An efficient framework for learning sentence representations

TL;DR

This paper introduces a simple, efficient framework for learning high-quality sentence representations from unlabeled data by reformulating context prediction as a classification task, outperforming existing methods in NLP tasks.

Contribution

The authors propose a novel classification-based approach for learning sentence embeddings that is both fast and effective, improving upon prior unsupervised and supervised methods.

Findings

Outperforms state-of-the-art on multiple NLP tasks

Achieves significant speedup in training time

Learns high-quality sentence representations

Abstract

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate the problem of predicting the context in which a sentence appears as a classification problem. Given a sentence and its context, a classifier distinguishes context sentences from other contrastive sentences based on their vector representations. This allows us to efficiently learn different types of encoding functions, and we show that the model learns high-quality sentence representations. We demonstrate that our sentence representations outperform state-of-the-art unsupervised and supervised representation learning methods on several downstream NLP tasks that involve understanding sentence semantics while achieving an order of magnitude speedup in training time.