Papers › Enriching Word Vectors with Subword Information

Enriching Word Vectors with Subword Information

15 Jul 2016TACL 2017 1arXiv:1607.04606archive 2025-07-28

Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.

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

No sample from the archive's official repository (facebookresearch/fastText) is linked to this paper; the 31 samples below come from 7 community repositories. Syntology harvested code from facebookresearch/fastText for another paper.

facebookresearch/fastText: Syntology's graph links these samples to On Evaluation of Bangla Word Analogies (arXiv:2304.04613; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 31 code samples harvested from 7 repositories linked to this paper: 25 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 31 samples from 7 repositories, 25 ran (21 with no instrument failure; 4 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

facebookresearch/fastText officialmentioned in papermentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Evaluation of Bangla Word Analogies (arXiv:2304.04613; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Babylonpartners/fastText_multilingual mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
DW-yejing/fasttext4j-jdk6 mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
FengJiaChunFromSYSU/fastText mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastText.zip: Compressing text classification models (arXiv:1612.03651; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
GitHubSprint/fasttext4j mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
Kinetikm/fastTextRelearning mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
Kinetikm/fasttextRelearnExperiment mentioned on GitHubNOASSERTIONSyntology: not harvested report
M155K4R4/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
MhYao2014/HyperbolicEmbedding mentioned on GitHubMITSyntology: not harvested report
MirkoLenz/ReCAP-Argument-Graph-Retrieval mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Universal Sentence Encoder (arXiv:1803.11175; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Nim-NLP/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
Omerktn/fastText-iterative mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ReCAP-UTR/Argument-Graph-Retrieval mentioned on GitHubtfApache-2.0Syntology: not harvested report
SarangShaikh201/fastText mentioned on GitHubSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
ahmedssabir/Visual-Semantic-Relatedness-with-Word-Embedding mentioned on GitHubpytorchSyntology: not harvested report
amymariaparker2401/new mentioned on GitHubNOASSERTIONSyntology: not harvested report
babylonhealth/fastText_multilingual mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
bamtercelboo/cw2vec mentioned on GitHubApache-2.0Syntology: not harvested report
bung87/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
currentsapi/fastlangid mentioned on GitHubApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastText.zip: Compressing text classification models (arXiv:1612.03651; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
dbaumgarten/FToDTF mentioned on GitHubtfApache-2.0Syntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
divisionai/fastText mentioned on GitHubMITSyntology: not harvested report
ericxsun/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
explosion/floret mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastText.zip: Compressing text classification models (arXiv:1612.03651; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
hufscapstone/Fast_text mentioned on GitHubMITSyntology: not harvested report
indix/whatthelang mentioned on GitHubApache-2.0Syntology: not harvested report
jen1995/fastText mentioned on GitHubMITSyntology: not harvested report
kpu/fastertext mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastText.zip: Compressing text classification models (arXiv:1612.03651; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
labdac/charlacompling mentioned on GitHubSyntology: not harvested report
linkfluence/fastText4j mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
lmd1993/fastTextBoost mentioned on GitHubNOASSERTIONSyntology: not harvested report
luckyPT/jvm-ml mentioned on GitHubtfSyntology: not harvested report
luhuiguo/jfasttext mentioned on GitHubNOASSERTIONSyntology: not harvested report
mrzzy/np-dl-assign-2 mentioned on GitHubtfSyntology: not harvested report
mwydmuch/extremeText mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
oapio/nlp-chinese-experiments mentioned on GitHubSyntology: not harvested report
plasticityai/magnitude mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
pommedeterresautee/fastrtext mentioned on GitHubNOASSERTIONSyntology: not harvested report
ppke-nlpg/fastText_factored-cbow mentioned on GitHubMITSyntology: not harvested report
rmenegaux/fastDNA mentioned on GitHubNOASSERTIONSyntology: not harvested report
romik9999/fasttext-1925f09ed3 mentioned on GitHubNOASSERTIONSyntology: not harvested report
trietnm2/sent2vec4j mentioned on GitHubSyntology: not harvested report
tshev/faster-FastText mentioned on GitHubMITSyntology: not harvested report
ulf1/augtxt mentioned on GitHubApache-2.0Syntology: 11 samples, 11 ran (0 instrument-failed) · 0 unverified report
vackosar/fasttext-vector-norms-and-oov-words mentioned on GitHubtfSyntology: not harvested report
vinhkhuc/JFastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
wyfish/fastText mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
xuzhezhaozhao/fastText_reading mentioned on GitHubNOASSERTIONSyntology: not harvested report
zhang2010hao/cw2vec-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
ZZhangyutong/fasttext mindsporeSyntology: not harvested report
cui0523/Code6 mindsporeSyntology: not harvested report
dmlc/gluon-nlp mxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing (arXiv:1907.04433; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

31 samples harvested: 25 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 6 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.

4ran · our draft was wrong
21ran
6unverified

Licence: 4 of the 31 samples are 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 7 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.

Kinetikm/fastTextRelearning community (archive-listed) 1 sample, 0 ran · 1 unverified
compute_similarity in 16 papers python/doc/examples/train_unsupervised.py unverified MIT (permissive) · 411c04ff52be0d9f · report
Omerktn/fastText-iterative community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
read_args python/fasttext_module/fasttext/FastText.py ran · our draft was wrong MIT (permissive) · f697966cbe929024 · report fixture: signature arg_list:list/1/str, arg_dict:dict/0/?, arg_names:list/1/str, default_values:dict/0/? · returned tuple · level recorded 2026-09-22
SarangShaikh201/fastText community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
create_lookup_tables utils.py ran · our draft was wrong fingerprinted licence not identified · pointer only · a16b79c7bc1860e5 · report fixture: signature words:list/1/str · returned tuple · level recorded 2026-09-22
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
utils.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 55d2494d83e5c523 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-22
get_batches in 12 papers utils.py unverified licence not identified · pointer only · cde234836e3f3978 · report
dbaumgarten/FToDTF community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
generate_ngram_per_word ftodtf/input.py ran fingerprinted Apache-2.0 (permissive) · b5b7c0a5146de532 · report fixture: signature word:str/0/str, ngram_window:int/0/int · returned list · level recorded 2026-09-26
pad_to_length in 18 papers ftodtf/input.py ran Apache-2.0 (permissive) · fa43a85dd995968e · report fixture: signature li:list/1/str, length:int/0/int, pad:str/0/str · returned list · level recorded 2026-09-26
parse_batch_func ftodtf/model.py ran Apache-2.0 (permissive) · 00bd40e0432ca4e5 · report fixture: signature batch_size:int/0/int · returned function · level recorded 2026-09-26
compute_word_similarities ftodtf/model.py unverified Apache-2.0 (permissive) · 153d1c4c32072113 · report
ngrams_to_vectors ftodtf/model.py unverified Apache-2.0 (permissive) · cf3407d8e4174215 · report
plasticityai/magnitude community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
check_glibc_version glibc.py ran MIT (permissive) · 39f3e4d5f2279ff9 · report fixture: signature version_str:str/0/str, required_major:int/0/int, minimum_minor:int/0/int · returned bool · level recorded 2026-09-26
entropy in 112 papers
census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket
pymagnitude/converter.py ran MIT (permissive) · 6e32ac79f67582c1 · report fixture: signature counter:dict/0/? · returned float64 · level recorded 2026-09-26
fast_md5_file pymagnitude/converter_shared.py ran MIT (permissive) · dee6b2dc58e092d3 · report fixture: signature path:str/0/str, block_size:int/0/int, stream:bool/0/bool · returned str · level recorded 2026-09-26
get_darwin_arches pep425tags.py ran MIT (permissive) · e3ecbfdb8037b64d · report fixture: signature major:int/0/int, minor:int/0/int, machine:str/0/str · returned list · level recorded 2026-09-26
get_flag pep425tags.py ran MIT (permissive) · 5066f582560cf77c · report fixture: signature var:str/0/str, fallback:callable/0/?, expected:bool/0/bool, warn:bool/0/bool · returned bool · level recorded 2026-09-26
have_compatible_glibc glibc.py ran fingerprinted MIT (permissive) · e0fd811edefc09ba · report fixture: signature required_major:int/0/int, minimum_minor:int/0/int · returned bool · level recorded 2026-09-26
md5_file pymagnitude/converter_shared.py ran MIT (permissive) · a89e48d6397ae9ba · report fixture: signature path:str/0/str, block_size:int/0/int · returned str · level recorded 2026-09-26
char_ngrams pymagnitude/converter_shared.py unverified MIT (permissive) · 478a1a9fc517ce62 · report
get_config_var pep425tags.py unverified MIT (permissive) · f546d4abc08099d7 · report
ulf1/augtxt community (archive-listed) 11 samples, 11 ran (0 instrument-failed) · 0 unverified
draw_index augtxt/typo.py ran fingerprinted Apache-2.0 (permissive) · 4464b010ea7987c2 · report fixture: signature n:int/0/int, loc:int/0/int · returned int · level recorded 2026-09-26
drop_word augtxt/order.py ran Apache-2.0 (permissive) · 839d40e2e8ad110b · report fixture: signature original:str/0/str, exclude:list/1/str, punct:str/0/str, num_aug:int/0/int · returned str · level recorded 2026-09-26
find_index in 8 papers augtxt/keyboard_layouts.py ran Apache-2.0 (permissive) · 8742e7667cc1dafa · report fixture: signature c:str/0/str, keymap:dict/0/? · returned tuple · level recorded 2026-09-26
merge_words augtxt/punct.py ran Apache-2.0 (permissive) · 280281e946bcacff · report fixture: signature text_:str/0/str, sep:list/1/str, exclude:list/1/str, num_aug:int/0/int · returned str · level recorded 2026-09-26
pressed_twice augtxt/typo.py ran fingerprinted Apache-2.0 (permissive) · ff4bb2b5311e1044 · report fixture: signature word:str/0/str, loc:str/0/str, keep_case:bool/0/bool · returned str · level recorded 2026-09-26
random_args augtxt/augmenters.py ran Apache-2.0 (permissive) · 4f5bb4400e32b7e9 · report fixture: signature cfg_:dict/0/? · returned dict · level recorded 2026-09-26
remove_syntaxinfo augtxt/punct.py ran fingerprinted Apache-2.0 (permissive) · 37d343258aa5993a · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
swap_consecutive augtxt/order.py ran Apache-2.0 (permissive) · 2eb54f96aa23c052 · report fixture: signature original:str/0/str, exclude:list/1/str, punct:str/0/str, num_aug:int/0/int · returned str · level recorded 2026-09-26
swap_consecutive augtxt/typo.py ran fingerprinted Apache-2.0 (permissive) · 48776fc059b48990 · report fixture: signature word:str/0/str, loc:str/0/str, keep_case:bool/0/bool · returned str · level recorded 2026-09-26
synonym_replacement in 8 papers augtxt/wordsubs.py ran Apache-2.0 (permissive) · e36a7da38a737dd2 · report fixture: signature original_seqs:list/1/list, synonyms:dict/0/?, num_augm:int/0/int, min_repl:int/0/int, max_repl:float/0/float, keep_case:bool/0/bool · returned list · level recorded 2026-09-26
write_twice augtxt/order.py ran Apache-2.0 (permissive) · 5f310db16b7971c6 · report fixture: signature original:str/0/str, exclude:list/1/str, punct:str/0/str, num_aug:int/0/int · returned str · level recorded 2026-09-26
zhang2010hao/cw2vec-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
load_model in 479 papers cw2vec.py ran · our draft was wrong no licence file found · pointer only · 847e1524ed1bff1a · report fixture: signature path:str/0/str, model:callable/0/? · returned SimpleModel · level recorded 2026-09-22

Tasks

Word EmbeddingsWord Similarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Word Similarity WS353 SkipGram Spearman's Rho 61.0 #3 of 3 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.

Methods

Introduced by this paper: fastText

fastText

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