Papers › A Corpus for Multilingual Document Classification in Eight Languages

A Corpus for Multilingual Document Classification in Eight Languages

24 May 2018LREC 2018 5arXiv:1805.09821archive 2025-07-28

Holger Schwenk, Xi-An Li

Cross-lingual document classification aims at training a document classifier on resources in one language and transferring it to a different language without any additional resources. Several approaches have been proposed in the literature and the current best practice is to evaluate them on a subset of the Reuters Corpus Volume 2. However, this subset covers only few languages (English, German, French and Spanish) and almost all published works focus on the the transfer between English and German. In addition, we have observed that the class prior distributions differ significantly between the languages. We argue that this complicates the evaluation of the multilinguality. In this paper, we propose a new subset of the Reuters corpus with balanced class priors for eight languages. By adding Italian, Russian, Japanese and Chinese, we cover languages which are very different with respect to syntax, morphology, etc. We provide strong baselines for all language transfer directions using multilingual word and sentence embeddings respectively. Our goal is to offer a freely available framework to evaluate cross-lingual document classification, and we hope to foster by these means, research in this important area.

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 15 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 14 samples from 1 repository, 7 ran (7 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/MLDoc officialmentioned in paperSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
n-waves/multifit mentioned on GitHubMITSyntology: 14 samples, 7 ran (0 instrument-failed) · 7 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

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 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.

1ran · violated contract
7ran
7unverified

Licence: 1 of the 15 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 2 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.

facebookresearch/MLDoc official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
check_data_sufficiency sampling_rcv2.py ran · violated contract licence not identified · pointer only · ecc0491c7303786a · report fixture: signature example_counts:dict/0/?, num_samples:int/0/int, label_priors:dict/0/?, threshold:float/0/float · returned bool · level recorded 2026-09-22
n-waves/multifit community (archive-listed) 14 samples, 7 ran (0 instrument-failed) · 7 unverified
build_vocab in 36 papers multifit/datasets/postprocess_wikitext.py ran MIT (permissive) · ddc663023f98e224 · report fixture: signature file_path:str/0/str, cutoff:int/0/int · returned dict · level recorded 2026-09-26
cross_remove_duplicates split-cls.py ran MIT (permissive) · 5f761b0bed59bd96 · report fixture: signature from_df:DataFrame/0/?, other_df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-26
detect_lang_from_dataset_path multifit/training.py ran MIT (permissive) · 57b99f2ca95b81fb · report fixture: signature dataset_path:PosixPath/0/? · returned str · level recorded 2026-09-26
get_and_unzip_data prepare_xnli.py ran MIT (permissive) · 6f5f358981413f2c · report fixture: signature url:str/0/str, fname:str/0/str, dest:str/0/str · returned PosixPath · level recorded 2026-09-26
remove_duplicates in 15 papers split-cls.py ran MIT (permissive) · 21075dccf90eda43 · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-26
remove_rt split-cls.py ran MIT (permissive) · 3d6c8a5734a1712d · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-26
to_json_serializable multifit/training.py ran MIT (permissive) · f32a11c0002ecb23 · report fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-26
download_data in 6 papers prepare_xnli.py unverified MIT (permissive) · fea81e299034679b · report
get_texts in 12 papers multifit/datasets/utils.py unverified MIT (permissive) · c657462a7c04bcc5 · report
multifit1152_lstm_nl3 multifit/configurations.py unverified MIT (permissive) · 47aefbe32b4a53dc · report
multifit1552_fp32 multifit/configurations.py unverified MIT (permissive) · 1232e453f40b140f · report
patch_learner multifit/training.py unverified MIT (permissive) · 620047035f3f6733 · report
read_clas_csv multifit/datasets/dataset.py unverified MIT (permissive) · 356ad3b49f5db3bc · report
read_wiki_articles multifit/datasets/dataset.py unverified MIT (permissive) · e4d788b551ad578b · report

Tasks

ClassificationCross-Lingual Document ClassificationDocument ClassificationGeneral ClassificationSentenceSentence Embeddings

Datasets

Introduced by this paper, per the archive.

MLDoc

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Chinese MultiCCA + CNN Accuracy 74.73 #3 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Chinese BiLSTM (UN) Accuracy 71.97 #4 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-French BiLSTM (UN) Accuracy 74.52 #4 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-French BiLSTM (Europarl) Accuracy 72.83 #5 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-French MultiCCA + CNN Accuracy 72.38 #6 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-German MultiCCA + CNN Accuracy 81.2% #4 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-German BiLSTM (Europarl) Accuracy 71.83% #5 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Italian MultiCCA + CNN Accuracy 69.38 #3 of 4 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Italian BiLSTM (Europarl) Accuracy 60.73 #4 of 4 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Japanese MultiCCA + CNN Accuracy 67.63 #2 of 3 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Russian BiLSTM (UN) Accuracy 61.42 #4 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Russian MultiCCA + CNN Accuracy 60.8 #5 of 5 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Spanish MultiCCA + CNN Accuracy 72.5 #4 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Spanish BiLSTM (UN) Accuracy 69.5 #5 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Spanish BiLSTM (Europarl) Accuracy 66.65 #6 of 6 Archive leaderboard report
Cross-Lingual Document Classification MLDoc Zero-Shot German-to-French BiLSTM (Europarl) Accuracy 75.45 #1 of 1 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