Browse State-of-the-Art › Cross-Lingual Document Classification
Cross-Lingual Document Classification
12 papers with code · 10 benchmarks · 2 datasets archive 2025-07-28
Cross-lingual document classification refers to the task of using data and models available for one language for which ample such resources are available (e.g., English) to solve classification tasks in another, commonly low-resource, language.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
10 leaderboard tables shown for this task, 10 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each 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”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 12 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 25 tagged: 4 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 25 of 25, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology 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”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
26 Dec 2018 13 repositories listed Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 4 pointer-only (licence)We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts.
-
4 Oct 2019 10 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Large deep learning models offer significant accuracy gains, but training billions to trillions of parameters is challenging.
-
10 Sep 2019 4 repositories listedPretrained language models are promising particularly for low-resource languages as they only require unlabelled data.
-
28 Dec 2019 2 repositories listedRecent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation.
-
24 May 2018 2 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 15 harvested samples) · 1 pointer-only (licence)In addition, we have observed that the class prior distributions differ significantly between the languages.
-
6 Jun 2016 2 repositories listed Syntology official (archive's flag): 1 ran · 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) · 1 unverified (of 2 harvested samples)To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a…
-
9 Oct 2014 2 repositories listedWe introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets…
-
27 Jan 2021 1 repository listedThe great majority of languages in the world are considered under-resourced for the successful application of deep learning methods.
-
16 Sep 2019 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)We consider the setting of semi-supervised cross-lingual understanding, where labeled data is available in a source language (English), but only unlabeled data is available in the target language.
-
30 Jun 2016 1 repository listedCrosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools.
-
17 Apr 2014 1 repository listedWe present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings.
-
20 Dec 2013 1 repository listedDistributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP.
-
Margin-aware Unsupervised Domain Adaptation for Cross-lingual Text Labeling1 Nov 2020 0 repositories listedUnsupervised domain adaptation addresses the problem of leveraging labeled data in a source domain to learn a well-performing model in a target domain where labels are unavailable.
-
Wasserstein distances for evaluating cross-lingual embeddings24 Oct 2019 0 repositories listedWord embeddings are high dimensional vector representations of words that capture their semantic similarity in the vector space.
-
Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification22 Dec 2018 0 repositories listedText classification must sometimes be applied in a low-resource language with no labeled training data.
-
Variational learning across domains with triplet information22 Oct 2018 0 repositories listedThe work investigates deep generative models, which allow us to use training data from one domain to build a model for another domain.
-
NMT-based Cross-lingual Document Embeddings29 Jul 2018 0 repositories listedThis paper investigates a cross-lingual document embedding method that improves the current Neural machine Translation framework based Document Vector (NTDV or simply NV).
-
A Multi-task Approach to Learning Multilingual Representations1 Jul 2018 0 repositories listedWe present a novel multi-task modeling approach to learning multilingual distributed representations of text.
-
Multilingual Seq2seq Training with Similarity Loss for Cross-Lingual Document Classification1 Jul 2018 0 repositories listedIn this paper we continue experiments where neural machine translation training is used to produce joint cross-lingual fixed-dimensional sentence embeddings.
-
Variational learning across domains with triplet information22 Jun 2018 0 repositories listedThe work investigates deep generative models, which allow us to use training data from one domain to build a model for another domain.
-
KIT-Multi: A Translation-Oriented Multilingual Embedding Corpus1 May 2018 0 repositories listed
-
Learning Monolingual Compositional Representations via Bilingual Supervision1 Aug 2016 0 repositories listed
-
Learning Cross-lingual Representations with Matrix Factorization1 Jun 2016 0 repositories listed
-
Learning Cross-lingual Word Embeddings via Matrix Co-factorization1 Jul 2015 0 repositories listed
-
A Multiplicative Model for Learning Distributed Text-Based Attribute Representations10 Jun 2014 0 repositories listedIn this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings.
Syntology lines on 5 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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