Loading...

Ezafe Recognition Using Dependency Parsing

Nassajian, Minoo | 2019

654 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51600 (31)
  4. University: Sharif University of Technology
  5. Department: Languages and Linguistics Center
  6. Advisor(s): Bahrani, Mohammad; Shojaei, Razieh
  7. Abstract:
  8. Ezafe is regarded as one of the most controversial and challenging issues in different Persian Language Processing (NLP) fields. It is recognized and pronounced but usually not written. So, this results in a high degree of ambiguity in Persian texts. Dependency grammar plays a significant role in optimization problems. So, to recognize the position of Ezafe in a sentence, this grammar is used in this current study. This method helps speed up computer operations and use low memory. Within this framework, first we take a close look at Ezafe distribution in Persian text. We use Uppsala Persian Dependency Corpus (2015) to analyze parsed sentences. The Ezafe constructions under study include nonverbal phrasal categories. Only eight simple Ezafe insertion rules are formulated to cover all cases of Ezafe occurrence which can be used in different NLP tasks which apply dependency parsing. To evaluate the rules, the Uppsala Persian Dependency test corpus is used. Three cases of the test corpus are considered to evaluate the performance of the proposed method: The first one is viewed as the gold corpus that both part-of-speech (POS) and dependency tags are gold. In the second case, only POS tags are gold. The third case contains sentences without POS and dependency tags. Sententecs are tagged in the second and third cases using a POS tagger and Dependency parser. The F-measure scores are 97.05%, 94.73%, and 93.77% respectively
  9. Keywords:
  10. Ezafe ; Ezafe Construction ; Dependency Grammar ; Persian Text Processing

 Digital Object List

 Bookmark

No TOC