Summary of Dataset Mention Extraction in Scientific Articles Using Bi-lstm-crf Model, by Tong Zeng et al.
Dataset Mention Extraction in Scientific Articles Using Bi-LSTM-CRF Model
by Tong Zeng, Daniel Acuna
First submitted to arxiv on: 21 May 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 The proposed work aims to improve the citation of datasets in scientific research, which is crucial for replication, reproducibility, and efficiency. Despite recent efforts by data repositories and funding agencies, citing datasets remains a rare practice. To address this issue, a neural network based on Bi-LSTM-CRF architecture is proposed to automatically extract dataset mentions from scientific articles. The method achieves an F1 score of 0.885 in social science articles released as part of the Rich Context Dataset. This work highlights the importance of tracking dataset usage and proposes modifications to the model for future improvements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper wants to make it easier for scientists to properly credit datasets, which are super important for research. Right now, people don’t often mention where they got their data from, even though it’s really helpful to know. The researchers think that if a computer can help find these mentions, it would be more accurate and efficient. They tried using a special kind of AI network and tested it on some social science articles. It worked pretty well! The team hopes this will help us learn more about how datasets are used in research. |
Keywords
» Artificial intelligence » F1 score » Lstm » Neural network » Tracking
