Tadahiro Matsumoto.

Also published as: Tadahiro Matsumoto


2024

pdf
Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing
Jiannan Mao | Chenchen Ding | Hour Kaing | Hideki Tanaka | Masao Utiyama | Tadahiro Matsumoto.
Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024

UDify is a multilingual and multi-task parser fine-tuned on mBERT that achieves remarkable performance in high-resource languages. However, the performance saturates early and decreases gradually in low-resource languages as training proceeds. This work applies a data augmentation method and conducts experiments on seven few-shot and four zero-shot languages. The unlabeled attachment scores were improved on the zero-shot languages dependency parsing tasks, with the average score rising from 67.1% to 68.7%. Meanwhile, dependency parsing tasks for high-resource languages and other tasks were hardly affected. Experimental results indicate the data augmentation method is effective for low-resource languages in a multilingual dependency parsing.

2023

pdf
Improving Zero-Shot Dependency Parsing by Unsupervised Learning
Jiannan Mao | Chenchen Ding | Hour Kaing | Hideki Tanaka | Masao Utiyama | Tadahiro Matsumoto
Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation