Papers by Teruaki Oka
Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Word Sense Disambiguation (WSD) is a core task in natural language processing . ancient Chinese has rarely been used in WSD tasks due to lack of a dataset . |
| Approach: | They annotate ancient Chinese text Zuo Zhuan using a copyright-free dictionary . they apply a method to find the most appropriate sense in a context using k-NN . |
| Outcome: | The proposed dataset will be available on GitHub. |
A Document-Level Text Simplification Dataset for Japanese (2024.lrec-main)
Copied to clipboard
| Challenge: | Document-level text simplification tasks combine summarization and intra-sentence simplification. |
| Approach: | They devised a Japanese document-level text simplification dataset based on newspaper articles and Wikipedia. |
| Outcome: | The proposed dataset compared Japanese document-level text simplification models with English models and newspaper articles. |
Token-length Bias in Minimal-pair Paradigm Datasets (2024.lrec-main)
Copied to clipboard
| Challenge: | Minimal-pair paradigm datasets are used to evaluate the linguistic knowledge of language models and provide an unsupervised method of acceptability judgment. |
| Approach: | They propose a debiased minimal pair generation method that allows MPP datasets to evaluate the linguistic knowledge of a language model correctly. |
| Outcome: | The proposed method is based on the percentage of minimal pairs in the MPP dataset where the model assigns a higher sentence log-likelihood than an unacceptable sentence. |
KOTONOHA: A Corpus Concordance System for Skewer-Searching NINJAL Corpora (2020.lrec-1)
Copied to clipboard
Teruaki Oka, Yuichi Ishimoto, Yutaka Yagi, Takenori Nakamura, Masayuki Asahara, Kikuo Maekawa, Toshinobu Ogiso, Hanae Koiso, Kumiko Sakoda, Nobuko Kibe
| Challenge: | NINJAL has developed several types of corpora for linguistic research . for each corpus NINJAL provided an online search environment, ‘Chunagon’ . |
| Approach: | NINJAL has developed several types of corpora for linguistic research . for each corpus NINJAL provided an online search environment, ‘Chunagon’, which is a morphological-information-annotation-based concordance system made publicly available in 2011 . NINjal has now provided a system ‘Kotonoha’ based on the ‘Chunegon’ systems . |
| Outcome: | NINJAL has provided a skewer-search system ‘Kotonoha’ based on ‘Chunagon’ systems. |