{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:19:48Z","timestamp":1750220388010,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,14]]},"DOI":"10.1145\/3447548.3470791","type":"proceedings-article","created":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T18:33:08Z","timestamp":1628879588000},"page":"4068-4069","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Language Scaling"],"prefix":"10.1145","author":[{"given":"Linjun","family":"Shou","sequence":"first","affiliation":[{"name":"Microsoft STCA NLP Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft STCA NLP Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Simon Fraser University, British Columbia, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiubo","family":"Geng","sequence":"additional","affiliation":[{"name":"Microsoft STCA NLP Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft STCA NLP Group, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Microsoft STCA NLP Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations. ArXiv abs\/1910.10893","author":"Bao Zuyi","year":"2019","unstructured":"Zuyi Bao , Rui Huang , C. Li , and Kenny Zhu . 2019. Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations. ArXiv abs\/1910.10893 ( 2019 ). Zuyi Bao, Rui Huang, C. Li, and Kenny Zhu. 2019. Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations. ArXiv abs\/1910.10893 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Hany Hassan, Wei Wang, and Claire Cardie.","author":"Chen Xilun","year":"2019","unstructured":"Xilun Chen , Ahmed Hassan Awadallah , Hany Hassan, Wei Wang, and Claire Cardie. 2019 . Multi-Source Cross-Lingual Model Transfer: Learning What to Share. In ACL. Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, and Claire Cardie. 2019. Multi-Source Cross-Lingual Model Transfer: Learning What to Share. In ACL."},{"key":"e_1_3_2_1_3_1","volume-title":"Cross-Lingual Natural Language Generation via Pre-Training. ArXiv abs\/1909.10481","author":"Chi Zewen","year":"2020","unstructured":"Zewen Chi , Li Dong , Furu Wei , Wenhui Wang , Xian-Ling Mao , and He yan Huang . 2020. Cross-Lingual Natural Language Generation via Pre-Training. ArXiv abs\/1909.10481 ( 2020 ). Zewen Chi, Li Dong, Furu Wei, Wenhui Wang, Xian-Ling Mao, and He yan Huang. 2020. Cross-Lingual Natural Language Generation via Pre-Training. ArXiv abs\/1909.10481 (2020)."},{"key":"e_1_3_2_1_4_1","unstructured":"Yiming Cui Wanxiang Che Ting Liu Bing Qin Shijin Wang and Guoping Hu. 2019. Cross-Lingual Machine Reading Comprehension. In EMNLP-IJCNLP. 1586--1595.  Yiming Cui Wanxiang Che Ting Liu Bing Qin Shijin Wang and Guoping Hu. 2019. Cross-Lingual Machine Reading Comprehension. In EMNLP-IJCNLP. 1586--1595."},{"key":"e_1_3_2_1_5_1","volume-title":"FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding. ArXiv abs\/2009.05166","author":"Fang Y.","year":"2020","unstructured":"Y. Fang , S. Wang , Z. Gan , S. Sun , and JJ. Liu . 2020 . FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding. ArXiv abs\/2009.05166 (2020). Y. Fang, S. Wang, Z. Gan, S. Sun, and JJ. Liu. 2020. FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding. ArXiv abs\/2009.05166 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Roman Grundkiewicz Marcin Junczys-Dowmunt and Kenneth Heafield. 2019. Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data. In BEA@ACL.  Roman Grundkiewicz Marcin Junczys-Dowmunt and Kenneth Heafield. 2019. Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data. In BEA@ACL.","DOI":"10.18653\/v1\/W19-4427"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1119"},{"key":"e_1_3_2_1_8_1","volume-title":"Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction. ArXiv abs\/2005.00987","author":"Kaneko Masahiro","year":"2020","unstructured":"Masahiro Kaneko , Masato Mita , Shun Kiyono , Jun Suzuki , and Kentaro Inui . 2020. Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction. ArXiv abs\/2005.00987 ( 2020 ). Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2020. Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction. ArXiv abs\/2005.00987 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"MLQA: Evaluating cross-lingual extractive question answering. arXiv preprint arXiv:1910.07475","author":"Lewis Patrick","year":"2019","unstructured":"Patrick Lewis , Barlas O?uz, Ruty Rinott , Sebastian Riedel , and Holger Schwenk . 2019 . MLQA: Evaluating cross-lingual extractive question answering. arXiv preprint arXiv:1910.07475 (2019). Patrick Lewis, Barlas O?uz, Ruty Rinott, Sebastian Riedel, and Holger Schwenk. 2019. MLQA: Evaluating cross-lingual extractive question answering. arXiv preprint arXiv:1910.07475 (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"CalibreNet: Calibration Networks for Multilingual Sequence Labeling. ArXiv abs\/2011.05723","author":"Liang Shining","year":"2020","unstructured":"Shining Liang , Linjun Shou , Jian Pei , Ming Gong , WanLi Zuo , and Daxin Jiang . 2020. CalibreNet: Calibration Networks for Multilingual Sequence Labeling. ArXiv abs\/2011.05723 ( 2020 ). Shining Liang, Linjun Shou, Jian Pei, Ming Gong, WanLi Zuo, and Daxin Jiang. 2020. CalibreNet: Calibration Networks for Multilingual Sequence Labeling. ArXiv abs\/2011.05723 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation. ArXiv abs\/2010.14271","author":"Liu Junhao","year":"2020","unstructured":"Junhao Liu , Linjun Shou , Jian Pei , Ming Gong , Min Yang , and Daxin Jiang . 2020. Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation. ArXiv abs\/2010.14271 ( 2020 ). Junhao Liu, Linjun Shou, Jian Pei, Ming Gong, Min Yang, and Daxin Jiang. 2020. Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation. ArXiv abs\/2010.14271 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Yinhan Liu and Jiatao Gu et al. 2020. Multilingual Denoising Pre-training for Neural Machine Translation. ArXiv abs\/2001.08210 (2020).  Yinhan Liu and Jiatao Gu et al. 2020. Multilingual Denoising Pre-training for Neural Machine Translation. ArXiv abs\/2001.08210 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Zhaojiang Lin, Peng Xu, and Pascale Fung.","author":"Liu Zihan","year":"2020","unstructured":"Zihan Liu , Genta Indra Winata , Zhaojiang Lin, Peng Xu, and Pascale Fung. 2020 . Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Taskoriented Dialogue Systems. ArXiv abs\/1911.09273 (2020). Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, and Pascale Fung. 2020. Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Taskoriented Dialogue Systems. ArXiv abs\/1911.09273 (2020)."},{"key":"e_1_3_2_1_14_1","unstructured":"Ryan McDonald Slav Petrov and Keith B Hall. 2011. Multi-source transfer of delexicalized dependency parsers. (2011).  Ryan McDonald Slav Petrov and Keith B Hall. 2011. Multi-source transfer of delexicalized dependency parsers. (2011)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"L. Qin Minheng Ni Y. Zhang and W. Che. 2020. CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP. In IJCAI.  L. Qin Minheng Ni Y. Zhang and W. Che. 2020. CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP. In IJCAI.","DOI":"10.24963\/ijcai.2020\/533"},{"key":"e_1_3_2_1_16_1","volume-title":"Cross-lingual dependency parsing with late decoding for truly low-resource languages. arXiv preprint arXiv:1701.01623","author":"Schlichtkrull Michael Sejr","year":"2017","unstructured":"Michael Sejr Schlichtkrull and Anders S\u00f8gaard . 2017. Cross-lingual dependency parsing with late decoding for truly low-resource languages. arXiv preprint arXiv:1701.01623 ( 2017 ). Michael Sejr Schlichtkrull and Anders S\u00f8gaard. 2017. Cross-lingual dependency parsing with late decoding for truly low-resource languages. arXiv preprint arXiv:1701.01623 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3013558.3013565"},{"key":"e_1_3_2_1_18_1","volume-title":"Crosslingual BERT transformation for zero-shot dependency parsing. arXiv preprint arXiv:1909.06775","author":"Wang Yuxuan","year":"2019","unstructured":"Yuxuan Wang , Wanxiang Che , Jiang Guo , Yijia Liu , and Ting Liu . 2019. Crosslingual BERT transformation for zero-shot dependency parsing. arXiv preprint arXiv:1909.06775 ( 2019 ). Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu, and Ting Liu. 2019. Crosslingual BERT transformation for zero-shot dependency parsing. arXiv preprint arXiv:1909.06775 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Q. Wu Zijia Lin B\u00f6rje F. Karlsson B. Huang and Jianguang Lou. 2020. UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data. In IJCAI.  Q. Wu Zijia Lin B\u00f6rje F. Karlsson B. Huang and Jianguang Lou. 2020. UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data. In IJCAI.","DOI":"10.24963\/ijcai.2020\/543"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Q. Wu Zijia Lin B\u00f6rje F. Karlsson Jian-Guang Lou and B. Huang. 2020. Single- \/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language. ArXiv abs\/2004.12440 (2020).  Q. Wu Zijia Lin B\u00f6rje F. Karlsson Jian-Guang Lou and B. Huang. 2020. Single- \/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language. ArXiv abs\/2004.12440 (2020).","DOI":"10.18653\/v1\/2020.acl-main.581"},{"key":"e_1_3_2_1_21_1","unstructured":"Linting Xue and Noah Constant et al. 2020. mT5: A massively multilingual pre-trained text-to-text transformer. ArXiv abs\/2010.11934 (2020).  Linting Xue and Noah Constant et al. 2020. mT5: A massively multilingual pre-trained text-to-text transformer. ArXiv abs\/2010.11934 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Ikumi Yamashita Satoru Katsumata Masahiro Kaneko Aizhan Imankulova and Mamoru Komachi. 2020. Cross-lingual Transfer Learning for Grammatical Error Correction. In COLING.  Ikumi Yamashita Satoru Katsumata Masahiro Kaneko Aizhan Imankulova and Mamoru Komachi. 2020. Cross-lingual Transfer Learning for Grammatical Error Correction. In COLING.","DOI":"10.18653\/v1\/2020.coling-main.415"},{"key":"e_1_3_2_1_23_1","volume-title":"Cohen","author":"Yang Z.","year":"2016","unstructured":"Z. Yang , R. Salakhutdinov , and William W . Cohen . 2016 . Multi-Task Cross-Lingual Sequence Tagging from Scratch. ArXiv abs\/1603.06270 (2016). Z. Yang, R. Salakhutdinov, and William W. Cohen. 2016. Multi-Task Cross-Lingual Sequence Tagging from Scratch. ArXiv abs\/1603.06270 (2016)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Fei Yuan Linjun Shou X. Bai Ming Gong Yaobo Liang N. Duan Y. Fu and Daxin Jiang. 2020. Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension. In ACL.  Fei Yuan Linjun Shou X. Bai Ming Gong Yaobo Liang N. Duan Y. Fu and Daxin Jiang. 2020. Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.87"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Wei Zhao Liang Wang Kewei Shen Ruoyu Jia and Jingming Liu. 2019. Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data. In NAACL-HLT.  Wei Zhao Liang Wang Kewei Shen Ruoyu Jia and Jingming Liu. 2019. Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data. In NAACL-HLT.","DOI":"10.18653\/v1\/N19-1014"},{"key":"e_1_3_2_1_26_1","unstructured":"Wangchunshu Zhou Tao Ge C. Mu Ke Xu Furu Wei and M. Zhou. 2020. Improving Grammatical Error Correction with Machine Translation Pairs. ArXiv abs\/1911.02825 (2020).  Wangchunshu Zhou Tao Ge C. Mu Ke Xu Furu Wei and M. Zhou. 2020. Improving Grammatical Error Correction with Machine Translation Pairs. ArXiv abs\/1911.02825 (2020)."}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Virtual Event Singapore","acronym":"KDD '21"},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3470791","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3470791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:31Z","timestamp":1750191511000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3470791"}},"subtitle":["Applications, Challenges and Approaches"],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":26,"alternative-id":["10.1145\/3447548.3470791","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3470791","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}