Datasets › MLDoc

MLDoc (Multilingual Document Classification Corpus)

Introduced by Holger Schwenk et al. in A Corpus for Multilingual Document Classification in Eight Languages1 Jan 2018 archive 2025-07-28

Multilingual Document Classification Corpus (MLDoc) is a cross-lingual document classification dataset covering English, German, French, Spanish, Italian, Russian, Japanese and Chinese. It is a subset of the Reuters Corpus Volume 2 selected according to the following design choices:

  • uniform class coverage: same number of examples for each class and language,
  • official train / development / test split: for each language a training data of different sizes (1K, 2K, 5K and 10K stories), a development (1K) and a test corpus (4K) are provided (with exception of Spanish and Russian with 9458 and 5216 training documents respectively.

Source: A Corpus for Multilingual Document Classification in Eight Languages

Benchmarks archive 2025-07-28

All 8 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Spanish XLMft UDA Accuracy 96.8 Bridging the domain gap in cross-lingual document classification laiguokun/xlu-data 6 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-French XLMft UDA Accuracy 96.05 Bridging the domain gap in cross-lingual document classification laiguokun/xlu-data 6 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-German XLMft UDA Accuracy 96.95% Bridging the domain gap in cross-lingual document classification laiguokun/xlu-data 5 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Chinese XLMft UDA Accuracy 93.32 Bridging the domain gap in cross-lingual document classification laiguokun/xlu-data 5 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Russian XLMft UDA Accuracy 89.7 Bridging the domain gap in cross-lingual document classification laiguokun/xlu-data 5 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Italian MultiFiT, pseudo Accuracy 76.02 MultiFiT: Efficient Multi-lingual Language Model Fine-tuning piegu/language-models +3 4 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot English-to-Japanese MultiFiT, pseudo Accuracy 69.57 MultiFiT: Efficient Multi-lingual Language Model Fine-tuning piegu/language-models +3 3 Compare
Cross-Lingual Document Classification MLDoc Zero-Shot German-to-French BiLSTM (Europarl) Accuracy 75.45 A Corpus for Multilingual Document Classification in... n-waves/multifit +1 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 4 · with a code link: 4 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 4 with a benchmark row: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 4 of 4 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 53. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • MLDoc
  • MLDoc Zero-Shot German-to-French
  • MLDoc Zero-Shot English-to-Spanish
  • MLDoc Zero-Shot English-to-Russian
  • MLDoc Zero-Shot English-to-Japanese
  • MLDoc Zero-Shot English-to-Italian
  • MLDoc Zero-Shot English-to-German
  • MLDoc Zero-Shot English-to-French
  • MLDoc Zero-Shot English-to-Chinese

9 variant names, as the archive lists them.

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