Loading...

Temporal Relation Extraction of Persian Texts by Learning Methods

Zandie, Roholla | 2015

513 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47496 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Ghasem Sani, Gholamreza
  7. Abstract:
  8. To fully understanding a text written in a natural language, we need to comprehend the events within that text. Temporal relation extraction always have been one of the main challenges in natural language processing in semantic level. Temporal relation extraction makes the understanding and interpretation of text easier and the extracted information can be used in many natural language systems like question answering, summarization, and information retrieval systems. Early researches on temporal relation extraction was mainly on English and limited to rule based systems. However, with extending the English corpora and availability of temporal corpora in other languages, more attention has been paid to machine learning methods. On the other hand, with the introduction of the TempEval competition as a subfield of SemEval, the research on temporal information extraction has been made more organized and disciplined. In this dissertation, we first designed and developed an automatic tagger for finding events. Then the output of this tagger corrected and temporal relations have been added to the corpus. First aim of this tagging has been the development of a Persian corpus of temporal information. In all of the tagging stages, the ISO-TimeML standard has been adopted. After extending the corpus, a system for recognizing the temporal relations based on different classifiers have been developed and these classifiers performance have been compared. Conditional random fields, Maximum entropy, Support vector machines, and Naïve Bayes are the classifiers used in this project and the best result achieved belongs to the conditional random fields. Finally, our best results have been compared to the one previous work on temporal relation extraction in Persian
  9. Keywords:
  10. Temporal Relation Classification ; Event Extraction ; Information Retrieval ; Persian Texts ; Automatic Tagging

 Digital Object List

 Bookmark

No TOC