Posts
Practical Time Series - from ARIMA to Deep Learning (Part 1)
time-seriesToday we are going to talk about time series and forecasting! Forecasting is the use of a predictive model to predict future values based on previously observed values and meaningful characteristics of the time series data. It has application in various industries and use cases such as finance, retail, marketing and even anomaly detection for system outage.
Why some linguistics is necessary for NLP
nlpDisclaimer: I’m no means an expert in linguistics and below is the opinion of my personal research. Feel free to correct me.
Backprop, Autograd and Squeezing in larger batch using PyTorch
deep-learning machine-learningBackprogation is a beautiful play of derivatives which we have taken for granted. We often do a simple one-liner:
Crossing the language barrier with NLP
machine-learning nlpOne of the biggest open problems in NLP is the unavailability of many non-English dataset. Dealing with low-resource/low-data setting can be quite frustrating when it seems impossible to transfer the same success we saw in various English NLP tasks. In fact, there are voices within the NLP community to advocate research and focus on low-resource language instead of spending the effort on beating the benchmark.
Fine Tuning OpenAI GPT for Sentence Summarization
deep-learning nlpTransfer learning is on the rage for 2018, 2019, and the trend is set to continue as research giants shows no sign of going bigger.
Model building and performance tips for PyTorch
deep-learningHere are some key observations and lessons learned from building a brand new Seq-to-Seq model for sentence summarization and training it against a 1 million samples dataset.
Transfer learning and beyond
deep-learning nlpTransfer learning has proven to be useful in NLP in the recent years. As many called the “Imagenet moment” when the likes of large pretrained language models such as BERT, GPT, GPT2 have sprung out from the big research labs, they have been extended in various methods to achieve further state of the art results on a wide range of NLP tasks.
AWS DeepRacer - Getting Rolling on Reinforcement Learning
reinforcement-learningWhat is the AWS DeepRacer?
Recent Advances in Abstractive Summarization Using Deep Learning Part 2
deep-learning nlpThis post is a continuation to the previous post here.
Recent Advances in Abstractive Summarization Using Deep Learning
deep-learning nlpThere has been a lot of advances in NLP and abstractive text summarization in these couple of years. While the first method that comes to our mind is deep learning, there are actually a lot more different ways to model the abstract representation of the text.