{"list":"other","total":137,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1710.04087","title":"Word Translation Without Parallel Data","created":"2017-10-11","cited_by_count":487},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"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":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"2005.04322","title":"LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation","created":"2020-05-09","cited_by_count":93},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"2004.05160","title":"On the Language Neutrality of Pre-trained Multilingual Representations","created":"2020-04-09","cited_by_count":85},{"id":"1904.00784","title":"A Survey of Code-switched Speech and Language Processing","created":"2019-03-25","cited_by_count":75},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"id":"2006.00206","title":"Corpus Creation for Sentiment Analysis in Code-Mixed Tamil-English Text","created":"2020-05-30","cited_by_count":67},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66},{"id":"2008.04277","title":"SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets","created":"2020-08-10","cited_by_count":62},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","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":"2104.00235","title":"Multilingual and code-switching ASR challenges for low resource Indian languages","created":"2021-04-01","cited_by_count":53},{"id":"2006.00210","title":"A Sentiment Analysis Dataset for Code-Mixed Malayalam-English","created":"2020-05-30","cited_by_count":50},{"id":"2112.06223","title":"ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation","created":"2021-12-12","cited_by_count":44},{"id":"2009.08088","title":"Code-switching pre-training for neural machine translation","created":"2020-09-17","cited_by_count":43},{"id":"2105.14779","title":"Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR","created":"2021-05-31","cited_by_count":41},{"id":"1803.09402","title":"Aggression-annotated Corpus of Hindi-English Code-mixed Data","created":"2018-03-26","cited_by_count":40},{"id":"2004.09447","title":"PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translation","created":"2020-04-20","cited_by_count":38},{"id":"2204.08398","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","created":"2022-04-18","cited_by_count":34},{"id":"1909.13016","title":"Overview for the Second Shared Task on Language Identification in Code-Switched Data","created":"2019-09-28","cited_by_count":33},{"id":"1611.00472","title":"Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text","created":"2016-11-02","cited_by_count":31},{"id":"1811.00241","title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition","created":"2018-11-01","cited_by_count":30},{"id":"2004.05051","title":"A New Dataset for Natural Language Inference from Code-mixed Conversations","created":"2020-04-10","cited_by_count":29},{"id":"2107.06483","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","created":"2021-07-14","cited_by_count":29},{"id":"2006.10414","title":"Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition","created":"2020-06-18","cited_by_count":28},{"id":"2008.00768","title":"One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech","created":"2020-08-03","cited_by_count":28},{"id":"2107.03760","title":"HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text","created":"2021-07-08","cited_by_count":28},{"id":"1811.02356","title":"Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation","created":"2018-11-06","cited_by_count":26},{"id":"1906.04138","title":"Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task","created":"2019-06-10","cited_by_count":24},{"id":"2004.14228","title":"Meta-Transfer Learning for Code-Switched Speech Recognition","created":"2020-04-29","cited_by_count":22},{"id":"2206.02093","title":"LAE: Language-Aware Encoder for Monolingual and Multilingual ASR","created":"2022-06-05","cited_by_count":22},{"id":"2105.04846","title":"Can You Traducir This? Machine Translation for Code-Switched Input","created":"2021-05-11","cited_by_count":21},{"id":"1610.02213","title":"Challenges of Computational Processing of Code-Switching","created":"2016-10-07","cited_by_count":20},{"id":"2206.14580","title":"Language-specific Characteristic Assistance for Code-switching Speech Recognition","created":"2022-06-29","cited_by_count":20},{"id":"2208.14536","title":"MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition","created":"2022-08-30","cited_by_count":19},{"id":"1909.05158","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","created":"2019-09-11","cited_by_count":18},{"id":"2106.10123","title":"Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text","created":"2021-06-18","cited_by_count":18},{"id":"2107.01573","title":"Arabic Code-Switching Speech Recognition using Monolingual Data","created":"2021-07-04","cited_by_count":17},{"id":"2206.13135","title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","created":"2022-06-27","cited_by_count":17},{"id":"1806.05997","title":"A Dataset for Building Code-Mixed Goal Oriented Conversation Systems","created":"2018-06-15","cited_by_count":16},{"id":"1809.01962","title":"Code-switched Language Models Using Dual RNNs and Same-Source Pretraining","created":"2018-09-06","cited_by_count":16},{"id":"2105.08807","title":"Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing","created":"2021-05-18","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":"2010.05549","title":"Improving Low Resource Code-switched ASR using Augmented Code-switched TTS","created":"2020-10-12","cited_by_count":15},{"id":"1810.11895","title":"Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training","created":"2018-10-28","cited_by_count":14},{"id":"2109.04653","title":"Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation","created":"2021-09-10","cited_by_count":13},{"id":"1807.10945","title":"Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech","created":"2018-07-28","cited_by_count":12},{"id":"1807.10949","title":"Building a Unified Code-Switching ASR System for South African Languages","created":"2018-07-28","cited_by_count":12},{"id":"1904.01989","title":"Subword-Level Language Identification for Intra-Word Code-Switching","created":"2019-04-03","cited_by_count":12},{"id":"2005.02295","title":"Code-switching patterns can be an effective route to improve performance of downstream NLP applications: A case study of humour, sarcasm and hate speech detection","created":"2020-05-05","cited_by_count":12},{"id":"2010.08136","title":"Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion","created":"2020-10-16","cited_by_count":12},{"id":"1806.05513","title":"Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System","created":"2018-06-14","cited_by_count":11},{"id":"2010.12730","title":"Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality","created":"2020-10-24","cited_by_count":11},{"id":"2006.00782","title":"Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition","created":"2020-06-01","cited_by_count":10},{"id":"2105.13573","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","created":"2021-05-28","cited_by_count":10},{"id":"2201.05771","title":"KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics","created":"2022-01-15","cited_by_count":10},{"id":"1904.06063","title":"Building a mixed-lingual neural TTS system with only monolingual data","created":"2019-04-12","cited_by_count":9},{"id":"1906.08647","title":"Semi-supervised acoustic model training for five-lingual code-switched ASR","created":"2019-06-20","cited_by_count":9},{"id":"1909.13006","title":"Part of speech tagging for code switched data","created":"2019-09-28","cited_by_count":9},{"id":"2103.00455","title":"NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformers","created":"2021-02-28","cited_by_count":9},{"id":"2112.06327","title":"Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networks","created":"2021-12-12","cited_by_count":9},{"id":"2102.09943","title":"Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach","created":"2021-02-19","cited_by_count":8},{"id":"2106.06004","title":"CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing","created":"2021-06-10","cited_by_count":8},{"id":"1604.03136","title":"Shallow Parsing Pipeline for Hindi-English Code-Mixed Social Media Text","created":"2016-04-11","cited_by_count":7},{"id":"1703.10772","title":"Joining Hands: Exploiting Monolingual Treebanks for Parsing of Code-mixing Data","created":"2017-03-31","cited_by_count":7},{"id":"1806.06200","title":"Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition","created":"2018-06-16","cited_by_count":7},{"id":"1904.03802","title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","created":"2019-04-08","cited_by_count":7},{"id":"1909.08504","title":"Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition","created":"2019-09-18","cited_by_count":7},{"id":"2009.03673","title":"kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification","created":"2020-09-08","cited_by_count":7},{"id":"2010.04482","title":"Word Level Language Identification in English Telugu Code Mixed Data","created":"2020-10-09","cited_by_count":7},{"id":"2103.00464","title":"NLP-CUET@LT-EDI-EACL2021: Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner","created":"2021-02-28","cited_by_count":7},{"id":"2103.14797","title":"Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data","created":"2021-03-27","cited_by_count":7},{"id":"2107.11534","title":"MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation","created":"2021-07-24","cited_by_count":7},{"id":"2108.01861","title":"Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Text","created":"2021-08-04","cited_by_count":7},{"id":"1808.07118","title":"Language Identification in Code-Mixed Data using Multichannel Neural Networks and Context Capture","created":"2018-08-21","cited_by_count":6},{"id":"2011.01913","title":"Towards Code-switched Classification Exploiting Constituent Language Resources","created":"2020-11-03","cited_by_count":6},{"id":"2106.01400","title":"Dual Script E2E framework for Multilingual and Code-Switching ASR","created":"2021-06-02","cited_by_count":6},{"id":"2201.12155","title":"Reducing language context confusion for end-to-end code-switching automatic speech recognition","created":"2022-01-28","cited_by_count":6},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6},{"id":"1711.01048","title":"Dual Language Models for Code Switched Speech Recognition","created":"2017-11-03","cited_by_count":5},{"id":"1805.08701","title":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance","created":"2018-05-22","cited_by_count":5},{"id":"1910.11590","title":"Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition","created":"2019-10-25","cited_by_count":5},{"id":"2006.07094","title":"Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition","created":"2020-06-12","cited_by_count":5},{"id":"2009.03397","title":"NLP-CIC at SemEval-2020 Task 9: Analysing sentiment in code-switching language using a simple deep-learning classifier","created":"2020-09-07","cited_by_count":5},{"id":"2010.00310","title":"\"Did you really mean what you said?\" : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings","created":"2020-10-01","cited_by_count":5},{"id":"2102.12407","title":"Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data","created":"2021-02-24","cited_by_count":5}],"next_cursor":"100"}