{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/matching-the-blanks-distributional-similarity","title":"Matching the Blanks: Distributional Similarity for Relation Learning","arxiv_id":"1906.03158","date":"2019-06-07","proceeding":"ACL 2019 7","authors":["Livio Baldini Soares","Nicholas FitzGerald","Jeffrey Ling","Tom Kwiatkowski"],"abstract":"General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris' distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task's training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.","url_abs":"https://arxiv.org/abs/1906.03158v1","url_pdf":"https://arxiv.org/pdf/1906.03158v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/Soikonomou/albert_final","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/Soikonomou/albert_final_infer12","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/Soikonomou/albert_final_infer8","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/Soikonomou/bert_new","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/Soikonomou/bert_new_new","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/cypressd1999/FYP_2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/dfki-nlp/mtb-bert-em","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/diffbot/knowledge-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/hieudepchai/BERT_IE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/jpablou/Matching-The-Blanks-Ths","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/plkmo/BERT-Relation-Extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"matching-the-blanks-distributional-similarity","repo_url":"https://github.com/yi-han/BERT_Relation_Extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-relation-classification","task_name":"Few-Shot Relation Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-classification-on-tacred-1","task":"Relation Classification","dataset":"TACRED","model":"MTB Baldini Soares et al. (2019)","rank_in_archive_order":9,"of":17,"metrics":{"F1":"71.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-semeval-2010-task-8","task":"Relation Extraction","dataset":"SemEval-2010 Task-8","model":"BERTEM+MTB","rank_in_archive_order":13,"of":31,"metrics":{"F1":"89.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-tacred","task":"Relation Extraction","dataset":"TACRED","model":"BERTEM+MTB","rank_in_archive_order":17,"of":40,"metrics":{"F1":"71.5","F1 (1% Few-Shot)":"43.4","F1 (10% Few-Shot)":"64.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.03158","atlas_url":"https://app.syntology.ai/?focus=1906.03158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03158"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jpablou/Matching-The-Blanks-Ths","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diffbot/knowledge-net","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cypressd1999/FYP_2021","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soikonomou/albert_final_infer8","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plkmo/BERT-Relation-Extraction","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soikonomou/albert_final_infer12","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soikonomou/albert_final","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soikonomou/bert_new_new","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yi-han/BERT_Relation_Extraction","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hieudepchai/BERT_IE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dfki-nlp/mtb-bert-em","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soikonomou/bert_new","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"listed":{"samples":14,"ran":9,"repositories":4}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"056e10dccac0c981","entry":"calc","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"056e10dccac0c981"}},{"code_sha256_prefix":"4ceff0a659777901","entry":"convert_examples_to_relation_extraction_features","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ceff0a659777901"}},{"code_sha256_prefix":"6925605bcb0e4afa","entry":"features2tensors","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6925605bcb0e4afa"}},{"code_sha256_prefix":"4dc5e7239221c929","entry":"gelu","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/model_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dc5e7239221c929"}},{"code_sha256_prefix":"bb4b4b5ebab73228","entry":"load_pickle","repo":"Soikonomou/albert_final_infer12","repo_kind":"listed","path":"src/tasks/infer.py","file_url":"https://github.com/Soikonomou/albert_final_infer12/blob/HEAD/src/tasks/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb4b4b5ebab73228"}},{"code_sha256_prefix":"6b2f5d5a22d006f7","entry":"load_pickle","repo":"yi-han/BERT_Relation_Extraction","repo_kind":"listed","path":"src/infer.py","file_url":"https://github.com/yi-han/BERT_Relation_Extraction/blob/HEAD/src/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b2f5d5a22d006f7"}},{"code_sha256_prefix":"5df801e41d511da6","entry":"measure_prf","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5df801e41d511da6"}},{"code_sha256_prefix":"8665fb489259bdf8","entry":"relation_extraction_data_loader","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8665fb489259bdf8"}},{"code_sha256_prefix":"99651d855fa20393","entry":"try_catch_annotator","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99651d855fa20393"}},{"code_sha256_prefix":"05732f1a5126672d","entry":"get_mask","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/model_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05732f1a5126672d"}},{"code_sha256_prefix":"7d1f16579e77c0fb","entry":"json2args","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"src/relation_extraction_json.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/relation_extraction_json.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d1f16579e77c0fb"}},{"code_sha256_prefix":"f31508e399da30ed","entry":"nltk_tokenization_engine","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"baseline/data_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/baseline/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f31508e399da30ed"}},{"code_sha256_prefix":"1012ce3bde482566","entry":"pkl_load","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","repo_kind":"listed","path":"baseline/data_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/baseline/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1012ce3bde482566"}},{"code_sha256_prefix":"e50b2589e0455d1f","entry":"train_and_eval","repo":"dfki-nlp/mtb-bert-em","repo_kind":"listed","path":"src/mtb/train_eval.py","file_url":"https://github.com/dfki-nlp/mtb-bert-em/blob/HEAD/src/mtb/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e50b2589e0455d1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}