Building a Unified NLP Framework at LinkedIn with Huiji Gao - #481
Published:May 6, 2021 19:18
•1 min read
•Practical AI
Analysis
This article discusses an interview with Huiji Gao, a Senior Engineering Manager at LinkedIn, focusing on the development and implementation of NLP tools and systems. The primary focus is on DeText, an open-source framework for ranking, classification, and language generation models. The conversation explores the motivation behind DeText, its impact on LinkedIn's NLP landscape, and its practical applications within the company. The article also touches upon the relationship between DeText and LiBERT, a LinkedIn-specific version of BERT, and the engineering considerations for optimization and practical use of these tools. The interview provides insights into LinkedIn's approach to NLP and its open-source contributions.
Key Takeaways
- •DeText is an open-source NLP framework developed at LinkedIn for ranking, classification, and language generation.
- •LiBERT is a LinkedIn-specific version of BERT, trained and calibrated on LinkedIn data, used in conjunction with DeText.
- •The article highlights the practical engineering considerations and optimization approaches used in deploying these NLP tools at LinkedIn.
Reference
“We dig into his interest in building NLP tools and systems, including a recent open-source project called DeText, a framework for generating models for ranking classification and language generation.”