Papers › Matching the Blanks: Distributional Similarity for Relation Learning

Matching the Blanks: Distributional Similarity for Relation Learning

7 Jun 2019ACL 2019 7arXiv:1906.03158archive 2025-07-28

Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling, Tom Kwiatkowski

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 4 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 4 repositories, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

13 repositories listed; official and paper-mentioned ones first.

Soikonomou/albert_final mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
Soikonomou/albert_final_infer12 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Soikonomou/albert_final_infer8 mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Soikonomou/bert_new mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
Soikonomou/bert_new_new mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
cypressd1999/FYP_2021 mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
dfki-nlp/mtb-bert-em mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
diffbot/knowledge-net mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Entity, Relation, and Event Extraction with Contextualized Span Representations (arXiv:1909.03546; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
hieudepchai/BERT_IE mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
jpablou/Matching-The-Blanks-Ths mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
plkmo/BERT-Relation-Extraction mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction mentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (0 instrument-failed) · 4 unverified report
yi-han/BERT_Relation_Extraction mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
7ran
5unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Soikonomou/albert_final_infer12 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
load_pickle in 115 papers src/tasks/infer.py ran · our draft was wrong Apache-2.0 (permissive) · bb4b4b5ebab73228 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
dfki-nlp/mtb-bert-em community (archive-listed) 1 sample, 0 ran · 1 unverified
train_and_eval in 6 papers src/mtb/train_eval.py unverified MIT (permissive) · e50b2589e0455d1f · report
uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction community (archive-listed) 11 samples, 7 ran (0 instrument-failed) · 4 unverified
calc in 9 papers src/utils.py ran fingerprinted MIT (permissive) · 056e10dccac0c981 · report fixture: signature tp:int/0/int, tp_fp:int/0/int, tp_tn:int/0/int · returned tuple · level recorded 2026-09-24
convert_examples_to_relation_extraction_features src/data_utils.py ran MIT (permissive) · 4ceff0a659777901 · report fixture: signature examples:list/1/Example, label2idx:dict/0/?, tokenizer:SimpleTokenizer/0/?, max_length:int/0/int · returned list · level recorded 2026-09-24
features2tensors src/data_utils.py ran MIT (permissive) · 6925605bcb0e4afa · report fixture: signature features:list/1/Feature, binary_mode:bool/0/bool, logger:SimpleLogger/0/? · returned TensorDataset · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
src/model_utils.py ran fingerprinted MIT (permissive) · 4dc5e7239221c929 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
measure_prf src/utils.py ran MIT (permissive) · 5df801e41d511da6 · report fixture: signature preds:list/1/str, gs_labels:list/1/str, non_rel_label:str/0/str · returned tuple · level recorded 2026-09-24
relation_extraction_data_loader src/data_utils.py ran MIT (permissive) · 8665fb489259bdf8 · report fixture: signature dataset:list/1/Feature, batch_size:int/0/int, task:str/0/str, logger:SimpleLogger/0/?, binary_mode:bool/0/bool · returned DataLoader · level recorded 2026-09-24
try_catch_annotator src/utils.py ran MIT (permissive) · 99651d855fa20393 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
json2args src/relation_extraction_json.py unverified MIT (permissive) · 7d1f16579e77c0fb · report
nltk_tokenization_engine baseline/data_utils.py unverified MIT (permissive) · f31508e399da30ed · report
pkl_load in 10 papers baseline/data_utils.py unverified MIT (permissive) · 1012ce3bde482566 · report
yi-han/BERT_Relation_Extraction community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
load_pickle in 115 papers src/infer.py ran · our draft was wrong no licence file found · pointer only · 6b2f5d5a22d006f7 · report fixture: signature filename:str/0/str, folder:str/0/str · returned dict · level recorded 2026-09-22

Tasks

Few-Shot Relation ClassificationRelation ClassificationRelation Extraction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Classification TACRED MTB Baldini Soares et al. (2019) F1 71.5 #9 of 17 Archive leaderboard report
Relation Extraction SemEval-2010 Task-8 BERTEM+MTB F1 89.5 #13 of 31 Archive leaderboard report
Relation Extraction TACRED BERTEM+MTB F1 71.5 #17 of 40 Archive leaderboard report
Relation Extraction TACRED BERTEM+MTB F1 (1% Few-Shot) 43.4 #17 of 40 Archive leaderboard report
Relation Extraction TACRED BERTEM+MTB F1 (10% Few-Shot) 64.8 #17 of 40 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections