Loading...

A Semantic Valency Lexicon for Persian Predicates and Visualization of their Relations

Salimifar, Saeedeh | 2019

504 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52646 (31)
  4. University: Sharif University of Technology
  5. Department: Languages and Linguistics Center
  6. Advisor(s): Khosravi Zadeh, Parvaneh; Shojaei, Razieh
  7. Abstract:
  8. The highest and most difficult layer of Natural Language Processing, is the understanding of meaning. As a result, lexicons and annotated corpora are of the utmost importance in this area. However, the lack of such semantic resources, especially in Abstract Meaning Representation (AMR), is one of the main issues in this field for Persian Language. This work by modeling PropBank, a semantic valency lexicon for English predicates, is the first step towards building such lexicons for Persian Language with the focus on AMR. Thus, a guideline describing how to annotate the Persian predicates is provided which first evaluates the common structures between the two languages and then focuses on the specific structures of Persian language. As a result, a new classification is presented for the pre-verbal element of the Persian Light Verb Constructions (LVCs) which divides them into the two general categories of “eventive” and “non-eventive” and later to “eventive nominal” and “eventine non-nominal” with the eventives being able to bear argument structure even outside the LVC while the non-eventives aren’t able to do so. Moreover, the current approaches to the verb “ʃodan” and passivization are examined and a new classification given the verb “ʃodan”, which fits the AMR purpose, is given. In addition, 9 modality tags are proposed for both Persian and English languages. Subjectless and impersonal constructions and control and raising verbs are also discussed and different approaches regarding AMR are proposed. With the prepared guideline, some general information such as meaning or part of speech, and semantic valencies of the predicates presented in the non-annotated corpus of “the Little Prince”, translated by “Mohammad Ghazi”, were annotated with at least one sentence containing the corresponding predicate being annotated as well to fully illustrate what each tag means. Finally, with a web-based application, visual representation of the semantic relations among the predicates is shown which indicates a predicate’s semantic valencies and its relation to other predicates with the same valency
  9. Keywords:
  10. Natural Language Processing ; Abstract Meaning Representation ; Semantic Valency ; Visual Representation ; Persian Predicates

 Digital Object List

 Bookmark

No TOC