Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,71 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- multilingual
|
4 |
+
- pl
|
5 |
+
- ru
|
6 |
+
- uk
|
7 |
+
- bg
|
8 |
+
- cs
|
9 |
+
- sl
|
10 |
+
datasets:
|
11 |
+
- SlavicNER
|
12 |
+
license: apache-2.0
|
13 |
+
library_name: transformers
|
14 |
+
pipeline_tag: token-classification
|
15 |
+
tags:
|
16 |
+
- ner
|
17 |
+
- named entity recognition
|
18 |
+
---
|
19 |
+
|
20 |
+
# Model description
|
21 |
+
|
22 |
+
This is a baseline model for named entity **recognition** trained on the cross-topic split of the
|
23 |
+
[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
|
24 |
+
|
25 |
+
|
26 |
+
# Resources and Technical Documentation
|
27 |
+
|
28 |
+
- Paper: [Cross-lingual Named Entity Corpus for Slavic Languages](https://arxiv.org/pdf/2404.00482), to appear in LREC-COLING 2024.
|
29 |
+
- Annotation guidelines: https://arxiv.org/pdf/2404.00482
|
30 |
+
- SlavicNER Corpus: https://github.com/SlavicNLP/SlavicNER
|
31 |
+
|
32 |
+
|
33 |
+
# Evaluation
|
34 |
+
|
35 |
+
*Will appear soon*
|
36 |
+
|
37 |
+
|
38 |
+
# Usage
|
39 |
+
|
40 |
+
*Will appear soon*
|
41 |
+
|
42 |
+
# Citation
|
43 |
+
|
44 |
+
```latex
|
45 |
+
@inproceedings{piskorski-etal-2024-cross-lingual,
|
46 |
+
title = "Cross-lingual Named Entity Corpus for {S}lavic Languages",
|
47 |
+
author = "Piskorski, Jakub and
|
48 |
+
Marci{\'n}czuk, Micha{\l} and
|
49 |
+
Yangarber, Roman",
|
50 |
+
editor = "Calzolari, Nicoletta and
|
51 |
+
Kan, Min-Yen and
|
52 |
+
Hoste, Veronique and
|
53 |
+
Lenci, Alessandro and
|
54 |
+
Sakti, Sakriani and
|
55 |
+
Xue, Nianwen",
|
56 |
+
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
|
57 |
+
month = may,
|
58 |
+
year = "2024",
|
59 |
+
address = "Torino, Italy",
|
60 |
+
publisher = "ELRA and ICCL",
|
61 |
+
url = "https://aclanthology.org/2024.lrec-main.369",
|
62 |
+
pages = "4143--4157",
|
63 |
+
abstract = "This paper presents a corpus manually annotated with named entities for six Slavic languages {---} Bulgarian, Czech, Polish, Slovenian, Russian,
|
64 |
+
and Ukrainian. This work is the result of a series of shared tasks, conducted in 2017{--}2023 as a part of the Workshops on Slavic Natural
|
65 |
+
Language Processing. The corpus consists of 5,017 documents on seven topics. The documents are annotated with five classes of named entities.
|
66 |
+
Each entity is described by a category, a lemma, and a unique cross-lingual identifier. We provide two train-tune dataset splits
|
67 |
+
{---} single topic out and cross topics. For each split, we set benchmarks using a transformer-based neural network architecture
|
68 |
+
with the pre-trained multilingual models {---} XLM-RoBERTa-large for named entity mention recognition and categorization,
|
69 |
+
and mT5-large for named entity lemmatization and linking.",
|
70 |
+
}
|
71 |
+
```
|