Deep Natural Language Processing for LinkedIn Search Systems (Research Paper Walkthrough)
#ai #linkedin #nlp
Ever wondered How LinkedIn Search system works? This paper from researchers from LinkedIn talks exactly that and tries to answer few interesting questions like: 1. When is deep NLP helpful/not helpful in search systems? 2. How to address latency challenges? 3. How to ensure model robustness?
⏩ Abstract: Many search systems work with large amounts of natural language data, e.g., search queries, user profiles and documents, where deep learning based natural language processing techniques (deep NLP) can be of great help. In this paper, we introduce a comprehensive study of applying deep NLP techniques to five representative tasks in search engines. Through the model design and experiments of the five tasks, readers can find answers to three important questions: (1) When is deep NLP helpful/not helpful in search systems? (2) How to address latency challenges? (3) How to ensure model robustness? This work builds on existing efforts of LinkedIn search, and is tested at scale on a commercial search engine. We believe our experiences can provide useful insights for the industry and research communities.
Please feel free to share out the content and subscribe to my channel :)
⏩ Subscribe - / @techvizthedatascienceguy
⏩ OUTLINE:
0:00 - Abstract
02:10 - Search Systems at LinkedIn
02:57 - Deep NLP components for Search
04:13 - Overview of a search system
05:56 - Query Intent Prediction
08:32 - Query Tagging
10:44 - Query Auto completion
12:38 - Query Suggestion
15:07 - Document Ranking
18:38 - When is deep nlp helpful?
19:20 - When deep nlp is not helpful?
19:45 - Latency is the biggest challenge in search systems
20:40 - Ensuring robustness and wrap-up
⏩ Paper Title: Deep Natural Language Processing for LinkedIn Search Systems
⏩ Paper: https://arxiv.org/abs/2108.08252
⏩ Author: Weiwei Guo, Xiaowei Liu, Sida Wang, Michaeel Kazi, Zhoutong Fu, Huiji Gao, Jun Jia, Liang Zhang, Bo Long
⏩ Organisation: LinkedIn
⏩ IMPORTANT LINKS
Full Playlist on BERT usecases in NLP: • Text Summarization of COVID-19 Medical Art...
Full Playlist on Text Data Augmentation Techniques: • Data Augmentation using Pre-trained Transf...
Full Playlist on Text Summarization: • Text Summarization of COVID-19 Medical Art...
Full Playlist on Machine Learning with Graphs: • DEEPWALK: Online Learning of Social Repres...
Full Playlist on Evaluating NLG Systems: • Evaluation of Text Generation: A Survey | ...
**********************************************
If you want to support me financially which is totally optional and voluntary ❤️
You can consider buying me chai ( because I don't drink coffee :) ) at https://www.buymeacoffee.com/TechvizC...
**********************************************
⏩ Youtube - / techvizthedatascienceguy
⏩ LinkedIn - / prakhar21
⏩ Medium - / prakhar.mishra
⏩ GitHub - https://github.com/prakhar21
⏩ Twitter - / rattller
*********************************************
Tools I use for making videos :)
⏩ iPad - https://tinyurl.com/y39p6pwc
⏩ Apple Pencil - https://tinyurl.com/y5rk8txn
⏩ GoodNotes - https://tinyurl.com/y627cfsa
#techviz #datascienceguy #nlproc #ai #search #machinelearning
About Me:
I am Prakhar Mishra and this channel is my passion project. I am currently pursuing my MS (by research) in Data Science. I have an industry work-ex of 3 years in the field of Data Science and Machine Learning with a particular focus on Natural Language Processing (NLP).