{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"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":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"1904.03670","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","created":"2019-04-07","cited_by_count":193},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148},{"id":"2012.06185","title":"Exploring wav2vec 2.0 on speaker verification and language identification","created":"2020-12-11","cited_by_count":95},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74},{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54},{"id":"2209.15329","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","created":"2022-09-30","cited_by_count":49},{"id":"2011.00406","title":"Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies","created":"2020-11-01","cited_by_count":47},{"id":"2204.02492","title":"Towards End-to-end Unsupervised Speech Recognition","created":"2022-04-05","cited_by_count":45},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42},{"id":"2102.06283","title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","created":"2021-02-11","cited_by_count":27},{"id":"2210.08634","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","created":"2022-10-16","cited_by_count":26},{"id":"1909.07930","title":"Ludwig: a type-based declarative deep learning toolbox","created":"2019-09-17","cited_by_count":24},{"id":"2011.09044","title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","created":"2020-11-18","cited_by_count":23},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22},{"id":"2010.12283","title":"ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding","created":"2020-10-23","cited_by_count":19},{"id":"1910.12729","title":"Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning","created":"2019-10-28","cited_by_count":16},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15},{"id":"1910.00912","title":"Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU","created":"2019-10-02","cited_by_count":13},{"id":"2102.06750","title":"Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding","created":"2021-02-12","cited_by_count":9},{"id":"2104.05752","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","created":"2021-04-07","cited_by_count":8},{"id":"2204.01893","title":"Deliberation Model for On-Device Spoken Language Understanding","created":"2022-04-04","cited_by_count":8},{"id":"2210.07189","title":"On Compressing Sequences for Self-Supervised Speech Models","created":"2022-10-13","cited_by_count":8},{"id":"2211.00586","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","created":"2022-11-01","cited_by_count":4},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3}],"next_cursor":null}