Summary of Ellen: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition, by Haris Riaz et al.
ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition
by Haris Riaz, Razvan-Gabriel Dumitru, Mihai Surdeanu
First submitted to arxiv on: 26 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 presents a novel approach to semi-supervised named entity recognition (NER), dubbed ELLEN, which achieves strong performance even with minimal supervision. The method blends fine-tuned language models with linguistic rules, leveraging insights such as “One Sense Per Discourse” and classifier confidence scores. ELLEN outperforms existing semi-supervised NER methods under the same supervision settings and achieves comparable performance to GPT-4 in a zero-shot scenario. Furthermore, it achieves over 75% of the performance of a fully supervised model trained on gold data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding names and labels (entities) in text without using too much training data. They developed a new method called ELLEN that uses language models and rules to do this task well even with very little supervision. It’s like having a smart tool that can help us identify important information in text. |
Keywords
» Artificial intelligence » Discourse » Gpt » Named entity recognition » Ner » Semi supervised » Supervised » Zero shot
