Papers › FastText.zip: Compressing text classification models

FastText.zip: Compressing text classification models

12 Dec 2016arXiv:1612.03651archive 2025-07-28

Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, Tomas Mikolov

We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy.

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

No sample from the archive's official repository (facebookresearch/fastText) is linked to this paper; the 18 samples below come from 6 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 18 code samples harvested from 6 repositories linked to this paper: 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. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 6 repositories, 11 ran (8 with no instrument failure; 3 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 4 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.

44 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
DW-yejing/fasttext4j-jdk6 mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
FengJiaChunFromSYSU/fastText mentioned on GitHubMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How to Fine-Tune BERT for Text Classification? (arXiv:1905.05583; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified) and RoBERTa: A Robustly Optimized BERT Pretraining Approach (arXiv:1907.11692; that paper's own run record: 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 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: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Enriching Word Vectors with Subword Information (arXiv:1607.04606; that paper's own run record: 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); nothing checks that they implement this paper's method. 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
Nim-NLP/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
Omerktn/fastText-iterative mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Enriching Word Vectors with Subword Information (arXiv:1607.04606; that paper's own run record: 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); nothing checks that they implement this paper's method. report
SarangShaikh201/fastText mentioned on GitHubSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
amymariaparker2401/new mentioned on GitHubNOASSERTIONSyntology: not harvested report
autumn0409/Log-based-Anomaly-Detection-System mentioned on GitHubSyntology: not harvested report
bung87/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
code2k13/nlphose mentioned on GitHubApache-2.0Syntology: not harvested report
code2k13/nlppipe mentioned on GitHubApache-2.0Syntology: not harvested report
currentsapi/fastlangid mentioned on GitHubApache-2.0Syntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
divisionai/fastText mentioned on GitHubMITSyntology: not harvested report
ericxsun/fastText mentioned on GitHubNOASSERTIONSyntology: not harvested report
explosion/floret mentioned on GitHubMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
hanfeng108/Language-Detection mentioned on GitHubpytorchSyntology: not harvested 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: 2 samples, 1 ran (0 instrument-failed) · 1 unverified 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
marfoq/unsupervised_translator mentioned on GitHubSyntology: not harvested report
mwydmuch/extremeText mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
omarfoq/unsupervised_translator mentioned on GitHubSyntology: not harvested 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
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
zafercavdar/fasttext-langdetect mentioned on GitHubMITSyntology: 1 sample, 0 ran · 1 unverified report
2023-MindSpore-1/ms-code-5 mindsporeSyntology: not harvested 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

18 samples harvested: 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. “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.

3ran · our draft was wrong
8ran
7unverified

Licence: 13 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

FengJiaChunFromSYSU/fastText community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
find_nearest_neighbor python/fastText/util/util.py ran MIT recorded; this copy not marked cleared · pointer only · 5d48a5764718f390 · report fixture: signature query:ndarray/1/float, vectors:ndarray/2/float, ban_set:set/0/?, cossims:ndarray/1/float · returned int64 · level recorded 2026-09-24
idx alignment/utils.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 831f6e244ecea2bb · report fixture: signature words:list/1/str · returned dict · level recorded 2026-09-25
procrustes in 6 papers alignment/utils.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 6f28ff1eccefb093 · report fixture: signature X_src:ndarray/2/float, Y_tgt:ndarray/2/float · returned ndarray · level recorded 2026-09-25
sqrt_eig alignment/unsup_align.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · e4a10d52bc6d1601 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24
test in 377 papers python/fastText/util/util.py ran MIT recorded; this copy not marked cleared · pointer only · 5c3bcf5ae2042c99 · report fixture: signature predictions:list/1/list, labels:list/1/list, k:int/0/int · returned tuple · level recorded 2026-09-24
getknn alignment/align.py unverified MIT recorded; this copy not marked cleared · pointer only · f685d8c430dfac70 · report
load_vectors in 6 papers alignment/utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 5b38e4065c54800a · report
SarangShaikh201/fastText community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
create_lookup_tables utils.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 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 identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 55d2494d83e5c523 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-22
get_batches in 12 papers utils.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · cde234836e3f3978 · report
currentsapi/fastlangid community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
clean_text in 84 papers fastlangid/utils.py ran fingerprinted Apache-2.0 (permissive) · cc21a5b05edde91f · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
convert2unicode fastlangid/regex_rule.py ran fingerprinted Apache-2.0 (permissive) · a6a95c0a40fa3d1f · report fixture: signature code:str/0/str · returned str · level recorded 2026-09-26
only_punctuations fastlangid/utils.py unverified Apache-2.0 (permissive) · 4b17e794d15f700c · report
explosion/floret community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
read_args python/floret_module/floret/floret.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
reduce_model python/floret_module/floret/util/util.py unverified MIT (permissive) here; the stored copy is pointer only · 3ab9d330ea24c434 · report
kpu/fastertext community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
guess_target_name reduce_model.py ran MIT recorded; this copy not marked cleared · pointer only · c2a80677a6cb6044 · report fixture: signature model_file:str/0/str, initial_dim:int/0/int, target_dim:int/0/int · returned str · level recorded 2026-09-24
rcsls alignment/unsup_multialign.py unverified MIT recorded; this copy not marked cleared · pointer only · d484b37352fc8959 · report
zafercavdar/fasttext-langdetect community (archive-listed) 1 sample, 0 ran · 1 unverified
download_model in 24 papers src/ftlangdetect/detect.py unverified MIT (permissive) · c0cfe33b609d38fd · report

Tasks

General ClassificationQuantizationText ClassificationWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

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