Merge pull request #2245 from Gloriaky/master

add latin dataset

flair/datasets/__init__.py

@@ -252,3 +252,4 @@
 from .biomedical import BIOBERT_SPECIES_S800
 from .biomedical import BIOBERT_GENE_BC2GM
 from .biomedical import BIOBERT_GENE_JNLPBA
+from.treebanks import UD_LATIN

flair/datasets/treebanks.py

@@ -567,6 +567,34 @@ def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True, s
         super(UD_ITALIAN, self).__init__(data_folder, in_memory=in_memory, split_multiwords=split_multiwords)
 
 
+class UD_LATIN(UniversalDependenciesCorpus):
+    def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True, split_multiwords: bool = True):
+
+        if type(base_path) == str:
+            base_path: Path = Path(base_path)
+
+        # this dataset name
+        dataset_name = self.__class__.__name__.lower()
+
+        # default dataset folder is the cache root
+        if not base_path:
+            base_path = Path(flair.cache_root) / "datasets"
+        data_folder = base_path / dataset_name
+
+        # download data if necessary
+        web_path = "https://github.com/UniversalDependencies/UD_Latin-LLCT/master/"
+        cached_path(f"{web_path}/la_llct-ud-dev.conllu", Path("datasets") / dataset_name)
+        cached_path(
+            f"{web_path}/la_llct-ud-test.conllu", Path("datasets") / dataset_name
+        )
+        cached_path(
+            f"{web_path}/la_llct-ud-train.conllu", Path("datasets") / dataset_name
+        )
+
+        super(UD_LATIN, self).__init__(data_folder, in_memory=in_memory, split_multiwords=split_multiwords)
+
+
+
 class UD_SPANISH(UniversalDependenciesCorpus):
     def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True, split_multiwords: bool = True):