تأثیر ساخت‌واژه‌ها در تجزیه وابستگی زبان فارسی

Data-driven systems can be adapted to different languages and domains easily. Using this trend in dependency parsing was lead to introduce data-driven approaches. Existence of appreciate corpora that contain sentences and theirs associated dependency trees are the only pre-requirement in data-driven approaches. Despite obtaining high accurate results for dependency parsing task in English language, for many of other languages with high free-word order and rich morphology, most applying algorithms lead to drop in accuracy compared to English language. Therefore, data-driven systems require careful selection of features and tuning of parameters to reach optimal performance. A dependency corpus for Persian language introduced recently. Persian language has high free-word order and rich morphology. In this paper we try to find detect effective factors for decreasing parsing accuracy and we present solutions to improve the accuracy.