Efficient comparison of sentence embeddings

TL;DR

This paper evaluates the efficiency of sentence embedding comparison methods, specifically comparing FAISS and Elasticsearch, with a focus on BERT embeddings in NLP tasks, highlighting FAISS's superior performance in centralized settings.

Contribution

The study compares two vector comparison approaches for sentence embeddings, demonstrating FAISS's effectiveness over Elasticsearch in specific NLP scenarios.

Findings

FAISS outperforms Elasticsearch in centralized environments.

FAISS is more efficient with large datasets.

The paper provides insights into embedding comparison performance.

Abstract

The domain of natural language processing (NLP), which has greatly evolved over the last years, has highly benefited from the recent developments in word and sentence embeddings. Such embeddings enable the transformation of complex NLP tasks, like semantic similarity or Question and Answering (Q&A), into much simpler to perform vector comparisons. However, such a problem transformation raises new challenges like the efficient comparison of embeddings and their manipulation. In this work, we will discuss about various word and sentence embeddings algorithms, we will select a sentence embedding algorithm, BERT, as our algorithm of choice and we will evaluate the performance of two vector comparison approaches, FAISS and Elasticsearch, in the specific problem of sentence embeddings. According to the results, FAISS outperforms Elasticsearch when used in a centralized environment with only one node, especially when big datasets are included.