CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs
Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. In this paper, we exploit the signals embedded in URLs to label web documents at scale with an average precision of 94.5% across different language pairs. We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other. We release a new web dataset consisting of over 392 million URL pairs from Common Crawl covering documents in 8144 language pairs of which 137 pairs include English. In addition to curating this massive dataset, we introduce baseline methods that leverage cross-lingual representations to identify aligned documents based on their textual content. Finally, we demonstrate the value of this parallel documents dataset through a downstream task of mining parallel sentences and measuring the quality of machine translations from models trained on this mined data. Our objective in releasing this dataset is to foster new research in cross-lingual NLP across a variety of low, medium, and high-resource languages.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CLIRMatrix: A massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval
We present CLIRMatrix, a massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval extracted automatically from Wikipedia. CLIRMatrix comprises (1) BI-139, a bilingual data…
Cross-Lingual Information RetrievalInformation RetrievalRetrievalA General-Purpose Multilingual Document Encoder
Massively multilingual pretrained transformers (MMTs) have tremendously pushed the state of the art on multilingual NLP and cross-lingual transfer of NLP models in particular. While a large body of work leveraged MMTs to…
Cross-Lingual TransferDocument ClassificationLong-range modelingMultilingual NLP+2SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access. MLIR enables users to retrieve semantically relevant…
Information RetrievalA New Massive Multilingual Dataset for High-Performance Language Technologies
We present the HPLT (High Performance Language Technologies) language resources, a new massive multilingual dataset including both monolingual and bilingual corpora extracted from CommonCrawl and previously unused web cr…
Language ModelingLanguage ModellingMachine TranslationManagement+1An Expanded Massive Multilingual Dataset for High-Performance Language Technologies
Training state-of-the-art large language models requires vast amounts of clean and diverse textual data. However, building suitable multilingual datasets remains a challenge. In this work, we present HPLT v2, a collectio…
Machine TranslationSentence