BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations

TL;DR

This paper presents a neural entity linking system optimized with Elasticsearch for real-time, resource-efficient inference in business conversation applications, linking entities to Wikipedia and Wikidata.

Contribution

It introduces a novel system combining neural entity linking with Elasticsearch to improve inference speed and memory efficiency in production environments.

Findings

Significant improvements in inference speed

Reduced memory consumption

Maintained high accuracy

Abstract

An Entity Linking system aligns the textual mentions of entities in a text to their corresponding entries in a knowledge base. However, deploying a neural entity linking system for efficient real-time inference in production environments is a challenging task. In this work, we present a neural entity linking system that connects the product and organization type entities in business conversations to their corresponding Wikipedia and Wikidata entries. The proposed system leverages Elasticsearch to ensure inference efficiency when deployed in a resource limited cloud machine, and obtains significant improvements in terms of inference speed and memory consumption while retaining high accuracy.