https://github.com/omarsar/appworks_meetup_2018
Contains all the material used for the "Applied Deep Learning for NLP Using PyTorch" meetup at AppWorks
https://github.com/omarsar/appworks_meetup_2018
cnn deep-learning neural-network nlp pytorch rnn
Last synced: 6 months ago
JSON representation
Contains all the material used for the "Applied Deep Learning for NLP Using PyTorch" meetup at AppWorks
- Host: GitHub
- URL: https://github.com/omarsar/appworks_meetup_2018
- Owner: omarsar
- Created: 2018-11-26T02:48:55.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2018-11-28T01:50:28.000Z (almost 7 years ago)
- Last Synced: 2025-03-24T18:21:25.731Z (7 months ago)
- Topics: cnn, deep-learning, neural-network, nlp, pytorch, rnn
- Language: Jupyter Notebook
- Homepage: https://www.eventbrite.com/e/applied-deep-learning-for-nlp-using-pytorch-tickets-52773928240
- Size: 4.45 MB
- Stars: 7
- Watchers: 1
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Applied Deep Learning for NLP Using PyTorch
This repository contains all the material used for the NLP meetup hosted and organized by [AppWorks](https://appworks.tw/). You can find the slides for this presentation [here](https://github.com/omarsar/appworks_meetup_2018/blob/master/Applied_Deep_Learning_for_NLP_PyTorch.pdf). Note that in order to run the notebooks in this repository you need to download a ["data"](https://drive.google.com/open?id=107WpItmepPDDddNi4_dlk-u-VuDJmRx4) folder which is missing from the repository because of file size limitations. If you have any other questions reach me through ellfae@gmail.com or directly message me on Twitter ([@omarsar0](https://twitter.com/omarsar0)).
## Event Description:
This month, AppWorks is hosting an AI meetup introducing Elvis Saravia, a deep learning & NLP researcher at NTHU, who will be sharing his knowledge about the latest trends and best practices in applied deep learning for NLP using PyTorch.
Elvis Saravia is a Ph.D. candidate at National Tsing Hua University in Taiwan. He is a Deep Learning and NLP researcher interested in building empathetic AI technologies. He has given multiple talks at venues such as PyConTW, RubyConf, PyTorch Developer Conference, and EMNLP. Elvis is the founder and editor of [dair.ai](https://medium.com/dair-ai), a popular publication that aims to communicate about the latest AI trends, technologies, research, and perspectives. He is also an educator and a top writer on Medium in the areas of Technology, Artificial Intelligence, and Innovation.
Recent advances in natural language processing (NLP) are in large part because of big data and modern deep learning techniques such as CNNs and ELMo contextualized embeddings. In this talk, we will dive deep into the best practices of applied deep learning for NLP and also discuss the recent trends. The second block of the talk will be a demo which showcases the use of tools such as Jupyter notebooks, spaCy, and PyTorch for building NLP applications, which include fine-grained sentiment analysis, neural machine translation, and phrase generation, among others.
**Language:** English
**Agenda:**
7:00pm - 8:00pm: Applied deep learning for NLP using PyTorch
8:00pm - 8:30pm: Q&A
8:30pm - 9:00pm: Mixer
**Event source:** [Link to event](https://www.eventbrite.com/e/applied-deep-learning-for-nlp-using-pytorch-tickets-52773928240)
## Meetup Format
- In the first block of the presentation I used the following [slides](https://github.com/omarsar/appworks_meetup_2018/blob/master/Applied_Deep_Learning_for_NLP_PyTorch.pdf).
- In the second block the following notebooks were discussed:
- [Abstractive Text Summarization](https://github.com/omarsar/appworks_meetup_2018/blob/master/ATS.ipynb) - the task of predicting a summary for a given piece of text using an encoder-decoder architecture.
- [Text-based Emotion Recognition](https://github.com/omarsar/appworks_meetup_2018/blob/master/Deep%20Learning%20Emotion%20Recognition%20PyTorch.ipynb) - the task of predicting the emotion conveyed in text using GRUs and embeddings.
