Metaphor detection is a fundamental task in natural language processing, yet research on historical languages remains limited. While progress has been made in modern Japanese metaphor detection, classical Japanese texts present unique challenges due to their distinct vocabulary, grammar, and metaphorical patterns. This paper addresses this gap by applying a BERT-based metaphor detection method enhanced with semantic classification information from the Word List by Semantic Principles (WLSP) to classical Japanese texts. We evaluate our approach on CHJ-Metaphor, a newly available corpus featuring metaphor annotations for three medieval Japanese works from the Corpus of Historical Japanese (CHJ). Our method achieves an F1-score of 82.18 through 5-fold cross-validation. Notably, qualitative analysis by domain experts reveals that our model successfully identifies genuine metaphors overlooked during manual annotation, demonstrating its potential as a tool for improving annotation quality in large-scale corpus construction. These results confirm the effectiveness of WLSP-enhanced approaches for metaphor detection in classical Japanese and suggest promising directions for applying similar techniques to other historical languages.

This article presents a word-sense annotation for the Corpus of Historical Japanese: a mashed-up Japanese lexicon based on the ‘Word List by Semantic Principles’ (WLSP). The WLSP is a large-scale Japanese thesaurus that includes 98,241 entries with syntactic and hierarchical semantic categories. The historical WLSP is also compiled for the words in ancient Japanese. We utilized a morpheme-word sense alignment table to extract all possible word sense candidates for each word appearing in the target corpus. Then, we manually disambiguated the word senses for 647,751 words in the texts from the 10th century to 1910.

This article presents a contrastive analysis between reading time and syntactic/semantic categories in Japanese. We overlaid the reading time annotation of BCCWJ-EyeTrack and a syntactic/semantic category information annotation on the ‘Balanced Corpus of Contemporary Written Japanese’. Statistical analysis based on a mixed linear model showed that verbal phrases tend to have shorter reading times than adjectives, adverbial phrases, or nominal phrases. The results suggest that the preceding phrases associated with the presenting phrases promote the reading process to shorten the gazing time.

The National Institute for Japanese Language and Linguistics, Japan (NINJAL) has undertaken a corpus compilation project to construct a web corpus for linguistic research comprising ten billion words. The project is divided into four parts: page collection, linguistic analysis, development of the corpus concordance system, and preservation. This article presents the corpus concordance system named ‘BonTen’ which enables the ten-billion-scaled corpus to be queried by string, a sequence of morphological information or a subtree of the syntactic dependency structure.