课程： Linguistic Resources for Natural Language Processing (STU0674) - Bosco/Patti - 2024/2025

主题目录

Information about classes and exams

全部折叠展开全部
- Annunci 讨论区
- NEW Announcement! SECOND PART of the course (Prof. Viviana Patti)
  The second part of the course will START on November 18 2024, at 2pm in Aula 3.06 Thin Client - Via Sant'Ottavio 54 - Torino.
  There will be no lesson on November 11,12 and 13, 2024
  Classes are designed for in-person attendance, not streamed nor recorded since recording or streaming could significantly lower their quality. Those who could not participate can consult the material on Moodle and in case of doubts consult the teacher if clarifications are needed.
  
  The Moodle page for the course will remain open to guests until the end of September.
- Information: classes, exams and topics (slides) 文件
- The 2025's dates of the exams of this course are as follows:
  January 14
  February 4
  April 3
  June 17 and 30
  July 15
  September 11
  October 30
  Each student must carefully check the dates (they can be changed) and register for the selected date for taking the exam.
Part ONE - lesson 1: September 16
- Introduction - PART 1 (slides) 文件
Part ONE - Lesson 2: September 17
- Introduction - PART 2 (slides) 文件
- Ambiguity, models and resources (slides) 文件
Part ONE - Lesson 3: September 18
Part ONE - Lesson 4: September 23
Part ONE - Lesson 5: September 24
Part ONE - Lesson 6: September 25
Part ONE - Lesson 7: September 30
- Exercises on constituency-based syntax 文件
- Syntax and constituency (slides) 文件
Part ONE - Lesson 8: October 1
Part ONE - Lesson 9: October 2
- Choice your group! 小组选择
  
  Opened: 2024年10月2日星期三 08:45
  
  Closes: 2024年10月9日星期三 13:00
- Tools for the generation and visualization of syntactic trees (slides) 文件
- Indications for the talk 文件
Part ONE - Lesson 10: October 7
- Reminder: Please select your team for the talk as soon as possible (using the link "Choice your group!" in lesson 9 section). The DEADLINE is October 9 at 1 pm.
- Exercise on the development of a linguistic resource 文件
- Development of a sample resource + Inception survival guide (slides) 文件
Part ONE - Lesson 11: October 8
- Development of resources and classification of corpora (slides) 文件
Part ONE - Lesson 12: October 9 - Seminar "VALICO-UD: ANNOTATING AN ITALIAN LEARNER CORPUS" by Elisa Di Nuovo
- Exercise on Inception: correction of the errors 文件
- Seminar on VALICO-UD (slides) 文件
Part ONE - Lesson 13: October 14
- Evaluation - Part 1 (slides) 文件
- Evaluation - Part 2 (slides) 文件
Part ONE - Lesson 14: October 15 - Seminar "RESOURCES FOR ANCIENT LANGUAGES" by Francesco Mambrini
- Inception: how to provide correct input 文件
Part ONE - Lesson 15: October 16
- Consortia, evaluation campaigns and resources 文件
Part ONE - Lesson 16: October 21 >>>> talks
- Multilingualism in NLP 文件
- Talks of the following teams: Italian-ONE, Chinese-ONE, English-ONE, French-ONE
Part ONE - Lesson 17: October 22 >>>> talks
- Talks of the following teams: PersianNLP, Spanish-ONE, Italian-TWO, Sicilian-ONE
Part ONE - Lesson 18: October 23 >>> talks
- Talks of the following teams: Russian-ONE, Italian-THREE, Italian-FOUR
- Indications for the oral part of the exam (includes the list of questions) 文件
- For those who are interested in more information about specific phenomena discussed in some topics and especially occurring in unformal register texts, the following reading can be a good starting point: Sanguinetti, Bosco, Cassidy et al - (2023) "Treebanking user-generated content: a UD based overview of guidelines, corpora and unified recommendations". Language Resources & Evaluation (2023) 57:493–544 (https://link.springer.com/content/pdf/10.1007/s10579-022-09581-9.pdf)
Part TWO - Week 1: November 18, 19,20
- Introduction to the course (II part) :: Love and Hate in the Time of Social Media 文件
Part TWO - Week 2: November 25
Part TWO - Week 3: December 2,3,4
- Developing corpora for sentiment analysis: main steps 文件
- Developing corpora for abusive language detection: focus on Abusive language / Hate speech et similia 文件
- Project Work 2 (PW2): Recognizing cancelling attitudes
- PW2 (Lab): Recognizing cancelling attitudes: an annotation task by Marco Antonio Stranisci 网页地址
PART TWO - Week 4: December 9,10,11
PART TWO: Week 5: December 16,17,18
- Viviana Patti WebEX Room 网页地址
- Emoji, emoticons, reactions in social media: A computational linguistics perspective 文件
- Project Work 1 (PW1): Annotating a Social Media Corpus (Tweets) with Hate Speech, Stance and Irony
- LR4NLP 24-25 - Survey 1: Annotator profile 网页地址
- Annotation - Agreement, Disagreement, Perspectives (slides) by Marco Madeddu 网页地址
  
  Introduction to Project Work One (PW1) for the exam (slides)
- Practice!
- Dataset to be downloaded 网页地址
- Dataset to be dowloaded (file .tsv) 文件
Happy Xmas Break and Happy New Year! 🌸🌱
PART TWO: Week 6: January 7,8,9 2025
FINAL EXAM for PART TWO (V. PATTI)
- The evaluation for the second part of the course will consist in a Project Work on the development of annotated corpora and analysis, to be implemented by following the instructions described in the following document:
- Instructions for the second part of the exam (Prof. V. Patti) 网页地址
Upload data report for the project work (V. Patti)
- Upload data and report for the project work (V. Patti). Exam Date: January 14, 2024 作业
  
  打开： 2025年01月4日星期六 00:00
  
  到期日： 2025年01月12日星期日 23:59
  
  Click here to upload a single .zip file containing all the files requested for the project work (data and report, see the instruction published below for PART TWO).
  Please, give the file the name of your group. It is expected that the contact person for the group will upload the file.
  Important: please start the report with a sort of 'cover page' including the name of the group and all the names of the group members that contributed to the report. The cover page will be considered extra w.r.t. the page limit.
  Please check carefully that the .zip file contains all the necessary files before uploading it. In the unfortunate event that you find you have to re-upload it, contact the teacher.

Linguistic Resources for Natural Language Processing (STU0674) - Bosco/Patti - 2024/2025

主题目录

Information about classes and exams

Part ONE - lesson 1: September 16

Part ONE - Lesson 2: September 17

Part ONE - Lesson 3: September 18

Part ONE - Lesson 4: September 23

Part ONE - Lesson 5: September 24

Part ONE - Lesson 6: September 25

Part ONE - Lesson 7: September 30

Part ONE - Lesson 8: October 1

Part ONE - Lesson 9: October 2

Part ONE - Lesson 10: October 7

Part ONE - Lesson 11: October 8

Part ONE - Lesson 12: October 9 - Seminar "VALICO-UD: ANNOTATING AN ITALIAN LEARNER CORPUS" by Elisa Di Nuovo

Part ONE - Lesson 13: October 14

Part ONE - Lesson 14: October 15 - Seminar "RESOURCES FOR ANCIENT LANGUAGES" by Francesco Mambrini

Part ONE - Lesson 15: October 16

Part ONE - Lesson 16: October 21 >>>> talks

Part ONE - Lesson 17: October 22 >>>> talks

Part ONE - Lesson 18: October 23 >>> talks

Part TWO - Week 1: November 18, 19,20

Part TWO - Week 2: November 25

Part TWO - Week 3: December 2,3,4

Project Work 2 (PW2): Recognizing cancelling attitudes

PART TWO - Week 4: December 9,10,11

PART TWO: Week 5: December 16,17,18

Project Work 1 (PW1): Annotating a Social Media Corpus (Tweets) with Hate Speech, Stance and Irony

Project Work 1 (PW1): Annotating a Social Media Corpus (Tweets) with Hate Speech, Stance and Irony

Happy Xmas Break and Happy New Year! 🌸🌱

PART TWO: Week 6: January 7,8,9 2025

FINAL EXAM for PART TWO (V. PATTI)

Upload data report for the project work (V. Patti)