BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations
This work addresses the problem of efficient entity linking in business conversations for production environments, but it is incremental as it builds on existing methods like BLINK with Elasticsearch optimizations.
The authors tackled the challenge of deploying a neural entity linking system for real-time inference in production by developing a system that links product and organization entities in business conversations to Wikipedia and Wikidata entries, achieving significant improvements in inference speed and memory consumption while maintaining high accuracy.
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.