{"list":"other","total":77,"rows":[{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2010.02353","title":"Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages","created":"2020-10-05","cited_by_count":159},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149},{"id":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139},{"id":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2012.15562","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","created":"2020-12-31","cited_by_count":113},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89},{"id":"2004.14327","title":"UDapter: Language Adaptation for Truly Universal Dependency Parsing","created":"2020-04-29","cited_by_count":77},{"id":"2012.15674","title":"ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora","created":"2020-12-31","cited_by_count":63},{"id":"1906.03785","title":"Generalized Data Augmentation for Low-Resource Translation","created":"2019-06-10","cited_by_count":53},{"id":"2009.09359","title":"Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation","created":"2020-09-20","cited_by_count":53},{"id":"2011.02690","title":"Entity Linking in 100 Languages","created":"2020-11-05","cited_by_count":52},{"id":"2005.04816","title":"Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation","created":"2020-05-11","cited_by_count":51},{"id":"2010.04480","title":"MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset","created":"2020-10-09","cited_by_count":47},{"id":"1912.02481","title":"Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor\\`ub\\'a and Twi","created":"2019-12-05","cited_by_count":33},{"id":"2010.12174","title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","created":"2020-10-23","cited_by_count":31},{"id":"2305.10951","title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","created":"2023-05-18","cited_by_count":31},{"id":"2210.14712","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","created":"2022-10-26","cited_by_count":28},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25},{"id":"2103.00751","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","created":"2021-03-01","cited_by_count":24},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24},{"id":"2305.12708","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer","created":"2023-05-22","cited_by_count":24},{"id":"2001.11453","title":"Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages","created":"2020-01-30","cited_by_count":22},{"id":"2004.14524","title":"Simulated Multiple Reference Training Improves Low-Resource Machine Translation","created":"2020-04-30","cited_by_count":22},{"id":"2104.07908","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","created":"2021-04-16","cited_by_count":21},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21},{"id":"2005.01866","title":"Soft Gazetteers for Low-Resource Named Entity Recognition","created":"2020-05-04","cited_by_count":20},{"id":"2203.03191","title":"Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features","created":"2022-03-07","cited_by_count":20},{"id":"2109.04080","title":"Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining","created":"2021-09-09","cited_by_count":19},{"id":"2210.12265","title":"On the Calibration of Massively Multilingual Language Models","created":"2022-10-21","cited_by_count":19},{"id":"2105.15071","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","created":"2021-05-31","cited_by_count":17},{"id":"2101.06779","title":"Few Shot Dialogue State Tracking using Meta-learning","created":"2021-01-17","cited_by_count":16},{"id":"2109.09161","title":"Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition","created":"2021-09-19","cited_by_count":16},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15},{"id":"2004.13240","title":"UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP","created":"2020-04-28","cited_by_count":14},{"id":"2102.04889","title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language","created":"2021-02-09","cited_by_count":14},{"id":"1911.03070","title":"Interactive Refinement of Cross-Lingual Word Embeddings","created":"2019-11-08","cited_by_count":13},{"id":"2004.03846","title":"Structure-Level Knowledge Distillation For Multilingual Sequence Labeling","created":"2020-04-08","cited_by_count":13},{"id":"2112.12650","title":"Distilling the Knowledge of Romanian BERTs Using Multiple Teachers","created":"2021-12-23","cited_by_count":13},{"id":"2205.02694","title":"Quantifying Language Variation Acoustically with Few Resources","created":"2022-05-05","cited_by_count":12},{"id":"2310.15799","title":"DALE: Generative Data Augmentation for Low-Resource Legal NLP","created":"2023-10-24","cited_by_count":12},{"id":"1906.03492","title":"Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations","created":"2019-06-08","cited_by_count":11},{"id":"2011.00767","title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","created":"2020-11-02","cited_by_count":11},{"id":"2104.12567","title":"Evaluating the Values of Sources in Transfer Learning","created":"2021-04-26","cited_by_count":11},{"id":"1705.00424","title":"Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary","created":"2017-05-01","cited_by_count":10},{"id":"2003.01343","title":"Improving Candidate Generation for Low-resource Cross-lingual Entity Linking","created":"2020-03-03","cited_by_count":10},{"id":"2010.02804","title":"Tackling the Low-resource Challenge for Canonical Segmentation","created":"2020-10-06","cited_by_count":10},{"id":"2104.03543","title":"Extended Parallel Corpus for Amharic-English Machine Translation","created":"2021-04-08","cited_by_count":10},{"id":"2104.04736","title":"Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing","created":"2021-04-10","cited_by_count":10},{"id":"2405.16656","title":"\"I Searched for a Religious Song in Amharic and Got Sexual Content Instead\": Investigating Online Harm in Low-Resourced Languages on YouTube","created":"2024-05-26","cited_by_count":9},{"id":"2005.00970","title":"Unsupervised Morphological Paradigm Completion","created":"2020-05-03","cited_by_count":8},{"id":"2105.14115","title":"Towards More Equitable Question Answering Systems: How Much More Data Do You Need?","created":"2021-05-28","cited_by_count":8},{"id":"2202.06650","title":"Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?","created":"2022-02-14","cited_by_count":7},{"id":"2204.05210","title":"Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling","created":"2022-04-11","cited_by_count":7},{"id":"2208.12888","title":"Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation","created":"2022-08-26","cited_by_count":7},{"id":"2003.03135","title":"Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages","created":"2020-03-06","cited_by_count":6},{"id":"2010.12627","title":"Anchor-based Bilingual Word Embeddings for Low-Resource Languages","created":"2020-10-23","cited_by_count":6},{"id":"2209.13515","title":"Assessing Digital Language Support on a Global Scale","created":"2022-09-27","cited_by_count":6},{"id":"2210.14378","title":"Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport","created":"2022-10-25","cited_by_count":6},{"id":"2210.14465","title":"Eeny, meeny, miny, moe. How to choose data for morphological inflection","created":"2022-10-26","cited_by_count":6},{"id":"2212.10018","title":"DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization","created":"2022-12-20","cited_by_count":6},{"id":"2203.08555","title":"Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning","created":"2022-03-16","cited_by_count":5},{"id":"2004.10270","title":"Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi","created":"2020-04-21","cited_by_count":4},{"id":"2205.12475","title":"Low Resource Style Transfer via Domain Adaptive Meta Learning","created":"2022-05-25","cited_by_count":4},{"id":"2302.07912","title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","created":"2023-02-15","cited_by_count":4},{"id":"2306.07610","title":"Soft Language Clustering for Multilingual Model Pre-training","created":"2023-06-13","cited_by_count":4},{"id":"2109.04443","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","created":"2021-09-09","cited_by_count":3},{"id":"2211.01200","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","created":"2022-11-02","cited_by_count":3},{"id":"2306.06384","title":"Adversarial Training For Low-Resource Disfluency Correction","created":"2023-06-10","cited_by_count":3},{"id":"1701.01623","title":"Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages","created":"2017-01-06","cited_by_count":2},{"id":"2004.07642","title":"Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers","created":"2020-04-16","cited_by_count":2},{"id":"2305.16106","title":"Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System","created":"2023-05-25","cited_by_count":1}],"next_cursor":null}