro I, Tsuyoshi Okita, Kazutaka Shimada, Hiroshi Sakamoto
In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm.
no code implementations • WS 2016 • Takashi Yamamura, Kazutaka Shimada, Shintaro Kawahara
As a case study for the corpus, we describe a method combined with LCSeg and TopicTiling for a topic segmentation task.