Proceedings of the 1st Workshop on Multilingual Representation Learning

Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor 2021-11 Association for Computational Linguistics Punta Cana, Dominican Republic text conference publication mrl-2021-multilingual https://aclanthology.org/2021.mrl-1.0/ Language Models are Few-shot Multilingual Learners Genta Indra Winata author Andrea Madotto author Zhaojiang Lin author Rosanne Liu author Jason Yosinski author Pascale Fung author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication winata-etal-2021-language 10.18653/v1/2021.mrl-1.1 https://aclanthology.org/2021.mrl-1.1/ 2021-11 1 15 Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora Takashi Wada author Tomoharu Iwata author Yuji Matsumoto author Timothy Baldwin author Jey Han Lau author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication wada-etal-2021-learning 10.18653/v1/2021.mrl-1.2 https://aclanthology.org/2021.mrl-1.2/ 2021-11 16 31 Clustering Monolingual Vocabularies to Improve Cross-Lingual Generalization Riccardo Bassani author Anders Søgaard author Tejaswini Deoskar author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication bassani-etal-2021-clustering 10.18653/v1/2021.mrl-1.3 https://aclanthology.org/2021.mrl-1.3/ 2021-11 32 40 Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings Lisa Woller author Viktor Hangya author Alexander Fraser author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication woller-etal-2021-neglect 10.18653/v1/2021.mrl-1.4 https://aclanthology.org/2021.mrl-1.4/ 2021-11 41 50 Specializing Multilingual Language Models: An Empirical Study Ethan C Chau author Noah A Smith author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication chau-smith-2021-specializing 10.18653/v1/2021.mrl-1.5 https://aclanthology.org/2021.mrl-1.5/ 2021-11 51 61 Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport Duy Phung author Hieu Minh Tran author Minh Van Nguyen author Thien Huu Nguyen author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication phung-etal-2021-learning 10.18653/v1/2021.mrl-1.6 https://aclanthology.org/2021.mrl-1.6/ 2021-11 62 73 Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training Vikram Gupta author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication gupta-2021-multilingual 10.18653/v1/2021.mrl-1.7 https://aclanthology.org/2021.mrl-1.7/ 2021-11 74 85 Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance Karthikeyan K author Aalok Sathe author Somak Aditya author Monojit Choudhury author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication k-etal-2021-analyzing 10.18653/v1/2021.mrl-1.8 https://aclanthology.org/2021.mrl-1.8/ 2021-11 86 95 Identifying the Importance of Content Overlap for Better Cross-lingual Embedding Mappings Réka Cserháti author Gábor Berend author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication cserhati-berend-2021-identifying 10.18653/v1/2021.mrl-1.9 https://aclanthology.org/2021.mrl-1.9/ 2021-11 96 106 On the Cross-lingual Transferability of Contextualized Sense Embeddings Kiamehr Rezaee author Daniel Loureiro author Jose Camacho-Collados author Mohammad Taher Pilehvar author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication rezaee-etal-2021-cross 10.18653/v1/2021.mrl-1.10 https://aclanthology.org/2021.mrl-1.10/ 2021-11 107 115 Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages Kelechi Ogueji author Yuxin Zhu author Jimmy Lin author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication ogueji-etal-2021-small 10.18653/v1/2021.mrl-1.11 https://aclanthology.org/2021.mrl-1.11/ 2021-11 116 126 Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval Xinyu Zhang author Xueguang Ma author Peng Shi author Jimmy Lin author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication zhang-etal-2021-mr 10.18653/v1/2021.mrl-1.12 https://aclanthology.org/2021.mrl-1.12/ 2021-11 127 137 VisualSem: a high-quality knowledge graph for vision and language Houda Alberts author Ningyuan Huang author Yash Deshpande author Yibo Liu author Kyunghyun Cho author Clara Vania author Iacer Calixto author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication alberts-etal-2021-visualsem 10.18653/v1/2021.mrl-1.13 https://aclanthology.org/2021.mrl-1.13/ 2021-11 138 152 Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages Rajaswa Patil author Jasleen Dhillon author Siddhant Mahurkar author Saumitra Kulkarni author Manav Malhotra author Veeky Baths author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication patil-etal-2021-vyakarana 10.18653/v1/2021.mrl-1.14 https://aclanthology.org/2021.mrl-1.14/ 2021-11 153 165 Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs Monisha Jegadeesan author Sachin Kumar author John Wieting author Yulia Tsvetkov author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication jegadeesan-etal-2021-improving 10.18653/v1/2021.mrl-1.15 https://aclanthology.org/2021.mrl-1.15/ 2021-11 166 175 The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding Archiki Prasad author Mohammad Ali Rehan author Shreya Pathak author Preethi Jyothi author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication prasad-etal-2021-effectiveness 10.18653/v1/2021.mrl-1.16 https://aclanthology.org/2021.mrl-1.16/ 2021-11 176 190 Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations Ekaterina Taktasheva author Vladislav Mikhailov author Ekaterina Artemova author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication taktasheva-etal-2021-shaking 10.18653/v1/2021.mrl-1.17 https://aclanthology.org/2021.mrl-1.17/ 2021-11 191 210 Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling Jitin Krishnan author Antonios Anastasopoulos author Hemant Purohit author Huzefa Rangwala author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication krishnan-etal-2021-multilingual 10.18653/v1/2021.mrl-1.18 https://aclanthology.org/2021.mrl-1.18/ 2021-11 211 223 Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition Jongin Kim author Nayoung Choi author Seunghyun Lim author Jungwhan Kim author Soojin Chung author Hyunsoo Woo author Min Song author Jinho D Choi author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication kim-etal-2021-analysis 10.18653/v1/2021.mrl-1.19 https://aclanthology.org/2021.mrl-1.19/ 2021-11 224 237 Regularising Fisher Information Improves Cross-lingual Generalisation Asa Cooper Stickland author Iain Murray author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication cooper-stickland-murray-2021-regularising 10.18653/v1/2021.mrl-1.20 https://aclanthology.org/2021.mrl-1.20/ 2021-11 238 241 DMix: Distance Constrained Interpolative Mixup Ramit Sawhney author Megh Thakkar author Shrey Pandit author Debdoot Mukherjee author Lucie Flek author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication sawhney-etal-2021-dmix 10.18653/v1/2021.mrl-1.21 https://aclanthology.org/2021.mrl-1.21/ 2021-11 242 244 Sequence Mixup for Zero-Shot Cross-Lingual Part-Of-Speech Tagging Megh Thakkar author Vishwa Shah author Ramit Sawhney author Debdoot Mukherjee author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication thakkar-etal-2021-sequence 10.18653/v1/2021.mrl-1.22 https://aclanthology.org/2021.mrl-1.22/ 2021-11 245 247 Well-Defined Morphology is Sentence-Level Morphology Omer Goldman author Reut Tsarfaty author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication goldman-tsarfaty-2021-well 10.18653/v1/2021.mrl-1.23 https://aclanthology.org/2021.mrl-1.23/ 2021-11 248 250 Cross-Lingual Training of Dense Retrievers for Document Retrieval Peng Shi author Rui Zhang author He Bai author Jimmy Lin author 2021-11 text Proceedings of the 1st Workshop on Multilingual Representation Learning Duygu Ataman editor Alexandra Birch editor Alexis Conneau editor Orhan Firat editor Sebastian Ruder editor Gozde Gul Sahin editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication shi-etal-2021-cross 10.18653/v1/2021.mrl-1.24 https://aclanthology.org/2021.mrl-1.24/ 2021-11 251 253