/
Final Project Kai-Wei Chang Final Project Kai-Wei Chang

Final Project Kai-Wei Chang - PowerPoint Presentation

CuddleBunny
CuddleBunny . @CuddleBunny
Follow
342 views
Uploaded On 2022-08-03

Final Project Kai-Wei Chang - PPT Presentation

CS UCLA kwkwchangnet Couse webpage httpsuclanlpgithubioCS26917 1 ML in NLP Requirement students 4 group project rubric 5 Proposal 25 Final report 10 presentation ID: 933736

https nlp data uclanlp nlp https uclanlp data pdf final github split error analysis research cs269 report webpage implement

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "Final Project Kai-Wei Chang" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Slide1

Final Project

Kai-Wei ChangCS @ UCLAkw@kwchang.netCouse webpage: https://uclanlp.github.io/CS269-17/

1

ML in NLP

Slide2

Requirement

#students: 4, group projectrubric5% Proposal25% Final report

10% presentation

 

ML in NLP

2

Slide3

Final Report

Can be in PDF format, a jupyter notebook, or a webpage. Less than 4 pages. ML in NLP3

Slide4

Project types

List of potential ideas: https://goo.gl/W9RuoZShared taskResearch projectNLP/ML applicationsLiterature survey / Reimplementing

Building a library / Demo

ML in NLP

4

Slide5

General Steps

Define your taskHow to evaluate?Where to get data/ how to split data (use pre-split data is possible) / Define your evaluation metricUnderstand your problem

Implement simple baseline and/or existing approaches Error analysis (e.g.,

https

://

arxiv.org/pdf/1606.02858v2.pdf

)

ML in NLP

5

Slide6

General Steps

Implement a non-trivial approachSanity check / Unit testing / Parameter tuningAnalysis Error analysis / Discussion/ Ablation study / Visualization

Improve your approach

ML in NLP

6

Slide7

Useful tools

https://uclanlp.github.io/CS269-17/resourceMachine learning toolbox:Scikit learn, Pytorch,

DyNet, TensorflowNLP toolbox:

NLTK

,

SpyCy

ML in NLP

7

Slide8

Paper summary

Individual projectPick a paper from ACL, EMNLP, NIPS, ICML, UAI, AAAI, … Example: https://www.salesforce.com/products/einstein/ai-research/tl-dr-reinforced-model-abstractive-summarization/https://research.googleblog.com/2017/08/transformer-novel-neural-network.html

https://github.com/uclanlp/reducingbias/blob/master/src/fairCRF_gender_ratio.ipynb

ML in NLP

8