Keywords: universal sentence representation, LSTM, natural language inference
TL;DR: Using LSTM encodings of both prefixes and suffixes gives better universal sentence representations.
Abstract: Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose a method to learn such representations by encoding the suffixes of word sequences in a sentence and training on the Stanford Natural Language Inference (SNLI) dataset. We demonstrate the effectiveness of our approach by evaluating it on the SentEval benchmark, improving on existing approaches on several transfer tasks.