| -rw-r--r-- | .gitignore | 162L |
| -rw-r--r-- | LICENSE | 661L |
| -rw-r--r-- | README.md | 59L |
| -rw-r--r-- | aec/evaluate.py | 200L |
| -rw-r--r-- | aec/fuzzy_align.py | 86L |
| -rw-r--r-- | aec/ids_to_documents.py | 164L |
| -rw-r--r-- | analysis/countries.py | 53L |
| -rw-r--r-- | analysis/errors.py | 173L |
| -rw-r--r-- | analysis/hplt quality.py | 53L |
| -rw-r--r-- | analysis/json2table.py | 44L |
| -rw-r--r-- | analysis/miscellaneous stats.py | 102L |
| -rw-r--r-- | baselines/DEGREE/.gitignore | 6L |
| -rw-r--r-- | baselines/DEGREE/LICENSE | 201L |
| -rw-r--r-- | baselines/DEGREE/README.md | 155L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_e2e_ace05e.json | 31L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_e2e_ace05ep.json | 31L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_e2e_ere.json | 31L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_eae_ace05e.json | 30L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_eae_ace05ep.json | 30L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_eae_ere.json | 30L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_eae_ucdp.json | 30L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_ed_ace05e.json | 31L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_ed_ace05ep.json | 31L |
| -rw-r--r-- | baselines/DEGREE/config/config_degree_ed_ere.json | 31L |
| -rw-r--r-- | baselines/DEGREE/convert_predictions.py | 41L |
| -rw-r--r-- | baselines/DEGREE/degree/data.py | 243L |
| -rw-r--r-- | baselines/DEGREE/degree/eval_end2endEE.py | 402L |
| -rw-r--r-- | baselines/DEGREE/degree/eval_pipelineEE.py | 446L |
| -rw-r--r-- | baselines/DEGREE/degree/generate_data_degree_e2e.py | 128L |
| -rw-r--r-- | baselines/DEGREE/degree/generate_data_degree_eae.py | 120L |
| -rw-r--r-- | baselines/DEGREE/degree/generate_data_degree_ed.py | 128L |
| -rw-r--r-- | baselines/DEGREE/degree/model.py | 48L |
| -rw-r--r-- | baselines/DEGREE/degree/template_generate_ace.py | 3799L |
| -rw-r--r-- | baselines/DEGREE/degree/template_generate_ere.py | 4352L |
| -rw-r--r-- | baselines/DEGREE/degree/template_generate_ucdp.py | 332L |
| -rw-r--r-- | baselines/DEGREE/degree/train_degree_e2e.py | 275L |
| -rw-r--r-- | baselines/DEGREE/degree/train_degree_eae.py | 269L |
| -rw-r--r-- | baselines/DEGREE/degree/train_degree_ed.py | 247L |
| -rw-r--r-- | baselines/DEGREE/degree/utils.py | 43L |
| -rw-r--r-- | baselines/DEGREE/env_reference.yml | 108L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/get_doc_statistics.py | 93L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/process_ace05e.py | 202L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/process_ace05ep.py | 1559L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/process_ere.py | 1668L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/process_ucdp.py | 106L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/split_dataset.py | 23L |
| -rw-r--r-- | baselines/DEGREE/preprocessing/split_dataset_dygie.py | 23L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_001 | 5L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_002 | 10L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_003 | 15L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_005 | 25L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_010 | 50L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_020 | 110L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_030 | 160L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_050 | 260L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05e/doc_list_075 | 400L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_001 | 5L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_002 | 10L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_003 | 15L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_005 | 25L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_010 | 50L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_020 | 110L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_030 | 160L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_050 | 260L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ace05ep/doc_list_075 | 400L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_001 | 4L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_002 | 8L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_003 | 12L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_005 | 20L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_010 | 40L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_020 | 80L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_030 | 120L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_050 | 200L |
| -rw-r--r-- | baselines/DEGREE/resource/low_resource_split/ere/doc_list_075 | 300L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ACE05-EP/dev.doc.txt | 28L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ACE05-EP/test.doc.txt | 40L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ACE05-EP/train.doc.txt | 529L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ACE05-EP/train_more.doc.txt | 531L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ERE-EN/dev.doc.txt | 31L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ERE-EN/test.doc.txt | 31L |
| -rw-r--r-- | baselines/DEGREE/resource/splits/ERE-EN/train.doc.txt | 396L |
| -rwxr-xr-x | baselines/DEGREE/scripts/process_ace05e.sh | 21L |
| -rwxr-xr-x | baselines/DEGREE/scripts/process_ace05ep.sh | 19L |
| -rwxr-xr-x | baselines/DEGREE/scripts/process_ere.sh | 19L |
| -rwxr-xr-x | baselines/DEGREE/scripts/process_ucdp.sh | 8L |
| -rwxr-xr-x | baselines/DEGREE/scripts/train_degree_e2e.sh | 9L |
| -rwxr-xr-x | baselines/DEGREE/scripts/train_degree_eae.sh | 9L |
| -rwxr-xr-x | baselines/DEGREE/scripts/train_degree_ed.sh | 9L |
| -rw-r--r-- | baselines/Decoder_models/Finetune_llms.ipynb | 210L |
| -rw-r--r-- | baselines/Decoder_models/Inference_llms.ipynb | 117L |
| -rw-r--r-- | baselines/Decoder_models/data_prep_FT.ipynb | 217L |
| -rw-r--r-- | baselines/Decoder_models/readme.md | 1L |
| -rw-r--r-- | baselines/README.md | 54L |
| -rwxr-xr-x | baselines/Text2Event/.gitignore | 27L |
| -rw-r--r-- | baselines/Text2Event/LICENSE | 21L |
| -rwxr-xr-x | baselines/Text2Event/README.md | 270L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/__init__.py | 0B |
| -rw-r--r-- | baselines/Text2Event/data_convert/convert_aec_dataset.py | 62L |
| -rw-r--r-- | baselines/Text2Event/data_convert/convert_aec_preds.py | 52L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/convert_text_to_tree.py | 140L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/format/__init__.py | 0B |
| -rwxr-xr-x | baselines/Text2Event/data_convert/format/target_format.py | 11L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/format/text2tree.py | 129L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/task_format/__init__.py | 6L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/task_format/event_extraction.py | 161L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/task_format/task_format.py | 4L |
| -rw-r--r-- | baselines/Text2Event/data_convert/ucdp_fields.py | 16L |
| -rwxr-xr-x | baselines/Text2Event/data_convert/utils.py | 61L |
| -rwxr-xr-x | baselines/Text2Event/evaluation.py | 258L |
| -rwxr-xr-x | baselines/Text2Event/extraction/__init__.py | 0B |
| -rwxr-xr-x | baselines/Text2Event/extraction/event_schema.py | 51L |
| -rwxr-xr-x | baselines/Text2Event/extraction/extract_constraint.py | 452L |
| -rwxr-xr-x | baselines/Text2Event/extraction/extraction_metrics.py | 76L |
| -rwxr-xr-x | baselines/Text2Event/extraction/label_tree.py | 99L |
| -rwxr-xr-x | baselines/Text2Event/extraction/predict_parser/__init__.py | 2L |
| -rwxr-xr-x | baselines/Text2Event/extraction/predict_parser/predict_parser.py | 84L |
| -rwxr-xr-x | baselines/Text2Event/extraction/predict_parser/tree_predict_parser.py | 283L |
| -rwxr-xr-x | baselines/Text2Event/requirements.txt | 29L |
| -rwxr-xr-x | baselines/Text2Event/run_eval.bash | 53L |
| -rwxr-xr-x | baselines/Text2Event/run_seq2seq.bash | 150L |
| -rwxr-xr-x | baselines/Text2Event/run_seq2seq.py | 747L |
| -rwxr-xr-x | baselines/Text2Event/run_seq2seq_verbose.bash | 150L |
| -rwxr-xr-x | baselines/Text2Event/run_seq2seq_with_pretrain.bash | 194L |
| -rw-r--r-- | baselines/Text2Event/scripts/convert_dyiepp_to_sentence.py | 44L |
| -rwxr-xr-x | baselines/Text2Event/scripts/processing_data.bash | 2L |
| -rwxr-xr-x | baselines/Text2Event/seq2seq/__init__.py | 4L |
| -rwxr-xr-x | baselines/Text2Event/seq2seq/constrained_seq2seq.py | 196L |
| -rwxr-xr-x | baselines/Text2Event/seq2seq/label_smoother_sum.py | 43L |
| -rwxr-xr-x | baselines/Text2Event/seq2seq/sentence_splitter.py | 39L |
| -rwxr-xr-x | baselines/Text2Event/seq2seq/utils.py | 647L |
| -rwxr-xr-x | baselines/Text2Event/show_tokenized_result.py | 51L |
| -rw-r--r-- | baselines/flan-t5/.gitignore | 168L |
| -rw-r--r-- | baselines/flan-t5/README.md | 37L |
| -rw-r--r-- | baselines/flan-t5/pyproject.toml | 7L |
| -rw-r--r-- | baselines/flan-t5/t5/__init__.py | 18L |
| -rw-r--r-- | baselines/flan-t5/t5/__main__.py | 7L |
| -rw-r--r-- | baselines/flan-t5/t5/collator.py | 35L |
| -rw-r--r-- | baselines/flan-t5/t5/config.py | 397L |
| -rw-r--r-- | baselines/flan-t5/t5/dataset.py | 124L |
| -rw-r--r-- | baselines/flan-t5/t5/experiment.py | 158L |
| -rw-r--r-- | baselines/flan-t5/t5/metric.py | 285L |
| -rw-r--r-- | baselines/flan-t5/t5/model.py | 81L |
| -rw-r--r-- | baselines/flan-t5/t5/process_output.py | 43L |
| -rw-r--r-- | baselines/flan-t5/t5/spec/__init__.py | 1L |
| -rw-r--r-- | baselines/flan-t5/t5/spec/aec_setup.py | 34L |
| -rw-r--r-- | baselines/flan-t5/t5/trainer.py | 116L |
| -rw-r--r-- | data/UCDP-AEC-ids/test.jsonl | 648L |
| -rw-r--r-- | data/UCDP-AEC-ids/test/data-00000-of-00001.arrow | 132480B |
| -rw-r--r-- | data/UCDP-AEC-ids/test/dataset_info.json | 109L |
| -rw-r--r-- | data/UCDP-AEC-ids/test/state.json | 13L |
| -rw-r--r-- | data/UCDP-AEC-ids/train.jsonl | 10064L |
| -rw-r--r-- | data/UCDP-AEC-ids/train/data-00000-of-00001.arrow | 2010928B |
| -rw-r--r-- | data/UCDP-AEC-ids/train/dataset_info.json | 109L |
| -rw-r--r-- | data/UCDP-AEC-ids/train/state.json | 13L |
| -rw-r--r-- | data/UCDP-AEC-ids/validation.jsonl | 651L |
| -rw-r--r-- | data/UCDP-AEC-ids/validation/data-00000-of-00001.arrow | 135304B |
| -rw-r--r-- | data/UCDP-AEC-ids/validation/dataset_info.json | 109L |
| -rw-r--r-- | data/UCDP-AEC-ids/validation/state.json | 13L |
| -rw-r--r-- | hplt_align/Annotate HPLT Alignment.ipynb | 358L |
| -rw-r--r-- | hplt_align/align_annotations.jsonl | 130L |
| -rw-r--r-- | hplt_align/build_cache.py | 35L |
| -rw-r--r-- | hplt_align/common.py | 36L |
| -rw-r--r-- | hplt_align/convert_to_jsonl.py | 39L |
| -rw-r--r-- | hplt_align/dataset_to_sources.py | 28L |
| -rw-r--r-- | hplt_align/minhash-retrieval/README.md | 31L |
| -rwxr-xr-x | hplt_align/minhash-retrieval/index_lines.sh | 2L |
| -rw-r--r-- | hplt_align/minhash-retrieval/requirements_nird.lock | 50L |
| -rw-r--r-- | hplt_align/minhash-retrieval/retriever.py | 118L |
| -rwxr-xr-x | hplt_align/minhash-retrieval/run_retrieval.sh | 5L |
| -rwxr-xr-x | hplt_align/minhash-retrieval/run_retrieval1.sh | 11L |
| -rw-r--r-- | hplt_align/shell.nix | 11L |
| -rw-r--r-- | hplt_align/sources_to_hplt_ids.py | 76L |
| -rw-r--r-- | hplt_align/zstd-index/Makefile | 3L |
| -rw-r--r-- | hplt_align/zstd-index/line_offsets_of_seekable_zstd.c | 111L |
| -rw-r--r-- | hplt_align/zstd-index/shell.nix | 6L |
| -rw-r--r-- | hplt_align/zstd-index/zstd-seek.c | 655L |
| -rw-r--r-- | hplt_align/zstd-index/zstd-seek.h | 219L |
