Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models

#ner #llms #naturallanguageprocessing
This video discusses how we can use LLMs like ChatGPT/GPT-4 to build a self-improving framework for doing Named-entity recognition in NLP. The self-improving framework pushes the boundary of zero-shot NER with LLMs and achieves an obvious performance improvement.
⏩ Abstract: Exploring the application of powerful large language models (LLMs) on the fundamental named entity recognition (NER) task has drawn much attention recently. This work aims to investigate the possibilities of pushing the boundary of zero-shot NER with LLM via a training-free self-improving strategy. We propose a self-improving framework, which utilize an unlabeled corpus to stimulate the self-learning ability of LLMs on NER. First, we use LLM to make predictions on the unlabeled corpus and obtain the self-annotated data. Second, we explore various strategies to select reliable samples from the self-annotated dataset as demonstrations, considering the similarity, diversity and reliability of demonstrations. Finally, we conduct inference for the test query via in-context learning with the selected self-annotated demonstrations. Through comprehensive experimental analysis, our study yielded the following findings: (1) The self-improving framework further pushes the boundary of zero-shot NER with LLMs, and achieves an obvious performance improvement; (2) Iterative self-improving or naively increasing the size of unlabeled corpus does not guarantee improvements; (3) There might still be space for improvement via more advanced strategy for reliable entity selection.
⏩ Paper Title: Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models
⏩ Paper: arxiv.org/pdf/2311.08921.pdf
⏩ Author: Tingyu Xie, Qi Li, Yan Zhang, Zuozhu Liu, Hongwei Wang
⏩ Organisation: Zhejiang University, National University of Singapore
⏩ IMPORTANT LINKS
Code Link: github.com/AGI-Edgerunners/LL...
BART paper summary: • BART: Denoising Sequen...
T5 paper summary: • T5: Exploring Limits o...
Pegasus paper summary: • PEGASUS: Pre-training ...
Research Paper Summaries: • Simple Unsupervised Ke...
Enjoy reading articles? then consider subscribing to Medium membership, it is just 5$ a month for unlimited access to all free/paid content.
Subscribe now - / membership
*********************************************
⏩ TH-cam - / @techvizthedatascienceguy
⏩ LinkedIn - / prakhar21
⏩ Medium - / prakhar.mishra
⏩ GitHub - github.com/prakhar21
*********************************************
⏩ Please feel free to share out the content and subscribe to my channel - / @techvizthedatascienceguy
Tools I use for making videos :)
⏩ iPad - tinyurl.com/y39p6pwc
⏩ Apple Pencil - tinyurl.com/y5rk8txn
⏩ GoodNotes - tinyurl.com/y627cfsa
#techviz #datascienceguy #deeplearning #ai #openai #chatgpt #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 4+ years in the field of Data Science and Machine Learning with a particular focus on Natural Language Processing (NLP).

[@TechVizTheDataScienceGuy]

🌟 Interested in consuming byte-sized AI/ML content. Then feel free to check www.youtube.com/@TechVizTheDataScienceGuy/shorts
🌟 Just like this one, if research paper summaries are your type, then check th-cam.com/play/PLsAqq9lZFOtWUz1WEoJ3GXw197LD7BxMc.html