{"list":"other","total":69,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"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":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"1907.05791","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","created":"2019-07-10","cited_by_count":223},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"2103.10730","title":"MuRIL: Multilingual Representations for Indian Languages","created":"2021-03-19","cited_by_count":179},{"id":"2106.12672","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","created":"2021-06-23","cited_by_count":160},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116},{"id":"2009.05387","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","created":"2020-09-11","cited_by_count":109},{"id":"1802.08395","title":"Towards end-to-end spoken language understanding","created":"2018-02-23","cited_by_count":92},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"1904.00784","title":"A Survey of Code-switched Speech and Language Processing","created":"2019-03-25","cited_by_count":75},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64},{"id":"1708.09803","title":"Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation","created":"2017-08-31","cited_by_count":58},{"id":"2011.00677","title":"IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP","created":"2020-11-02","cited_by_count":58},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56},{"id":"1909.08582","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","created":"2019-09-18","cited_by_count":55},{"id":"1910.13923","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer","created":"2019-10-30","cited_by_count":47},{"id":"2109.06598","title":"Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP","created":"2021-09-14","cited_by_count":47},{"id":"2103.09666","title":"Multimodal End-to-End Sparse Model for Emotion Recognition","created":"2021-03-17","cited_by_count":40},{"id":"2003.07568","title":"XPersona: Evaluating Multilingual Personalized Chatbot","created":"2020-03-17","cited_by_count":36},{"id":"2003.01901","title":"Learning Fast Adaptation on Cross-Accented Speech Recognition","created":"2020-03-04","cited_by_count":28},{"id":"1512.00103","title":"Multilingual Language Processing From Bytes","created":"2015-12-01","cited_by_count":26},{"id":"2109.04607","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","created":"2021-09-10","cited_by_count":25},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23},{"id":"2110.06744","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","created":"2021-10-13","cited_by_count":20},{"id":"2106.03958","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","created":"2021-06-07","cited_by_count":19},{"id":"2009.05720","title":"Improving Bi-LSTM Performance for Indonesian Sentiment Analysis Using Paragraph Vector","created":"2020-09-12","cited_by_count":18},{"id":"2009.09629","title":"Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition","created":"2020-09-21","cited_by_count":17},{"id":"2009.09309","title":"Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation","created":"2020-09-19","cited_by_count":16},{"id":"1805.12070","title":"Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning","created":"2018-05-30","cited_by_count":15},{"id":"1810.05334","title":"IndoSum: A New Benchmark Dataset for Indonesian Text Summarization","created":"2018-10-12","cited_by_count":14},{"id":"1908.09982","title":"On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression","created":"2019-08-27","cited_by_count":14},{"id":"2011.00679","title":"Liputan6: A Large-scale Indonesian Dataset for Text Summarization","created":"2020-11-02","cited_by_count":14},{"id":"2201.10066","title":"Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources","created":"2022-01-25","cited_by_count":11},{"id":"2011.02128","title":"Cross-Lingual Machine Speech Chain for Javanese, Sundanese, Balinese, and Bataks Speech Recognition and Synthesis","created":"2020-11-04","cited_by_count":8},{"id":"2101.11216","title":"PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation","created":"2021-01-27","cited_by_count":6},{"id":"1505.03085","title":"Indonesian Social Media Sentiment Analysis With Sarcasm Detection","created":"2015-05-12","cited_by_count":5},{"id":"2009.05687","title":"Investigating Bi-LSTM and CRF with POS Tag Embedding for Indonesian Named Entity Tagger","created":"2020-09-11","cited_by_count":5},{"id":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5},{"id":"2011.03286","title":"Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation","created":"2020-11-06","cited_by_count":4},{"id":"2104.06268","title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","created":"2021-04-13","cited_by_count":4},{"id":"1809.03391","title":"Toward a Standardized and More Accurate Indonesian Part-of-Speech Tagging","created":"2018-09-10","cited_by_count":3},{"id":"2009.07119","title":"Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features","created":"2020-09-15","cited_by_count":3},{"id":"2010.02396","title":"Plan Optimization to Bilingual Dictionary Induction for Low-Resource Language Families","created":"2020-10-05","cited_by_count":3},{"id":"1810.11612","title":"Handling Imbalanced Dataset in Multi-label Text Categorization using Bagging and Adaptive Boosting","created":"2018-10-27","cited_by_count":1},{"id":"2010.02395","title":"A Generalized Constraint Approach to Bilingual Dictionary Induction for Low-Resource Language Families","created":"2020-10-05","cited_by_count":1}],"next_cursor":null}