# Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

## TL;DR

This paper demonstrates that supervised training on natural language inference data produces universal sentence representations that outperform unsupervised methods across various NLP transfer tasks.

## Contribution

The authors introduce a supervised approach to learn universal sentence embeddings from NLI data, showing improved transfer performance over previous unsupervised methods.

## Key findings

- Supervised NLI-trained embeddings outperform unsupervised methods on transfer tasks.
- The approach is comparable to ImageNet features in computer vision.
- The encoder is publicly available for use.

## Abstract

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.