diff --git a/seacrowd/sea_datasets/nusaparagraph_emot/nusaparagraph_emot.py b/seacrowd/sea_datasets/nusaparagraph_emot/nusaparagraph_emot.py index c1782487f..068508998 100644 --- a/seacrowd/sea_datasets/nusaparagraph_emot/nusaparagraph_emot.py +++ b/seacrowd/sea_datasets/nusaparagraph_emot/nusaparagraph_emot.py @@ -11,7 +11,7 @@ _SOURCE_VIEW_NAME = DEFAULT_SOURCE_VIEW_NAME _UNIFIED_VIEW_NAME = DEFAULT_SEACROWD_VIEW_NAME _LANGUAGES = [ - "btk", "bew", "bug", "jav", "mad", "mak", "min", "mui", "rej", "sun" + "btx", "bew", "bug", "jav", "mad", "mak", "min", "mui", "rej", "sun" ] # We follow ISO639-3 language code (https://iso639-3.sil.org/code_tables/639/data) _CITATION = """\ @unpublished{anonymous2023nusawrites:, @@ -66,7 +66,7 @@ def seacrowd_config_constructor(lang, schema, version): subset_id="nusaparagraph_emot", ) LANGUAGES_MAP = { - "btk": "batak", + "btx": "batak", "bew": "betawi", "bug": "buginese", "jav": "javanese", @@ -167,4 +167,4 @@ def _generate_examples(self, filepath: Path) -> Tuple[int, Dict]: df = pd.read_csv(filepath).reset_index() for row in df.itertuples(): ex = {"id": str(row.id), "text": row.text, "label": row.label} - yield row.id, ex \ No newline at end of file + yield row.id, ex