Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning
This work addresses the need for efficient unsupervised sentence encoders in natural language processing, offering a significant speed improvement over existing approaches.
The authors tackled the problem of unsupervised sentence representation learning by introducing a novel objective function that uses paragraph-level discourse coherence, enabling training many times faster than prior methods and achieving strong performance in extrinsic evaluations.
This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely discriminative, allowing us to train models many times faster than was possible under prior methods, and it yields models which perform well in extrinsic evaluations.