Using Psuedolabels for training Sentiment Classifiers makes the model generalize better across datasets

no code implementations • 5 Oct 2021 • Natesh Reddy, Muktabh Mayank Srivastava

The problem statement addressed in this work is : For a public sentiment classification API, how can we set up a classifier that works well on different types of data, having limited ability to annotate data from across domains.

Sentiment Analysis Sentiment Classification

Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models

no code implementations • 23 Nov 2020 • Natesh Reddy, Pranaydeep Singh, Muktabh Mayank Srivastava

When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment.

Aspect-Based Sentiment Analysis (ABSA) Language Modelling +2