Session

John Ortega
21 Sep 2019
17:00-17:45
Data Science and Machine Learning

Using Big Data to Assist with Low Resources in Natural Language Processing

Many modern-day projects may not have access to tons of data sources to train a model that is artificially intelligent enough to create accurate predictions.
Natural Language Processing (NLP) tasks often consist of text classification problems where generalized corpora seems to be useless.
We will dive into a semi-supervised way of representing text that takes advantage of pre-trained models to better model the semantic meaning of text.
Specifically, machine translation and movie classification tasks will be addressed.