{"list":"other","total":190,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"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":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"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":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"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":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"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":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2012.15613","title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","created":"2020-12-31","cited_by_count":318},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"1904.09077","title":"Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT","created":"2019-04-19","cited_by_count":301},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"1507.04808","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","created":"2015-07-17","cited_by_count":207},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"1703.09902","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","created":"2017-03-29","cited_by_count":206},{"id":"2007.12720","title":"MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines","created":"2020-07-10","cited_by_count":204},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"1902.10909","title":"BERT for Joint Intent Classification and Slot Filling","created":"2019-02-28","cited_by_count":196},{"id":"1309.4168","title":"Exploiting Similarities among Languages for Machine Translation","created":"2013-09-17","cited_by_count":191},{"id":"1604.02201","title":"Transfer Learning for Low-Resource Neural Machine Translation","created":"2016-04-08","cited_by_count":188},{"id":"1901.08149","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","created":"2019-01-23","cited_by_count":188},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186},{"id":"1902.04094","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","created":"2019-02-11","cited_by_count":185},{"id":"2004.06871","title":"TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue","created":"2020-04-15","cited_by_count":185},{"id":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"1903.05566","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","created":"2019-03-13","cited_by_count":166},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"1805.06297","title":"A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings","created":"2018-05-16","cited_by_count":146},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"1606.03777","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","created":"2016-06-12","cited_by_count":143},{"id":"1706.04902","title":"A Survey Of Cross-lingual Word Embedding Models","created":"2017-06-15","cited_by_count":143},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"1810.13327","title":"Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog","created":"2018-10-31","cited_by_count":125},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1809.05972","title":"Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization","created":"2018-09-16","cited_by_count":116},{"id":"2002.03518","title":"Multilingual Alignment of Contextual Word Representations","created":"2020-02-10","cited_by_count":114},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"2012.15562","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","created":"2020-12-31","cited_by_count":113},{"id":"1907.05774","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","created":"2019-07-12","cited_by_count":110},{"id":"2007.03001","title":"Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters","created":"2020-07-06","cited_by_count":110},{"id":"1612.01627","title":"Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots","created":"2016-12-06","cited_by_count":103},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"1506.06714","title":"A Neural Network Approach to Context-Sensitive Generation of Conversational Responses","created":"2015-06-22","cited_by_count":98},{"id":"1708.07149","title":"Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses","created":"2017-08-23","cited_by_count":98},{"id":"1702.03859","title":"Offline bilingual word vectors, orthogonal transformations and the inverted softmax","created":"2017-02-13","cited_by_count":96},{"id":"2004.04721","title":"Translation Artifacts in Cross-lingual Transfer Learning","created":"2020-04-09","cited_by_count":96},{"id":"2010.02194","title":"Self-training Improves Pre-training for Natural Language Understanding","created":"2020-10-05","cited_by_count":96},{"id":"1911.03688","title":"ConveRT: Efficient and Accurate Conversational Representations from Transformers","created":"2019-11-09","cited_by_count":95},{"id":"2002.12328","title":"Few-shot Natural Language Generation for Task-Oriented Dialog","created":"2020-02-27","cited_by_count":89},{"id":"2009.13570","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","created":"2020-09-28","cited_by_count":89},{"id":"2004.14353","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","created":"2020-04-29","cited_by_count":83},{"id":"1808.04776","title":"Retrieve and Refine: Improved Sequence Generation Models For Dialogue","created":"2018-08-14","cited_by_count":82},{"id":"2006.06402","title":"CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP","created":"2020-06-11","cited_by_count":79},{"id":"2004.14327","title":"UDapter: Language Adaptation for Truly Universal Dependency Parsing","created":"2020-04-29","cited_by_count":77},{"id":"1911.03906","title":"Efficient Dialogue State Tracking by Selectively Overwriting Memory","created":"2019-11-10","cited_by_count":76},{"id":"2010.11683","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","created":"2020-10-22","cited_by_count":76},{"id":"1804.07745","title":"Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion","created":"2018-04-20","cited_by_count":70},{"id":"1804.08217","title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","created":"2018-04-23","cited_by_count":70},{"id":"1902.09492","title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing","created":"2019-02-25","cited_by_count":70},{"id":"1907.04448","title":"Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning","created":"2019-07-09","cited_by_count":66},{"id":"2002.11893","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","created":"2020-02-27","cited_by_count":66}],"next_cursor":"100"}