tailieunhanh - Báo cáo khoa học: "Machine-Learning-Based Transformation of Passive Japanese Sentences into Active by Separating Training Data into Each Input Particle"

Masaki Murata National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0289, Japan murata@ Tamotsu Shirado National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0289, Japan shirado@ Abstract We developed a new method of transforming Japanese case particles when transforming Japanese passive sentences into active sentences. It separates training data into each input particle and uses machine learning for each particle. We also used numerous rich features for learning. Our method obtained a high rate of accuracy (). In contrast, a method that did not separate training data for any input particles obtained a. | Machine-Learning-Based Transformation of Passive Japanese Sentences into Active by Separating Training Data into Each Input Particle Masaki Murata National Institute of Information and Communications Technology 3-5 Hikaridai Seika-cho Soraku-gun Kyoto 619-0289 Japan murata@ Tamotsu Shirado National Institute of Information and Communications Technology 3-5 Hikaridai Seika-cho Soraku-gun Kyoto 619-0289 Japan shirado@ Abstract We developed a new method of transforming Japanese case particles when transforming Japanese passive sentences into active sentences. It separates training data into each input particle and uses machine learning for each particle. We also used numerous rich features for learning. Our method obtained a high rate of accuracy . In contrast a method that did not separate training data for any input particles obtained a lower rate of accuracy . In addition a method that did not have many rich features for learning used in a previous study Mu-rata and Isahara 2003 obtained a much lower accuracy rate . We confirmed that these improvements were significant through a statistical test. We also conducted experiments utilizing traditional methods using verb dictionaries and manually prepared heuristic rules and confirmed that our method obtained much higher accuracy rates than traditional methods. 1 Introduction This paper describes how passive Japanese sentences can be automatically transformed into active. There is an example of a passive Japanese sentence in Figure 1. The Japanese suffix reta functions as an auxiliary verb indicating the passive voice. There is a corresponding active-voice sentence in Figure 2. When the sentence in Figure 1 is transformed into an active sentence i ni by which is a case postpositional particle with Toshiyuki Kanamaru National Institute of Information and Communications Technology 3-5 Hikaridai Seika-cho Soraku-gun Kyoto 619-0289 Japan kanamaru@ Hitoshi Isahara National .

• Báo cáo khoa học
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên