Papers › A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces

A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces

13 Sep 2019arXiv:1909.06092archive 2025-07-28

Anne Lauscher, Goran Glavaš, Simone Paolo Ponzetto, Ivan Vulić

Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1) operate on under-specified and mutually differing bias definitions, (2) are tailored for a particular bias (e.g., gender bias) and (3) have been evaluated inconsistently and non-rigorously. In this work, we introduce a general framework for debiasing word embeddings. We operationalize the definition of a bias by discerning two types of bias specification: explicit and implicit. We then propose three debiasing models that operate on explicit or implicit bias specifications and that can be composed towards more robust debiasing. Finally, we devise a full-fledged evaluation framework in which we couple existing bias metrics with newly proposed ones. Experimental findings across three embedding methods suggest that the proposed debiasing models are robust and widely applicable: they often completely remove the bias both implicitly and explicitly without degradation of semantic information encoded in any of the input distributional spaces. Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.

PaperPDFCodeCode 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 19 code samples harvested from 3 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 19 samples from 3 repositories, 18 ran (18 with no instrument failure; 0 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.

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.

anlausch/debie mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nfriedri/debie-backend mentioned on GitHubMITSyntology: 14 samples, 14 ran (0 instrument-failed) · 0 unverified report
nfriedri/debie-frontend mentioned on GitHubMITSyntology: not harvested report
umanlp/debie-command-line mentioned on GitHubMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 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.

Code Syntology ran Syntology

19 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

1ran · violated contract
17ran
1unverified

Licence: 1 of the 19 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 3 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.

anlausch/debie community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
boolean_string in 17 papers exp_debiasnet_args.py ran · violated contract no licence file found · pointer only · d481e95ca1390889 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-22
nfriedri/debie-backend community (archive-listed) 14 samples, 14 ran (0 instrument-failed) · 0 unverified
create_duplicates calculation.py ran MIT (permissive) · 559fa36b836d0d46 · report fixture: signature set1:Tensor/2/float, set2:dict/0/?, set3:list/1/Tensor, set4:dict/0/? · returned tuple · level recorded 2026-09-24
dict_keys_to_string json_controller.py ran MIT (permissive) · 99bdfa1c386e0cc2 · report fixture: signature vector_dict:dict/0/? · returned str · level recorded 2026-09-24
dict_to_json json_controller.py ran MIT (permissive) · c21d9e8dd31a20a5 · report fixture: signature vector_dict:dict/0/? · returned dict · level recorded 2026-09-24
format_set_sizes specification_controller.py ran MIT (permissive) · ce02a6d9b77ea470 · report fixture: signature vector_set1:dict/0/?, vector_set2:dict/0/? · returned tuple · level recorded 2026-09-24
format_sets specification_controller.py ran MIT (permissive) · 33edd73c1410848f · report fixture: signature t1:dict/0/?, t2:dict/0/?, a1:dict/0/?, a2:dict/0/? · returned tuple · level recorded 2026-09-24
get_vector_from_small_dict Version0.1/compute_analogy.py ran MIT (permissive) · bcfffd82f19b8867 · report fixture: signature dict1:dict/0/? · returned list · level recorded 2026-09-24
json_vector_retrieval json_controller.py ran MIT (permissive) · 0e30b32211028bc2 · report fixture: signature vector_dict:dict/0/?, not_found:list/1/str · returned str · level recorded 2026-09-24
load_binary_embeddings data_controller.py ran MIT (permissive) · 11c6271f3ac7fad6 · report fixture: signature vocab_path:str/0/str, vecs_path:str/0/str, inverse:bool/0/bool, normalize:bool/0/bool · returned tuple · level recorded 2026-09-24
load_vectors_binary data_controller.py ran MIT (permissive) · afd00edba761da8c · report fixture: signature path:str/0/str, normalize:bool/0/bool · returned ndarray · level recorded 2026-09-24
load_vocab_binary data_controller.py ran MIT (permissive) · 0f45921d6c72d3da · report fixture: signature path:str/0/str, inverse:bool/0/bool · returned dict · level recorded 2026-09-24
retrieve_vector_multiple vector_retrieval.py ran MIT (permissive) · f5d190ff20783914 · report fixture: signature vocab:dict/0/?, vectors:Tensor/2/float, word_list:list/1/str · returned tuple · level recorded 2026-09-24
retrieve_vector_single vector_retrieval.py ran MIT (permissive) · 261fa31e43f56cbc · report fixture: signature vocab:dict/0/?, vectors:Tensor/2/float, target_word:str/0/str · returned tuple · level recorded 2026-09-24
transform_dict_to_list calculation.py ran MIT (permissive) · ccdaa630046f3a52 · report fixture: signature dict1:dict/0/? · returned ndarray · level recorded 2026-09-24
transform_multiple_dicts_to_lists calculation.py ran MIT (permissive) · 3e20da2273d79713 · report fixture: signature dict1:dict/0/?, dict2:dict/0/?, dict3:dict/0/?, dict4:dict/0/? · returned tuple · level recorded 2026-09-24
umanlp/debie-command-line community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
bias_analogy_test bias_evaluation/bat.py ran MIT (permissive) · 9b616b12c15d0fcb · report fixture: signature target1:dict/0/?, target2:dict/0/?, attribute1:dict/0/?, attribute2:dict/0/? · returned float · level recorded 2026-09-24
eval_svm bias_evaluation/svm_classifier.py ran MIT (permissive) · 83515675d0094fcb · report fixture: signature augmentations1:list/1/str, augmentations2:list/1/str, target1:list/1/str, target2:list/1/str, vocab:dict/0/?, vecs:ndarray/2/float · returned float · level recorded 2026-09-24
target_set_mean_vector bias_evaluation/ect.py ran fingerprinted MIT (permissive) · 549b1aad49e944c5 · report fixture: signature target_list:list/1/ndarray · returned ndarray · level recorded 2026-09-24
load_dict_uploaded_file upload_controller.py unverified MIT (permissive) · cfc69051efee0623 · report

Tasks

Word Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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