No training required: Exploring random encoders for sentence classification

What this post added

This post introduces a novel baseline for sentence embeddings by exploring various methods for computing sentence representations from pretrained word embeddings without any additional training. It investigates the effectiveness of random parameterizations over pretrained word embeddings, including bag of random embedding projections, random LSTMs, and echo state networks, demonstrating that these can sometimes match the performance of well-known sentence encoders like SkipThought and InferSent. The post also provides recommendations for proper experimental protocol for sentence classification evaluation.