Update README.md

README.md

@@ -1,67 +1,95 @@
----
-language:
-- multilingual
-- pl
-- ru
-- uk
-- bg
-- cs
-- sl
-datasets:
-- SlavicNER
-license: apache-2.0
-library_name: transformers
-pipeline_tag: text2text-generation
-tags:
-- lemmatization
-widget:
-  - text: "pl:Polsce"
-  - text: "cs:Velké Británii"
-  - text: "bg:българите"
-  - text: "ru:Великобританию"
-  - text: "sl:evropske komisije"
-  - text: "uk:Європейського агентства лікарських засобів"
----
-
-# Model description
-
-This is a baseline model for named entity **lemmatization** trained on the single-out topic split of the 
-[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
-
-
-# Resources and Technical Documentation
-
-- Paper: [Cross-lingual Named Entity Corpus for Slavic Languages](https://arxiv.org/pdf/2404.00482), to appear in LREC-COLING 2024.
-- Annotation guidelines: https://arxiv.org/pdf/2404.00482
-- SlavicNER Corpus: https://github.com/SlavicNLP/SlavicNER
-
-
-# Evaluation
-
-*Will appear soon*
-
-
-# Usage
-
-You can use this model directly with a pipeline for text2text generation:
-
-```python
-from transformers import pipeline
-
-model_name = "SlavicNLP/slavicner-lemma-cross-topic-large"
-pipe = pipeline("text2text-generation", model_name)
-
-texts = ["pl:Polsce", "cs:Velké Británii", "bg:българите", "ru:Великобританию",
-         "sl:evropske komisije", "uk:Європейського агентства лікарських засобів"]
-
-outputs = pipe(texts)
-
-ids = [o['generated_text'] for o in outputs]
-print(ids)
-# ['GPE-Poland', 'GPE-Great-Britain', 'GPE-Bulgaria', 'GPE-Great-Britain',
-#  'ORG-European-Commission', 'ORG-EMA-European-Medicines-Agency']
-```
-
-# Citation
-
-*Will appear soon*
+---
+language:
+- multilingual
+- pl
+- ru
+- uk
+- bg
+- cs
+- sl
+datasets:
+- SlavicNER
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text2text-generation
+tags:
+- lemmatization
+widget:
+  - text: "pl:Polsce"
+  - text: "cs:Velké Británii"
+  - text: "bg:българите"
+  - text: "ru:Великобританию"
+  - text: "sl:evropske komisije"
+  - text: "uk:Європейського агентства лікарських засобів"
+---
+
+# Model description
+
+This is a baseline model for named entity **lemmatization** trained on the single-out topic split of the 
+[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
+
+
+# Resources and Technical Documentation
+
+- Paper: [Cross-lingual Named Entity Corpus for Slavic Languages](https://arxiv.org/pdf/2404.00482), to appear in LREC-COLING 2024.
+- Annotation guidelines: https://arxiv.org/pdf/2404.00482
+- SlavicNER Corpus: https://github.com/SlavicNLP/SlavicNER
+
+
+# Evaluation
+
+*Will appear soon*
+
+
+# Usage
+
+You can use this model directly with a pipeline for text2text generation:
+
+```python
+from transformers import pipeline
+
+model_name = "SlavicNLP/slavicner-lemma-cross-topic-large"
+pipe = pipeline("text2text-generation", model_name)
+
+texts = ["pl:Polsce", "cs:Velké Británii", "bg:българите", "ru:Великобританию",
+         "sl:evropske komisije", "uk:Європейського агентства лікарських засобів"]
+
+outputs = pipe(texts)
+
+ids = [o['generated_text'] for o in outputs]
+print(ids)
+# ['GPE-Poland', 'GPE-Great-Britain', 'GPE-Bulgaria', 'GPE-Great-Britain',
+#  'ORG-European-Commission', 'ORG-EMA-European-Medicines-Agency']
+```
+
+# Citation
+
+```latex
+@inproceedings{piskorski-etal-2024-cross-lingual,
+    title = "Cross-lingual Named Entity Corpus for {S}lavic Languages",
+    author = "Piskorski, Jakub  and
+      Marci{\'n}czuk, Micha{\l}  and
+      Yangarber, Roman",
+    editor = "Calzolari, Nicoletta  and
+      Kan, Min-Yen  and
+      Hoste, Veronique  and
+      Lenci, Alessandro  and
+      Sakti, Sakriani  and
+      Xue, Nianwen",
+    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
+    month = may,
+    year = "2024",
+    address = "Torino, Italy",
+    publisher = "ELRA and ICCL",
+    url = "https://aclanthology.org/2024.lrec-main.369",
+    pages = "4143--4157",
+    abstract = "This paper presents a corpus manually annotated with named entities for six Slavic languages {---} Bulgarian, Czech, Polish, Slovenian, Russian,
+                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
+                Language Processing. The corpus consists of 5,017 documents on seven topics. The documents are annotated with five classes of named entities.
+                Each entity is described by a category, a lemma, and a unique cross-lingual identifier. We provide two train-tune dataset splits
+                {---} single topic out and cross topics. For each split, we set benchmarks using a transformer-based neural network architecture
+                with the pre-trained multilingual models {---} XLM-RoBERTa-large for named entity mention recognition and categorization,
+                and mT5-large for named entity lemmatization and linking.",
+}
+```
+