Learning mechanism in machine translation system "PIVOT"
Mitsugu Miura, Mikito Hirata, Nawi Hoshino · 1992
NEC's machine translation system "PIVOT" provides analysis editing functions. The user can interactively correct errors in analysis results, such as dependency and case. However, without a learning mechanism, the user must correct similar dependency errors several times. We discuss the learning mechanism to utilize dependency and case information specified by the user. We compare four types of matching methods by simulation and show non-restricted best matching is the most effective.