A dictionary for analysis to analyse contemporary written text automatically in Short Unit Words. You can use it to analyse text, such as for the following:

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

Lexicon size (UTF-8)

This is a dictionary for automated analysis of Short Unit Word transcribed text of modern spoken words. The “Corpus of Everyday Japanese Conversation (CEJC)” is used for learning, so it can be used to analyse the text according to the transcription criteria.

Criteria for transcribing CEJC can be found in the following literature:

• 臼田泰如, 川端良子, 西川賢哉, 徳永弘子, 小磯花絵: 『日本語日常会話コーパス』の転記基準について, 言語処理学 会第23回年次大会発表論文集, pp.174-177 (2017).
• 川端良子, 川端 良子, 臼田 泰如, 西川 賢哉, 徳永 弘子, 小 磯 花絵: 「日常会話コーパス」の転記基準と作業工程, 言語資源活用ワークショップ2016予稿集, pp.296-306 (2017).

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature references as needed.

Lexicon size (UTF-8)

This is a dictionary for automated Short Unit Word analysis of texts written in colloquial old kana. It can be used primarily for analysing magazine articles written in colloquial old kana.

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

This is a dictionary for automated analysis of Short Unit Word of modern essay articles. It can be used to analyse modern magazines such as Meiroku Zasshi, Taiyou, and Kokumin no Tomo.

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature references as needed.

This is an analysis dictionary for automated Short Unit Word analysis of modern spoken materials. It is primarily used to analyse stylish or personal text.

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

This is an analysis dictionary for automated short-unit analysis of medieval colloquial materials. It can be mainly used to analyse texts such as Sharebon (late Edo-period novelette about life in the red-light districts) and Ninjobon novels.

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

This is an analysis dictionary for automated Short Unit Word analysis of medieval Japanese text. You can use it to parse text, such as the following:

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

This is an analysis dictionary for automated Short Unit Word analysis of middle-old Japanese text. You can use it to parse text, such as the following:

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.

This is an analysis dictionary for automated short-unit analysis of the Man'yōshū poetry collection.

If you intend to use the product for profit, please consult the following contact points beforehand.

When publicising the results of a study conducted using this dictionary for analysis, clearly state this fact. Refer to the literature in the references as needed.