NPFL128 Language Technologies in Practice
2024 Summer

Instructor:	Jirka Hana
e-mail:	Jirka.<my last name>@gmail.com (start the email's subject with NPFL128)
Time & Place:	Wednesday 9-10:30 S7 (ignore the part scheduled for 8:10-9:00)

 

1. Description and Objectives of the Course

The course surveys solutions to common NLP tasks ranging from entity recognition to text generation. It evaluates various approaches (machine learning, rules, larger resources, ...) and their combinations.

Most of the course consists of students presenting and discussing papers relevant to a given topic. Part of the course is also implementation of a prototype system, typically replicating one described in one of the papers.

2. Discussion

This course is organized as a discussion of important papers. Everybody reads all the papers to be able to participate in the discussion. For each paper, one student will be responsible for presenting the paper and leading the discussion.

Not every detail of each paper is important to us now. Do not present aspects that are no longer relevant (e.g., there was a lot of development in word embeddings, so there is typically no reason to discuss how a paper from 2001 handled it).

• Choose a paper and tell me which one.
• Reads all papers
• Create a Google doc document named (NPFL128 <your_name>) and share it with me. Use the same document for all papers.
• For a paper that you did not choose, write 4-8 bullets summarizing:
  • the basic idea of the paper
  • aspects of the paper you find interesting, useful in other areas, etc.
  • aspects of the paper you think could be improved
  • Do this before the paper is scheduled, and send me a notification about it.
• For the selected paper, create a presentation and send it to me by noon on the Monday before the class.

3. Project

There is one programming [Project] due on July 31 (talk to me if you cannot meet the deadline). Note that using git and Pull requests is required.

4. Grading

5. Schedule

Candidate papers

• Morphology and General approches:
• Yarowsky & Wicentowski (2000): Minimally Supervised Morphological Analysis by Multimodal Alignment
• Cucerzan & Yarowsky (2002): Bootstrapping a Multilingual Part-of-speech Tagger in One Person-day
  Cucerzan & Yarowsky (2003): Minimally Supervised Induction of Grammatical Gender
• LLM:
• Gao et al (2023): Retrieval-Augmented Generation for Large Language Models: A Survey.
• Tonmoy et al (2024): A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
• Entity recognition
• Jehangir et al (2023): A survey on Named Entity Recognition – datasets, tools, and methodologies
• Li et al (2022): A Survey on Deep Learning for Named Entity Recognition
• Nadeau & Sekine (2007): A survey of named entity recognition and classification
• Cucerzan (2007): Large-Scale Named Entity Disambiguation Based on Wikipedia Data
• Gao & Cucerzan (2017): Entity Linking to One Thousand Knowledge Bases. ECIR.
• Sentiment Analysis:
• Liu (2017): Many Facets of Sentiment Analysis
• Mohammad (2017): Challenges in Sentiment Analysis
• Evaluation:
• Ribeiro et al (2020): Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.
• Other:
• Shlens: A Tutorial on Principal Component Analysis

Discussion on	Presented by	Topic	Slides
Feb 21	me	Introduction	Zippf's law, Processing morphology
Feb 28		NO CLASS
Mar 6	Tomáš	Cucerzan & Yarowsky (2002): Bootstrapping a Multilingual Part-of-speech Tagger in One Person-day Cucerzan & Yarowsky (2003): Minimally Supervised Induction of Grammatical Gender;	slides
Mar 13		Yarowsky & Wicentowski (2000): Minimally Supervised Morphological Analysis by Multimodal Alignment
Mar 20	Michal	Liu (2017): Many Facets of Sentiment Analysis
	Anna	Mohammad (2017): Challenges in Sentiment Analysis
Mar 27	Kate	Shlens: A Tutorial on Principal Component Analysis
Apr 3	Dan	Ribeiro et al (2020): Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.
Apr 10	Danil	Gao et al (2023): Retrieval-Augmented Generation for Large Language Models: A Survey.
Apr 17	Kristýna	Tonmoy et al (2024): A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models:	slides
Apr 24	Adam	Jehangir et al (2023): A survey on Named Entity Recognition – datasets, tools, and methodologies	slides
May 1		National Holiday - NO CLASS
May 8		National Holiday - NO CLASS
May 15	Maksim	Li et al (2022): A Survey on Deep Learning for Named Entity Recognition	slides
May 22		Gao & Cucerzan (2017): Entity Linking to One Thousand Knowledge Bases. ECIR.