3 papers
cs.CL2024
An Analysis on Automated Metrics for Evaluating Japanese-English Chat Translation
Andre Rusli, Makoto Shishido
This paper analyses how traditional baseline metrics, such as BLEU and TER, and neural-based methods, such as BERTScore and COMET, score several NMT models performance on chat tran…
cs.CL2024
On the Applicability of Zero-Shot Cross-Lingual Transfer Learning for Sentiment Classification in Distant Language Pairs
Andre Rusli, Makoto Shishido
This research explores the applicability of cross-lingual transfer learning from English to Japanese and Indonesian using the XLM-R pre-trained model. The results are compared with…
cs.CL2024
An Experimental Evaluation of Japanese Tokenizers for Sentiment-Based Text Classification
Andre Rusli, Makoto Shishido
This study investigates the performance of three popular tokenization tools: MeCab, Sudachi, and SentencePiece, when applied as a preprocessing step for sentiment-based text classi…