├── README.md ├── compute_distances.py ├── eval_perplexity.py ├── extract_representations.py ├── get_rotated_subspace_distances.py ├── get_scaled_subspace_distances.py ├── requirements.txt ├── scripts ├── concatenate_examples.py ├── count_tokens.py ├── deduplicate_examples.py ├── get_global_mean.py ├── get_text_data.py ├── subset_examples.py └── tokenize_examples.py ├── src ├── distances.py ├── utils.py └── xlmr_modeling.py ├── visualization ├── get_pos_representations.py ├── get_position_representations.py ├── ud_pos_dict.txt ├── visualization_constants.py ├── visualization_utils.py └── visualize_representations.py └── visualizations_graphic.png /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/README.md -------------------------------------------------------------------------------- /compute_distances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/compute_distances.py -------------------------------------------------------------------------------- /eval_perplexity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/eval_perplexity.py -------------------------------------------------------------------------------- /extract_representations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/extract_representations.py -------------------------------------------------------------------------------- /get_rotated_subspace_distances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/get_rotated_subspace_distances.py -------------------------------------------------------------------------------- /get_scaled_subspace_distances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/get_scaled_subspace_distances.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/concatenate_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/concatenate_examples.py -------------------------------------------------------------------------------- /scripts/count_tokens.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/count_tokens.py -------------------------------------------------------------------------------- /scripts/deduplicate_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/deduplicate_examples.py -------------------------------------------------------------------------------- /scripts/get_global_mean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/get_global_mean.py -------------------------------------------------------------------------------- /scripts/get_text_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/get_text_data.py -------------------------------------------------------------------------------- /scripts/subset_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/subset_examples.py -------------------------------------------------------------------------------- /scripts/tokenize_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/scripts/tokenize_examples.py -------------------------------------------------------------------------------- /src/distances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/src/distances.py -------------------------------------------------------------------------------- /src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/src/utils.py -------------------------------------------------------------------------------- /src/xlmr_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/src/xlmr_modeling.py -------------------------------------------------------------------------------- /visualization/get_pos_representations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/get_pos_representations.py -------------------------------------------------------------------------------- /visualization/get_position_representations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/get_position_representations.py -------------------------------------------------------------------------------- /visualization/ud_pos_dict.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/ud_pos_dict.txt -------------------------------------------------------------------------------- /visualization/visualization_constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/visualization_constants.py -------------------------------------------------------------------------------- /visualization/visualization_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/visualization_utils.py -------------------------------------------------------------------------------- /visualization/visualize_representations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualization/visualize_representations.py -------------------------------------------------------------------------------- /visualizations_graphic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tylerachang/multilingual-geometry/HEAD/visualizations_graphic.png --------------------------------------------------------------------------------