@article{oai:ipsj.ixsq.nii.ac.jp:00091615,
 author = {岡, 照晃 and 小町, 守 and 小木曽, 智信 and 松本, 裕治 and Teruaki, Oka and Mamoru, Komachi and Toshinobu, Ogiso and Yuji, Matsumoto},
 issue = {4},
 journal = {情報処理学会論文誌},
 month = {Apr},
 note = {生の歴史的資料の中には，濁点が期待されるのに濁点の付いていない，濁点無表記の文字が多く含まれている．濁点無表記文字は可読性・検索性を下げるため，歴史コーパス整備の際には濁点付与が行われる．しかし，濁点付与は専門家にしか行えないため，作業人員の確保が大きな課題となっている．また，作業対象が膨大であるため，作業を完了するまでにも時間がかかる．そこで本論文では，濁点付与の自動化について述べる．我々は濁点付与を文字単位のクラス分類問題として定式化した．提案手法は分類を周辺文字列の情報のみで行うため，分類器の学習には形態素解析済みコーパスを必要としない．大規模な近代語のコーパスを学習に使用し，近代の雑誌「国民之友」に適合率96%，再現率98%の濁点付与を達成した．, Raw historical texts often include mark-lacking characters, which lack compulsory voiced consonant mark. Since mark-lacking characters degrade readability and retrievability, voiced consonant marks are annotated when creating historical corpus. However, since only experts can perform the labeling procedure for historical texts, getting annotators is a large challenge. Also, it is time-consuming to conduct annotation for large-scale historical texts. In this paper, we propose an approach to automatic labeling of voiced consonant marks for mark-lacking characters. We formulate the task into a character-based classification problem. Since our method uses as its feature set only surface information about the surrounding characters, we do not require corpus annotated with word boundaries and POS-tags for training. We exploited large data sets and achieved 96% precision and 98% recall on a near-modern Japanese magazine, Kokumin-no-Tomo.},
 pages = {1641--1654},
 title = {統計的機械学習を用いた歴史的資料への濁点付与の自動化},
 volume = {54},
 year = {2013}
}