Skip to main content

NLP resources from Uni. of Edinburgh

https://wiki.inf.ed.ac.uk/MLforNLP/WebHome



Machine Learning for Natural Language Processing (ML-for-NLP)

This reading group focuses on Machine Learning techniques that may be applied to the field of Natural Language Processing. Participants are encouraged to suggest topics, papers, or tutorials (which need not involve any current application in NLP) by adding them to the lists below. Suggesting a paper does not constitute any sort of commitment to presenting that paper.
Meetings are approximately every week on Thursdays. Meetings will be in 4.02 at 3pm unless otherwise stated.
Announcements for this group will be made by email, and it is possible to sign up to the mailing list here.

News

  • No news, is good news

Tools for Research. Meeting notes

Unix Tools
The screen command. Cheatsheet, John's screen resources (John says: Note that the screen configuration files are named .screenrc and .screenrc.gen, and so you have to explicitly look for dotfiles to see them. The viewRepos.sh and launchRepositoryEditors.sh scripts are pretty specific to my directory arrangement and may need tweaking for others' setups.)
Unix for Poets by Ken Church is a nice guide to using the unix tool set: tr,grep,sort,uniq,wc,rev,sed,awk,shuf,cat,tac,tail,cut,paste,etc.
Basic stuff but super useful
-dave
LaTeX & PDFs & Bibliography Management
JabRef - bibliography management
Okular - pdf highlighting
Research organization
Large-Scale Computation
Machine learning & Coding libraries

Rota

Empty.

Paper Recommendations

Please add papers you consider appropriate for ML-for-NLP. Please also add thematic categories that are not covered.
Statistical Significance Testing
Loss Minimization
Bayesian Methods
Topic Models
Sampling Methods
Dynamical Systems
Information Theory
Variational Methods
Probabilistic Generative Models
Graphical Models
Deep learning and Energy Based Models
Language Modeling

Other Reading Groups

Useful Links

Previous meetings

Past meetings

3pm, Thursday 6th September, room 1.16 (Planning Meeting)

  • Discuss ideas for topics to be presented
  • Discuss whether or not you are happy for our meetings to become more exercise-based

3pm, Thursday 13th September, Room 3.02 (Information Theory Primer)

3pm, Thursday 20th September, Room 4.02 (Information Theory MacKay )

  • Chapter 2 of MacKay (pages 34-48 of the pdf, pages 22 -- 36 of the book), and focus on solutions:
    • Generation and inference:
      • Exercise 2.4
      • Exercise 2.5
      • Example 2.6

3pm, Thursday 27th September, room 4.02 (Information Theory MacKay )

  • Chapter 2 of MacKay (pages 34-48 of the pdf, pages 22 -- 36 of the book), and focus on solutions:
    • Bayesian predictive distribution:
      • Exercise 2.8
    • Jensen's inequality (important for all versions of EM):
      • Exercise 2.14
      • Example 2.15

3pm, Thursday 4th October, room 4.02 (Hypothesis Testing)

3pm, Thursday 18th October, room 4.02 (Variational EM)

bkj-VBwalkthrough.pdf: Variational EM

Meetings in 2011

Comments

Popular posts from this blog

Publishing business basics

Basic Steps: 1. Decide name for the company 2. Register the company with ministry - you will need an attorney (Lawyer for that) 3. Register with Registrar of News Papers in India if it's a magazine/News paper.  4. Study the relevant acts in general or get them known from the lawyer 5. Start publishing Following are details regarding the same (not that well written) : ----- Some starts and books; * Start Your Own Self-Publishing Business (Entrepreneur Magazine's Start Up) by Entrepreneur Press  * How To Start And Run A Small Book Publishing Company: A Small Business Guide To Self-Publishing And Independent Publishing by Peter I. Hupalo  * Art & Science Of Book Publishing by Herbert S., Jr. Bailey  * This Business of Books: A Complete Overview of the Industry from Concept Through Sales by Claudia Suzanne Raja Rammohun Roy National Agency for ISBN West Block-I, Wing-6, 2nd Floor, Sector -I, R.K. Puram, New Delhi-110066 Some new things and t...

ती अशीच त्याला भेटली, अगदी अचानक आलेल्या पावसासारखी

खूप पावसाळे गेले. पण अगदी अलीकडे पर्यंत त्याला पाऊस कधीच आवडलेला नव्हता. पाऊस म्हंटल की त्याला भीती वाटायची, नसती कट कट वाटायची. भिजणे तर त्याला कधीच नको वाटायचे, उगाच सर्दी ला आमंत्रण. पण मागच्या पवसाळ्यात ढग असे आले आणि पाऊस इतका पडला की तो पावसाच्या प्रेमातच पडला. पाऊस आधीही पडायचा, कदाचित असाच, इतकाच किंवा जास्त ही. पण या वेळेस मात्र पाऊस एकटा आला नाही, त्याच्या आयुष्यात सोबत घेऊन आला तिच्या केसांचा ओला सुगंध. ती अशीच त्याला भेटली, अगदी अचानक आलेल्या मुंबईतल्या पावसासारखी, चिंब भिजलेली. त्याला ती आवडली आणि म्हणून पाऊस ही. ती त्याला पुन्हा भेटली, न ठरवून, अशीच पुन्हा एकदा अचानक पावसाराखीच. ते बोलले, थांबले, विसावले. ती समोर आली तेंव्हा पाऊस नव्हताच, ती अजून थोडी जवळ आली तेंव्हा ही पाऊस नव्हता. तो तिच्याकडे सारखा पहातच होता, पण नजर चोरून. आयुष्यात पहिल्यांदा त्याने पावसाकडे येण्याची विनवणी केली. आशेच्या नजरेने त्याने ढगांकडे पाहिले. ढग होते, पण अजून पाऊस मात्र नव्हता. तरी ही आजूबाजूंच्या झाडात, डोंगरात, फुलात आणि पाखरात ओलावा होताच. त्याच्या विनवनीने अखेर तो आला. रिम-झिम, रिम-झिम...

NVDIA AI India

 NVDIA AI some Insights after digesting the event with some Diwali Delicacies! I had good time at the NVIDIA AI Summit held at the Jio World Center in Mumbai. It felt like every company working on artificial intelligence in India was present, either as an exhibitor or an attendee. Some sessions were so packed that people were standing, and even then, many more were trying to get in. Much of the discussion revolved around Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). These are undoubtedly central topics in AI today, drawing significant attention. I’m a huge admirer of RAG, but I still wouldn’t go as far as to say that “LLM (+RAG) is AI.” Although no one at the conference explicitly said this, it felt implied over the three days of sessions. I may be wrong, but I sensed a push for these technologies. Not just from NVIDIA, but from any hardware supplier, there’s an incentive to promote anything that drives demand for their solutions. NVIDIA’s GPUs are a backbo...