Summary of Re-examine Distantly Supervised Ner: a New Benchmark and a Simple Approach, by Yuepei Li et al.
Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach
by Yuepei Li, Kang Zhou, Qiao Qiao, Qing Wang, Qi Li
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a new approach to Distantly-Supervised Named Entity Recognition (DS-NER) that tackles the issue of relying on large human-labeled validation sets. The authors propose CuPUL, a token-level Curriculum-based Positive-Unlabeled Learning method that uses curriculum learning to order training samples from easy to hard. This approach stabilizes training and makes it robust and effective on small validation sets, addressing false negative issues using the Positive-Unlabeled learning paradigm. CuPUL demonstrates improved performance in real-life applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way of recognizing named entities without needing lots of labeled data. Normally, this process relies on large amounts of human-annotated data, which can be time-consuming and expensive. The authors created a new approach called CuPUL that uses curriculum learning to make the training process more stable and effective. This method is useful for real-life applications where we don’t have access to lots of labeled data. |
Keywords
* Artificial intelligence * Curriculum learning * Named entity recognition * Ner * Supervised * Token
