|
1 | | -[insert some sort of preview or teaser to reel in your audience!] |
| 1 | + |
| 2 | + |
2 | 3 |
|
3 | | -# NLP Workshop Series |
4 | 4 | The official ACM AI NLP Workshop Series repository. |
5 | 5 |
|
6 | 6 | ## Table of Contents: |
7 | 7 |
|
8 | 8 | <div class="alert alert-block alert-info"> |
9 | | -<ul> |
10 | | - <li>1. <a href="#1.-file-directory-structure">File Directory Structure</a></li> |
11 | | - <li>2. <a href="#2.-dataset">Dataset</a></li> |
12 | | - <li>3. <a href="#3.-getting-started">Getting Started</a> |
13 | | - <ul> |
14 | | - <li>3.1. <a href="#3.1.-workshop-1-basics-of-nlp">Workshop 1 Basics of NLP</a></li> |
15 | | - <li>3.2. <a href="#3.2.-workshop-2-more-advanced-nlp-models">Workshop 2 More Advanced NLP Models</a></li> |
16 | | - <li>3.3. <a href="#3.3.-workshop-3-transformers">Workshop 3 Transformers</a></li> |
17 | | - </ul> |
| 9 | +<ol> |
| 10 | + <li><a href="#1-file-directory-structure">File Directory Structure</a></li> |
| 11 | + <li> |
| 12 | + <a href="#2-datasets">Datasets</a> |
| 13 | + <ul type="none"> |
| 14 | + <li><a href="#21-workshop-1">2.1 Workshop 1</a></li> |
| 15 | + <li><a href="#22-workshop-2">2.2 Workshop 2</a></li> |
| 16 | + <li><a href="#23-workshop-3">2.3 Workshop 3</a></li> |
| 17 | + </ul> |
18 | 18 | </li> |
19 | | - <li>4. <a href="#4.-resources">Resources</a></li> |
20 | | - <li>5. <a href="#5.-meeting-notes">Meeting Notes</a></li> |
21 | | - <li>6. <a href="#6.-author-info">Author Info</a></li> |
22 | | -</ul> |
| 19 | + <li> |
| 20 | + <a href="#3-getting-started">Getting Started</a> |
| 21 | + <ul type="none"> |
| 22 | + <li><a href="#31-workshop-1-basics-of-nlp">3.1 Workshop 1: Basics of NLP</a></li> |
| 23 | + <li><a href="#32-workshop-2-rnns-for-multiclassification">3.2 Workshop 2: RNNs for Multiclassification</a></li> |
| 24 | + <li><a href="#33-workshop-3-seq2seq-for-machine-translation">3.3 Workshop 3: Seq2Seq for Machine Translation</a></li> |
| 25 | + </ul> |
| 26 | + </li> |
| 27 | + <li> |
| 28 | + <a href="#4-resources">Resources</a> |
| 29 | + <ul type="none"> |
| 30 | + <li><a href="#41-workshop-1">4.1 Workshop 1</a></li> |
| 31 | + <li><a href="#42-workshop-2">4.2 Workshop 2</a></li> |
| 32 | + <li><a href="#43-workshop-3">4.3 Workshop 3</a></li> |
| 33 | + </ul> |
| 34 | + </li> |
| 35 | + <li><a href="#5-author-info">Author Info</a></li> |
| 36 | +</ol> |
23 | 37 | </div> |
24 | 38 |
|
25 | 39 | # 1. File Directory Structure |
26 | 40 |
|
27 | 41 | ```bash |
28 | | -NLP-SERIES |
29 | | - | -- Meeting-Notes |
30 | | - | | -- 4/15 |
31 | | - | | -- ... |
32 | | - | |
33 | | - | -- workshop-1 |
34 | | - | | -- README.md |
35 | | - | | ... |
36 | | - | |
37 | | - | -- workshop-2 |
38 | | - | | -- README.md |
39 | | - | | ... |
40 | | - | |
41 | | - | -- workshop-3 |
42 | | - | | -- README.md |
43 | | - | | ... |
44 | | - | |
45 | | - | README.md |
| 42 | +nlp-series |
| 43 | + | -- workshop-1 |
| 44 | + | | -- [Workshop 1 Resources] |
| 45 | + | |
| 46 | + | -- workshop-2 |
| 47 | + | | -- [Workshop 2 Resources] |
| 48 | + | |
| 49 | + | -- workshop-3 |
| 50 | + | | -- [Workshop 3 Resources] |
| 51 | + | |
| 52 | + | -- NLP_Main_Header_Dark.png |
| 53 | + | -- NLP_Main_Header_Light.png |
| 54 | + | -- README.md |
46 | 55 | ``` |
47 | 56 |
|
48 | | -# 2. Dataset |
| 57 | +# 2. Datasets |
| 58 | + |
| 59 | +## 2.1 Workshop 1 |
| 60 | +- [Twitter Sentiment Analysis Hatred Speech](https://www.kaggle.com/datasets/arkhoshghalb/twitter-sentiment-analysis-hatred-speech) by arkhoshghalb |
| 61 | + |
| 62 | +## 2.2 Workshop 2 |
| 63 | +- [Emotions Dataset for NLP](https://www.kaggle.com/datasets/praveengovi/emotions-dataset-for-nlp) by Praveen |
| 64 | + |
| 65 | +## 2.3 Workshop 3 |
| 66 | +- [English to French Translations](http://www.manythings.org/anki) from the Tatoeba Project |
49 | 67 |
|
50 | | -- [Twitter Sentiment Analysis Hatred Speech](https://www.kaggle.com/datasets/arkhoshghalb/twitter-sentiment-analysis-hatred-speech) by arkhoshghalb is the dataset we use across all 3 workshops. |
51 | 68 |
|
52 | 69 | # 3. Getting Started |
53 | 70 |
|
54 | | -## 3.1. Workshop 1 Basics of NLP |
| 71 | +## 3.1. Workshop 1: Basics of NLP |
55 | 72 |
|
56 | 73 | Have you ever wondered how Siri learns your interests, or how Twitter filters hate speech? ACM AI’s Natural Language Processing (NLP) Workshop series is a series of interactive, in-person demos covering the ins and outs of NLP! In our first workshop, we’ll learn the uses and practice the basics of NLP through interactive Colab notebooks that you can bring home to experiment with. By the end, you’ll know how to apply the models you learn to classify any text you want. |
57 | 74 |
|
58 | | -## 3.2. Workshop 2 More Advanced NLP Models |
| 75 | +## 3.2. Workshop 2: RNNs for Multiclassification |
| 76 | + |
| 77 | +This workshop is about Recurrent Neural Networks for NLP for detecting emotions in a multi-class dataset. This workshop is self-contained from the first and covers RNNs from the ground up! |
59 | 78 |
|
60 | | -[Insert description & other important README information here.] |
| 79 | +## 3.3. Workshop 3: Seq2Seq for Machine Translation |
61 | 80 |
|
62 | | -## 3.3. Workshop 3 Transformers |
| 81 | +Language Translation is a ubiquitous topic of Modern Natural Language Processing, and the AI that powers language translation is critical to creating a world where we can break down communication barriers between communities that speak different languages. |
| 82 | + |
| 83 | +By the end of this workshop, the reader will have a working Language Translation model similar to Google Translate! |
63 | 84 |
|
64 | | -[Insert description & other important README information here.] |
65 | 85 |
|
66 | 86 | # 4. Resources |
67 | 87 |
|
68 | | -- [Melanie Walsh Text Analysis Tutorial](https://melaniewalsh.github.io/Intro-Cultural-Analytics/05-Text-Analysis/04-Sentiment-Analysis.html#) is a great scaffolding for our first workshop. |
69 | | -- [NeuromatchAcademy's Text Analysis Tutorial](https://github.com/NeuromatchAcademy/course-content-dl/tree/main/tutorials) provides another skeleton for our first workshop. |
70 | | -- [Arth's Colab Notebooks](https://drive.google.com/drive/folders/1y7R_lD8-OAyMD6oecoShiDl23ke5Nai0) is the 3rd reference for a table of contents for our first workshop. |
| 88 | +Note: All figures made by [Arth Shukla](#5-author-info) with the exception of [NLPW3_Fig4a](./workshop-3/figures/NLPW3_Fig4a.png) from [*Understanding LSTM Networks*](https://colah.github.io/posts/2015-08-Understanding-LSTMs/) by Christopher Olah. |
71 | 89 |
|
72 | | -# 5. Meeting Notes |
| 90 | +## 4.1 Workshop 1 |
73 | 91 |
|
74 | | -Meeting notes kept on 1 rolling document located [here](https://docs.google.com/document/d/1UKkSFjyYP_txn-A7Lig2tjfwcZqNEzux6DfYdCZAM4U/edit#). |
| 92 | +Each of the following covers a similar topic to our first workshop: |
| 93 | +- [Melanie Walsh Text Analysis Tutorial](https://melaniewalsh.github.io/Intro-Cultural-Analytics/05-Text-Analysis/04-Sentiment-Analysis.html#) |
| 94 | +- [NeuromatchAcademy's Text Analysis Tutorial](https://github.com/NeuromatchAcademy/course-content-dl/tree/main/tutorials) |
| 95 | +- [Arth's Inspirit AI Colab Notebooks](https://drive.google.com/drive/folders/1y7R_lD8-OAyMD6oecoShiDl23ke5Nai0) |
75 | 96 |
|
76 | | -# 6. Author Info |
| 97 | +## 4.2 Workshop 2 |
| 98 | + |
| 99 | +We base our second workshop on the following notebook: |
| 100 | +- [Emotion Classification (NLP)](https://www.kaggle.com/code/dorgavra/emotion-classification-nlp/notebook) by Dor Gavra |
| 101 | + |
| 102 | +## 4.3 Workshop 3 |
| 103 | + |
| 104 | +We base our code on the following example tutorial: |
| 105 | +- [Keras NLP Character-Level Seq2Seq RNN Model](https://keras.io/examples/nlp/lstm_seq2seq/) |
| 106 | + |
| 107 | +We also base many of our explanations on the following resources: |
| 108 | +- [*Encoder-Decoder Seq2Seq Models, Clearly Explained!!*](https://medium.com/analytics-vidhya/encoder-decoder-seq2seq-models-clearly-explained-c34186fbf49b) by Kriz Moses |
| 109 | +- [*A Simple Introduction to Sequence to Sequence Models*](https://www.analyticsvidhya.com/blog/2020/08/a-simple-introduction-to-sequence-to-sequence-models/#:~:text=Sequence%20to%20Sequence%20) from Analytics Vidhya |
| 110 | +- [*What is Teacher Forcing for Recurrent Neural Networks?*](https://machinelearningmastery.com/teacher-forcing-for-recurrent-neural-networks/) by Jason Brownlee |
| 111 | +- [*Understanding LSTM Networks*](https://colah.github.io/posts/2015-08-Understanding-LSTMs/) by Christopher Olah for [NLPW3_Fig4a](./workshop-3/figures/NLPW3_Fig4a.png) |
| 112 | + |
| 113 | + |
| 114 | +# 5. Author Info |
77 | 115 |
|
78 | | -- Vincent Tu: [LinkedIn](https://www.linkedin.com/in/vincent-tu-422b18208/) | [GitHub](https://github.com/alckasoc) |
79 | 116 | - Arth Shukla: [LinkedIn](https://www.linkedin.com/in/arth-shukla/) | [GitHub](https://github.com/arth-shukla) |
80 | | -- Jackie Piepkrn: [LinkedIn](https://www.linkedin.com/in/jackie-piepkorn-70295418a/) |
| 117 | +- Jackie Piepkorn: [LinkedIn](https://www.linkedin.com/in/jackie-piepkorn-70295418a/) | [GitHub](https://github.com/jackiepiepkorn) |
| 118 | +- Vincent Tu: [LinkedIn](https://www.linkedin.com/in/vincent-tu-422b18208/) | [GitHub](https://github.com/alckasoc) |
0 commit comments