In this paper, we introduce XGLUE, a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora, and evaluate their performance across a diverse set of cross-lingual tasks. Comparing to GLUE (Wang et al., 2019), which is labeled in English and includes natural language understanding tasks only, XGLUE has three main advantages: (1) it provides two corpora with different sizes for cross-lingual pre-training; (2) it provides 11 diversified tasks that cover both natural language understanding and generation scenarios; (3) for each task, it provides labeled data in multiple languages. We extend a recent cross-lingual pre-trained model Unicoder (Huang et al., 2019) to cover both understanding and generation tasks, which is evaluated on XGLUE as a strong baseline. We also evaluate the base versions (12-layer) of Multilingual BERT, XLM and XLM-R for comparison.<\/p>\n","protected":false},"excerpt":{"rendered":"
In this paper, we introduce XGLUE, a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora, and evaluate their performance across a diverse set of cross-lingual tasks. Comparing to GLUE (Wang et al., 2019), which is labeled in English and includes natural language understanding tasks only, XGLUE has three main […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13545],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-657132","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"arXiv preprint","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-4-19","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2004.01401","label_id":"243109","label":0},{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/05\/2004.01401_XGLUE-A-New-Benchmark-Dataset.pdf","id":"663819","title":"2004-01401_xglue-a-new-benchmark-dataset","label_id":"243132","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":663819,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/06\/2004.01401_XGLUE-A-New-Benchmark-Dataset.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Yaobo Liang","user_id":36036,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Yaobo Liang"},{"type":"user_nicename","value":"Nan Duan","user_id":33052,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nan Duan"},{"type":"text","value":"Yeyun Gong","user_id":0,"rest_url":false},{"type":"text","value":"Ning Wu","user_id":0,"rest_url":false},{"type":"text","value":"Fenfei Guo","user_id":0,"rest_url":false},{"type":"text","value":"Weizhen Qi","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Ming Gong (YIMING)","user_id":39078,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ming Gong (YIMING)"},{"type":"user_nicename","value":"Linjun Shou (\u5bff\u6797\u94a7)","user_id":39060,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Linjun Shou (\u5bff\u6797\u94a7)"},{"type":"user_nicename","value":"Daxin Jiang (\u59dc\u5927\u6615)","user_id":31642,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daxin Jiang (\u59dc\u5927\u6615)"},{"type":"text","value":"Guihong Cao","user_id":0,"rest_url":false},{"type":"text","value":"Xiaodong Fan","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Bruce Zhang","user_id":31325,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Bruce Zhang"},{"type":"text","value":"Rahul Agrawal","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Edward Cui","user_id":31719,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Edward Cui"},{"type":"text","value":"Sining Wei","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Taroon Bharti","user_id":33900,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Taroon Bharti"},{"type":"text","value":"Jiun-Hung Chen","user_id":0,"rest_url":false},{"type":"text","value":"Winnie Wu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Shuguang Liu","user_id":33632,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shuguang Liu"},{"type":"user_nicename","value":"Fan Yang","user_id":31782,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Fan Yang"},{"type":"user_nicename","value":"Ming Zhou","user_id":32942,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ming Zhou"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[773560,920469],"msr_project":[663420],"publication":[],"video":[],"download":[668187,693600,746317],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/657132"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/657132\/revisions"}],"predecessor-version":[{"id":657135,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/657132\/revisions\/657135"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=657132"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=657132"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=657132"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=657132"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=657132"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=657132"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=657132"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=657132"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=657132"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=657132"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=657132"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=657132"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=657132"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=657132"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=657132"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}