1 / 19

بسم الله الرحمن الرحيم ICS 482 Natural Language Processing

بسم الله الرحمن الرحيم ICS 482 Natural Language Processing. Lecture 24: Project Ideas + Students Presentations Husni Al-Muhtaseb. Students Presentations. Evaluation at WebCT Presentation file and Document word file Submit through webct assignment ‘Presentation Material’

maris-wolfe
Download Presentation

بسم الله الرحمن الرحيم ICS 482 Natural Language Processing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. بسم الله الرحمن الرحيمICS 482 Natural Language Processing Lecture 24: Project Ideas + Students Presentations Husni Al-Muhtaseb

  2. Students Presentations • Evaluation at WebCT • Presentation file and Document word file • Submit through webct assignment • ‘Presentation Material’ • as soon as you present your lecture

  3. Student Presentation Files • Summary of your lecture • References • Obstacles faced • Things learned and skills practiced • recommendation • Three true/ false questions • addressing the main issues with answers for possible inclusion in the exam

  4. Students Presentations • Evaluation at WebCT • Presentation file and Summary word file • Submit through webct assignment • ‘Presentation Material’ • as soon as you present your lecture • Sunday, May 13 • Al-Elaiwi Moh'd - Diacritization: A Challenge to Arabic Treebank Annotation and Parsing   • Naif Al-Abdulhay - The Challenge Of Arabic For NLP/MT   • Abdul Rahman Al Khaldi - Statistical Transliteration for English-Arabic Cross

  5. Online Instructor Evaluation • Reminder: • Online Course and Instructor Evaluation

  6. Some Projects • Arabic POS Tagger • Specific Information Picker • An Arabic morphological analyzer • An Arabic Spell checker w/ morphology analysis • An Arabic Syntax analyzer • Random syntactically-correct Arabic sentence generator

  7. Some more Projects • An English to Arabic machine translation using word re-ordering • Moh’d Ones on WebCt

  8. Plain Arabic Text Training Corpus ManTag DataExtract Probability Matrix Lexicons Untagged Arabic Corpus Tagged Corpus APT Arabic POS Tagger

  9. Specific Information Picker • Given a list of links to English newspapers/ sites, find all pages that are talking about Saudi Arabia and send them to an automatic translator

  10. An Arabic morphological analyzer • Invited Lecture by Yousuf Al-Uraini • Implementation of Buckwalter’s AraMorph on C# • Code in Java is available at supplementary material of the website

  11. An Arabic Spell checker • Spell checker for Arabic text including morphology analysis

  12. An Arabic Syntax analyzer • We Have comprehensive rules such as الجملة البحتة الاسمية البسيطة (ب ا ب): تـعــريــف: هي جملة صحيحة التركيب تبدأ باسم وتخلو من أية أداة وتشكل جملة واحدة فقط التــركــيـب: <ب ا ب>  <مبتدأ (حالة , جنس)> <خبر حالة جنس)> <أسلوب إغراء> <أسلوب تحذير>

  13. Syntax analyzer – Example of rules <حالة = ح>  <إفراد> <تثنية> <جمع> <جنس = س>  <تذكير> <تأنيث>

  14. Syntax analyzer – Example of rules <مبتدأ ح,س>  <اسم علم ح,س> <مبتدأ ح,س غير علم> <اسم إشارة ح,س> <مبتدأ ح,س غير إشارة> <اسم ح,س معرف يأل> <مبتدأ ح,س> <مضاف> <مبتدأ ح,س> <ضمير مفرد ح,س> <مبتدأ ح,س غير ضمير> <اسم من الأسماء الستة ح,س> <مبتدأ ح,س ليس من الأسماء الستة> <اسم عدد من ثلاثة إلى عشرة> <تمييز جمع>

  15. Random syntactically-correct Arabic sentence generator • Randomly generate Arabic sentences that have correct syntax according to the given grammar

  16. English to Arabic machine translator • Given an English sentence translate to Arabic using lexicon and word ordering technique • Example next page

  17. English to Arabic Machine Translation • Salma came • Lexicon • Salma:مفرد، ..سلمى، اسم علم، مؤنث، • Came: جاء، فعل، ماض، متعادل ... • Word to word: سلمى جاء • Needed Translation: جاءت سلمى • Modification Rules • Exchange the positions of subject and verb • If the gender is feminine the verb should be the same

  18. Moh’d Ones on WebCt • Generates complete well-formed sentences from a user input of uninflected content words .e.g. like you give the system verb, noun, ...etc and the system will construct the sentence • Makes use of a bilingual corpus to perform word sense disambiguation • Detects proper nouns, nouns, verbs, etc... in text(s) • Intelligent Word Prediction uses knowledge of syntax and word frequencies to predict the next word in a sentence as the sentence is being entered, and updates this prediction as the word is typed

  19. Thank you • السلام عليكم ورحمة الله

More Related