Latent Features in Automatic Tense Translation between Chinese and English

On the task of determining the tense to use when translating a Chinese verb into English, current systems do not perform as well as human translators. The main focus of the present paper is to identify features that human translators use, but which are not currently automatically extractable. The goal is twofold: to test a particular hypothesis about what additional information human translators might be using, and as a pilot to determine where to focus effort on developing automatic extraction methods for features that are somewhat beyond the reach of current feature extraction. The paper shows that incorporating several latent features into the tense classifier boosts the tense classifier’s performance, and a tense classifier using only the latent features outperforms one using only the surface features. Our findings confirm the utility of the latent features in automatic tense classification, explaining the gap between automatic classification systems and the human brain.