Summary of Efontes. Part Of Speech Tagging and Lemmatization Of Medieval Latin Texts.a Cross-genre Survey, by Krzysztof Nowak et al.
eFontes. Part of Speech Tagging and Lemmatization of Medieval Latin Texts.A Cross-Genre Survey
by Krzysztof Nowak, Jędrzej Ziębura, Krzysztof Wróbel, Aleksander Smywiński-Pohl
First submitted to arxiv on: 29 Jun 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 paper introduces a set of AI models called eFontes that can automatically annotate Medieval Latin texts with linguistic information such as lemmatization, part-of-speech tagging, and morphological feature determination. The models were trained on a dataset of Polish Medieval Latin texts using the Transformers library and achieved high accuracy rates: 92.60% for lemmatization, 83.29% for part-of-speech tagging, and 88.57% for morphological feature determination. The research highlights the importance of high-quality annotated corpora and proposes future enhancements to the models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way for computers to understand Medieval Latin texts. It makes special AI models called eFontes that can do things like find the base form of words (lemmatization), figure out what part of speech each word is (part-of-speech tagging), and identify specific features about the words (morphological feature determination). These models were trained using a new dataset of Polish Medieval Latin texts. The results show that these models are very good at their jobs, with accuracy rates of 92.60%, 83.29%, and 88.57% respectively. This is important because it shows how much value high-quality annotated corpora can bring to AI research. |
Keywords
* Artificial intelligence * Lemmatization
