Learning to Generate Reviews and Discovering Sentiment

by   Alec Radford, et al.

We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to high-level concepts. Specifically, we find a single unit which performs sentiment analysis. These representations, learned in an unsupervised manner, achieve state of the art on the binary subset of the Stanford Sentiment Treebank. They are also very data efficient. When using only a handful of labeled examples, our approach matches the performance of strong baselines trained on full datasets. We also demonstrate the sentiment unit has a direct influence on the generative process of the model. Simply fixing its value to be positive or negative generates samples with the corresponding positive or negative sentiment.


AlbMoRe: A Corpus of Movie Reviews for Sentiment Analysis in Albanian

Lack of available resources such as text corpora for low-resource langua...

Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

Sentiment analysis is a common task in natural language processing that ...

Differentiating Approach and Avoidance from Traditional Notions of Sentiment in Economic Contexts

There is growing interest in the role of sentiment in economic decision-...

Sentiment Recognition in Egocentric Photostreams

Lifelogging is a process of collecting rich source of information about ...

A New Approach for Measuring Sentiment Orientation based on Multi-Dimensional Vector Space

This study implements a vector space model approach to measure the senti...

BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews

The analysis of consumer sentiment, as expressed through reviews, can pr...

Please sign up or login with your details

Forgot password? Click here to reset