We have many public platforms and social media platforms for communications, exchange/share of information, expressing feelings, etc… There are many state-of-the-art NLP tasks that run on the text data available on these public or social media platforms, but the test data is not up to the distribution of standard English language which affects the performance of the said tasks. So here we take the input sentence which is corrupted and project it to the target sentence which is in the distribution of standard English. By using this we can improve the performance of most NLP tasks. Input sentences will have corruption and we convert it into standard English while preserving the semantic meaning of the sentences. As mentioned in the research paper, we will be using Sequence cross-entropy (Categorical cross-entropy) as our loss function, where we sum over cross-entropy loss at each time step in predicting the character for the current time step.

Taylor wanted to see if he could improve his predictions by using his domain knowledge about college football. By using his understanding of the game, Taylor was able to boost his performance into the 100th percentile, proving just how important subject matter expertise is in data science. A simple example of this is when Taylor saw Alabama ranked by DataRobot as a 7 point game, his domain knowledge (or some would say blind allegiance to Alabama) led him to change it to a 10 point game. With his added insights, Taylor improved his picks to the 100th percentile.