Kei Uchiumi — accepted AI-conference papers

2022

Word-level Perturbation Considering Word Length and Compositional Subwords

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki

ACL 2022findings

We present two simple modifications for word-level perturbation: Word Replacement considering Length (WR-L) and Compositional Word Replacement (CWR).In conventional word replacement, a word in an input is replaced with a word sampled from the entire vocabulary, regardless of the length and context o…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2020

How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text

Chihiro Shibata, Kei Uchiumi, Daichi Mochihashi

COLING 2020main

Long Short-Term Memory recurrent neural network (LSTM) is widely used and known to capture informative long-term syntactic dependencies. However, how such information are reflected in its internal vectors for natural text has not yet been sufficiently investigated. We analyze them by learning a lang…

Cited by 9 Source ↗PDF ↗Scholar ↗