Hamming Sentence Embeddings for Information Retrieval

Abstract

In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed. We investigate the compression of sentence embeddings using a neural encoder-decoder architecture, which is trained by minimizing reconstruction error. Instead of employing the original real-valued embeddings, we use latent representations in Hamming space produced by the encoder for similarity calculations. In quantitative experiments on several benchmarks for semantic similarity tasks, we show that our compressed hamming embeddings yield a comparable performance to uncompressed embeddings (Sent2Vec, InferSent, Glove-BoW), at compression ratios of up to 256:1. We further demonstrate that our model strongly decorrelates input features, and that the compressor generalizes well when pre-trained on Wikipedia sentences. We publish the source code on Github and all experimental results.

arXiv comment4 Pages, 9 Figures, 1 Table

References in corpus (11)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Sentences and Documents
• Categorical Reparameterization with Gumbel-Softmax
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
• An efficient framework for learning sentence representations
• Text Understanding from Scratch
• SentEval: An Evaluation Toolkit for Universal Sentence Representations
• Towards Universal Paraphrastic Sentence Embeddings
• Compressing Word Embeddings via Deep Compositional Code Learning
• Word2Bits - Quantized Word Vectors