The Universal Dependencies (UD) project seeks to develop cross-linguistically consistent treebank annotation of morphology and syntax for multiple languages. The first version of the dataset was released in 2015 and consisted of 10 treebanks over 10 languages. Version 2.7 released in 2020 consists of 183 treebanks over 104 languages. The annotation consists of UPOS (universal part-of-speech tags), XPOS (language-specific part-of-speech tags), Feats (universal morphological features), Lemmas, dependency heads and universal dependency labels.

520 PAPERS • 13 BENCHMARKS

Common Voice is an audio dataset that consists of a unique MP3 and corresponding text file. There are 9,283 recorded hours in the dataset. The dataset also includes demographic metadata like age, sex, and accent. The dataset consists of 7,335 validated hours in 60 languages.

448 PAPERS • 146 BENCHMARKS

MuST-C currently represents the largest publicly available multilingual corpus (one-to-many) for speech translation. It covers eight language directions, from English to German, Spanish, French, Italian, Dutch, Portuguese, Romanian and Russian. The corpus consists of audio, transcriptions and translations of English TED talks, and it comes with a predefined training, validation and test split.

216 PAPERS • 2 BENCHMARKS

A corpus of parallel text in 21 European languages from the proceedings of the European Parliament.

128 PAPERS • 1 BENCHMARK

This corpus comprises of monolingual data for 100+ languages and also includes data for romanized languages. This was constructed using the urls and paragraph indices provided by the CC-Net repository by processing January-December 2018 Commoncrawl snapshots. Each file comprises of documents separated by double-newlines and paragraphs within the same document separated by a newline. The data is generated using the open source CC-Net repository.

115 PAPERS • NO BENCHMARKS YET

WikiANN, also known as PAN-X, is a multilingual named entity recognition dataset. It consists of Wikipedia articles that have been annotated with LOC (location), PER (person), and ORG (organization) tags in the IOB2 format¹². This dataset serves as a valuable resource for training and evaluating named entity recognition models across various languages.

72 PAPERS • 4 BENCHMARKS

The shared task of CoNLL-2002 concerns language-independent named entity recognition. The types of named entities include: persons, locations, organizations and names of miscellaneous entities that do not belong to the previous three groups. The participants of the shared task were offered training and test data for at least two languages. Information sources other than the training data might have been used in this shared task.

70 PAPERS • 3 BENCHMARKS

End-to-end speech-to-text translation (ST) has recently witnessed an increased interest given its system simplicity, lower inference latency and less compounding errors compared to cascaded ST (i.e. speech recognition + machine translation). End-to-end ST model training, however, is often hampered by the lack of parallel data. Thus, we created CoVoST, a large-scale multilingual ST corpus based on Common Voice, to foster ST research with the largest ever open dataset. Its latest version covers translations from English into 15 languages---Arabic, Catalan, Welsh, German, Estonian, Persian, Indonesian, Japanese, Latvian, Mongolian, Slovenian, Swedish, Tamil, Turkish, Chinese---and from 21 languages into English, including the 15 target languages as well as Spanish, French, Italian, Dutch, Portuguese, Russian. It has total 2,880 hours of speech and is diversified with 78K speakers.

66 PAPERS • NO BENCHMARKS YET

OSCAR or Open Super-large Crawled ALMAnaCH coRpus is a huge multilingual corpus obtained by language classification and filtering of the Common Crawl corpus using the goclassy architecture. The dataset used for training multilingual models such as BART incorporates 138 GB of text.

64 PAPERS • NO BENCHMARKS YET

CELEX database comprises three different searchable lexical databases, Dutch, English and German. The lexical data contained in each database is divided into five categories: orthography, phonology, morphology, syntax (word class) and word frequency.

59 PAPERS • NO BENCHMARKS YET

Europarl-ST is a multilingual Spoken Language Translation corpus containing paired audio-text samples for SLT from and into 9 European languages, for a total of 72 different translation directions. This corpus has been compiled using the debates held in the European Parliament in the period between 2008 and 2012.

57 PAPERS • NO BENCHMARKS YET

WikiLingua includes ~770k article and summary pairs in 18 languages from WikiHow. Gold-standard article-summary alignments across languages are extracted by aligning the images that are used to describe each how-to step in an article.

52 PAPERS • 5 BENCHMARKS

Multilingual Knowledge Questions and Answers (MKQA) is an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Answers are based on a language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering.

49 PAPERS • NO BENCHMARKS YET

CoVoST is a large-scale multilingual speech-to-text translation corpus. Its latest 2nd version covers translations from 21 languages into English and from English into 15 languages. It has total 2880 hours of speech and is diversified with 78K speakers and 66 accents.

34 PAPERS • 1 BENCHMARK

Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically-diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model selection for massively multilingual image captioning models, and show strong correlation results with human evaluations when using XM3600 as golden references for automatic metrics.

28 PAPERS • 1 BENCHMARK

CVSS is a massively multilingual-to-English speech to speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems

26 PAPERS • 4 BENCHMARKS

license: apache-2.0 tags: human-feedback size_categories: 100K<n<1M pretty_name: OpenAssistant Conversations

25 PAPERS • NO BENCHMARKS YET

XGLUE is an evaluation benchmark XGLUE,which is composed of 11 tasks that span 19 languages. For each task, the training data is only available in English. This means that to succeed at XGLUE, a model must have a strong zero-shot cross-lingual transfer capability to learn from the English data of a specific task and transfer what it learned to other languages. Comparing to its concurrent work XTREME, XGLUE has two characteristics: First, it includes cross-lingual NLU and cross-lingual NLG tasks at the same time; Second, besides including 5 existing cross-lingual tasks (i.e. NER, POS, MLQA, PAWS-X and XNLI), XGLUE selects 6 new tasks from Bing scenarios as well, including News Classification (NC), Query-Ad Matching (QADSM), Web Page Ranking (WPR), QA Matching (QAM), Question Generation (QG) and News Title Generation (NTG). Such diversities of languages, tasks and task origin provide a comprehensive benchmark for quantifying the quality of a pre-trained model on cross-lingual natural lan

22 PAPERS • 2 BENCHMARKS

xSID, a new evaluation benchmark for cross-lingual (X) Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect, covering Arabic (ar), Chinese (zh), Danish (da), Dutch (nl), English (en), German (de), Indonesian (id), Italian (it), Japanese (ja), Kazakh (kk), Serbian (sr), Turkish (tr) and an Austro-Bavarian German dialect, South Tyrolean (de-st).

18 PAPERS • NO BENCHMARKS YET

X-FACT is a large publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers. The dataset includes a multilingual evaluation benchmark that measures both out-of-domain generalization, and zero-shot capabilities of the multilingual models.

16 PAPERS • 1 BENCHMARK

MultiEURLEX is a multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. The dataset covers 23 official EU languages from 7 language families.

11 PAPERS • NO BENCHMARKS YET

Global Voices is a multilingual dataset for evaluating cross-lingual summarization methods. It is extracted from social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages.

9 PAPERS • NO BENCHMARKS YET

EUR-Lex-Sum is a dataset for cross-lingual summarization. It is based on manually curated document summaries of legal acts from the European Union law platform. Documents and their respective summaries exist as crosslingual paragraph-aligned data in several of the 24 official European languages, enabling access to various cross-lingual and lower-resourced summarization setups. The dataset contains up to 1,500 document/summary pairs per language, including a subset of 375 cross-lingually aligned legal acts with texts available in all 24 languages.

8 PAPERS • NO BENCHMARKS YET

We introduce HumanEval-XL, a massively multilingual code generation benchmark specifically crafted to address this deficiency. HumanEval-XL establishes connections between 23 NLs and 12 programming languages (PLs), and comprises of a collection of 22,080 prompts with an average of 8.33 test cases. By ensuring parallel data across multiple NLs and PLs, HumanEval-XL offers a comprehensive evaluation platform for multilingual LLMs, allowing the assessment of the understanding of different NLs. Our work serves as a pioneering step towards filling the void in evaluating NL generalization in the area of multilingual code generation. We make our evaluation code and data publicly available at https://github.com/FloatAI/HumanEval-XL.

6 PAPERS • NO BENCHMARKS YET

WikiNEuRal is a high-quality automatically-generated dataset for Multilingual Named Entity Recognition.

6 PAPERS • NO BENCHMARKS YET

MuMiN is a misinformation graph dataset containing rich social media data (tweets, replies, users, images, articles, hashtags), spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade.

5 PAPERS • 3 BENCHMARKS

The DISRPT 2019 workshop introduces the first iteration of a cross-formalism shared task on discourse unit segmentation. Since all major discourse parsing frameworks imply a segmentation of texts into segments, learning segmentations for and from diverse resources is a promising area for converging methods and insights. We provide training, development and test datasets from all available languages and treebanks in the RST, SDRT and PDTB formalisms, using a uniform format. Because different corpora, languages and frameworks use different guidelines for segmentation, the shared task is meant to promote design of flexible methods for dealing with various guidelines, and help to push forward the discussion of standards for discourse units. For datasets which have treebanks, we will evaluate in two different scenarios: with and without gold syntax, or otherwise using provided automatic parses for comparison.

4 PAPERS • NO BENCHMARKS YET

GeoCoV19 is a large-scale Twitter dataset containing more than 524 million multilingual tweets. The dataset contains around 378K geotagged tweets and 5.4 million tweets with Place information. The annotations include toponyms from the user location field and tweet content and resolve them to geolocations such as country, state, or city level. In this case, 297 million tweets are annotated with geolocation using the user location field and 452 million tweets using tweet content.

4 PAPERS • NO BENCHMARKS YET

A dataset of approximately 75,000 phrases and sentences, syntactically analyzed as typelogical derivations (i.e. proofs of modal intuitionistic linear logic, or programs of the corresponding λ calculus). Analyses were obtained by transforming the dependency graphs of the Lassy-Small corpus.

4 PAPERS • NO BENCHMARKS YET

The DISRPT 2021 shared task, co-located with CODI 2021 at EMNLP, introduces the second iteration of a cross-formalism shared task on discourse unit segmentation and connective detection, as well as the first iteration of a cross-formalism discourse relation classification task.

3 PAPERS • NO BENCHMARKS YET

DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity.

3 PAPERS • NO BENCHMARKS YET

MRS, a multilingual reply suggestion dataset with ten languages. MRS can be used to compare two families of models: 1) retrieval models that select the reply from a fixed set and 2) generation models that produce the reply from scratch. Therefore, MRS complements existing cross-lingual generalization benchmarks that focus on classification and sequence labeling tasks.

3 PAPERS • NO BENCHMARKS YET

The DBRD (pronounced dee-bird) dataset contains over 110k book reviews along with associated binary sentiment polarity labels. It is greatly influenced by the Large Movie Review Dataset and intended as a benchmark for sentiment classification in Dutch.

2 PAPERS • 1 BENCHMARK

The evaluation of vision-language models (VLMs) has mainly relied on English-language benchmarks, leaving significant gaps in both multilingual and multicultural coverage. While multilingual benchmarks have expanded, both in size and languages, many rely on translations of English datasets, failing to capture cultural nuances. In this work, we propose Kaleidoscope, as the most comprehensive exam benchmark to date for the multilingual evaluation of vision-language models. Kaleidoscope is a large-scale, in-language multimodal benchmark designed to evaluate VLMs across diverse languages and visual inputs. Kaleidoscope covers 18 languages and 14 different subjects, amounting to a total of 20,911 multiple-choice questions. Built through an open science collaboration with a diverse group of researchers worldwide, Kaleidoscope ensures linguistic and cultural authenticity. We evaluate top-performing multilingual vision-language models and find that they perform poorly on low-resource languages

2 PAPERS • NO BENCHMARKS YET

DpgMedia2019 is a Dutch news dataset for partisanship detection. It contains more than 100K articles that are labelled on the publisher level and 776 articles that were crowdsourced using an internal survey platform and labelled on the article level.

1 PAPER • NO BENCHMARKS YET

EMC Dutch clinical corpus contains four types of anonymized clinical documents: entries from general practitioners, specialists’ letters, radiology reports, and discharge letters. The identified UMLS terms in the corpus are annotated for negation, temporality, and experiencer properties.

1 PAPER • NO BENCHMARKS YET

Dataset Description EUROPA is a dataset designed for training and evaluating multilingual keyphrase generation models in the legal domain. It consists of legal judgments from the Court of Justice of the European Union (EU) and includes instances in all 24 official EU languages.

1 PAPER • NO BENCHMARKS YET

Dataset Summary INCLUDE is a comprehensive knowledge- and reasoning-centric benchmark across 44 languages that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed. It contains 22,637 4-option multiple-choice-questions (MCQ) extracted from academic and professional exams, covering 57 topics, including regional knowledge.

1 PAPER • NO BENCHMARKS YET

A corpus of about 115 hours of Dutch speech from juveniles, non-native speakers and seniors, consisting of read text and man-machine dialogues.

1 PAPER • NO BENCHMARKS YET

LEMONADE is a large, expert-annotated dataset for event extraction from news articles in 20 languages: English, Spanish, Arabic, French, Italian, Russian, German, Turkish, Burmese, Indonesian, Ukrainian, Korean, Portuguese, Dutch, Somali, Nepali, Chinese, Persian, Hebrew, and Japanese.

1 PAPER • NO BENCHMARKS YET

This dataset contains named entities annotations for European Parliament recordings in Dutch, French, German and Spanish. The entity annotation scheme follows OntoNotes v5. The original unannotated dataset is VoxPopuli.

1 PAPER • NO BENCHMARKS YET

Mega-COV is a billion-scale dataset from Twitter for studying COVID-19. The dataset is diverse (covers 234 countries), longitudinal (goes as back as 2007), multilingual (comes in 65 languages), and has a significant number of location-tagged tweets (~32M tweets).

1 PAPER • NO BENCHMARKS YET

Mint is a new Multilingual intimacy analysis dataset covering 13,384 tweets in 10 languages including English, French, Spanish, Italian, Portuguese, Korean, Dutch, Chinese, Hindi, and Arabic. The dataset is released along with the SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis.

1 PAPER • NO BENCHMARKS YET

This dataset contains orthographic samples of words in 19 languages (ar, br, de, en, eno, ent, eo, es, fi, fr, fro, it, ko, nl, pt, ru, sh, tr, zh). Each sample contains two text features: a Word (the textual representation of the word according to its orthography) and a Pronunciation (the highest-surface IPA pronunciation of the word as pronunced in its language).

1 PAPER • NO BENCHMARKS YET

PolyNews is a multilingual dataset containing news titles in 77 languages and 19 scripts.

1 PAPER • NO BENCHMARKS YET

PolyNews is a multilingual parallel dataset containing news titles 833 language pairs, spanning in 64 languages and 17 scripts.

1 PAPER • NO BENCHMARKS YET

The SWC is a corpus of aligned Spoken Wikipedia articles from the English, German, and Dutch Wikipedia. This corpus has several outstanding characteristics:

1 PAPER • 1 BENCHMARK

The IT Translation Task is a shared task introduced in the First Conference on Machine Translation. Compared to WMT 2016 News, this task brought several novelties to WMT:

1 PAPER • NO BENCHMARKS YET