{"list":"other","total":139,"rows":[{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"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":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"1710.04087","title":"Word Translation Without Parallel Data","created":"2017-10-11","cited_by_count":487},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2004.14900","title":"MLSUM: The Multilingual Summarization Corpus","created":"2020-04-30","cited_by_count":121},{"id":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118},{"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":"2309.07462","title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","created":"2023-09-14","cited_by_count":88},{"id":"2311.08526","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","created":"2023-11-14","cited_by_count":88},{"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":"1904.00784","title":"A Survey of Code-switched Speech and Language Processing","created":"2019-03-25","cited_by_count":75},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68},{"id":"2305.14235","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","created":"2023-05-23","cited_by_count":65},{"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":"2301.01967","title":"A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies","created":"2023-01-05","cited_by_count":59},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"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":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51},{"id":"2108.13655","title":"MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER","created":"2021-08-31","cited_by_count":42},{"id":"2311.08711","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","created":"2023-11-15","cited_by_count":39},{"id":"2402.12204","title":"Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages","created":"2024-02-19","cited_by_count":36},{"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":"2406.15481","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","created":"2024-06-17","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":"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":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27},{"id":"2204.05076","title":"End-to-End Speech Translation for Code Switched Speech","created":"2022-04-11","cited_by_count":26},{"id":"2103.07792","title":"Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling","created":"2021-03-13","cited_by_count":25},{"id":"2309.16953","title":"Enhancing Code-switching Speech Recognition with Interactive Language Biases","created":"2023-09-29","cited_by_count":21},{"id":"1909.05158","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","created":"2019-09-11","cited_by_count":18},{"id":"2106.09460","title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","created":"2021-06-17","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":"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":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16},{"id":"2504.01801","title":"Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training","created":"2025-04-02","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":"2506.00087","title":"SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset","created":"2025-05-30","cited_by_count":14},{"id":"1906.08972","title":"A Deep Generative Model for Code-Switched Text","created":"2019-06-21","cited_by_count":13},{"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":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12},{"id":"2311.15023","title":"Offensive Language Identification in Transliterated and Code-Mixed Bangla","created":"2023-11-25","cited_by_count":12},{"id":"2405.02578","title":"Mixat: A Data Set of Bilingual Emirati-English Speech","created":"2024-05-04","cited_by_count":12},{"id":"2102.01051","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","created":"2021-02-01","cited_by_count":11},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11},{"id":"2501.09512","title":"PIER: A Novel Metric for Evaluating What Matters in Code-Switching","created":"2025-01-16","cited_by_count":11},{"id":"2105.13573","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","created":"2021-05-28","cited_by_count":10},{"id":"2201.03804","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","created":"2022-01-11","cited_by_count":10},{"id":"2309.15674","title":"Speech collage: code-switched audio generation by collaging monolingual corpora","created":"2023-09-27","cited_by_count":10},{"id":"2312.08856","title":"Attention-Guided Adaptation for Code-Switching Speech Recognition","created":"2023-12-14","cited_by_count":10},{"id":"2405.20628","title":"ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos","created":"2024-05-31","cited_by_count":10},{"id":"2408.08964","title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","created":"2024-08-16","cited_by_count":10},{"id":"2507.18791","title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages","created":"2025-07-24","cited_by_count":10},{"id":"2409.15905","title":"Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM","created":"2024-09-24","cited_by_count":9},{"id":"2412.09034","title":"Dialogue Language Model with Large-Scale Persona Data Engineering","created":"2024-12-12","cited_by_count":9},{"id":"2106.06004","title":"CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing","created":"2021-06-10","cited_by_count":8},{"id":"2210.12540","title":"EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching","created":"2022-10-22","cited_by_count":8},{"id":"2303.04092","title":"CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization","created":"2023-03-07","cited_by_count":8},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8},{"id":"2506.01840","title":"Minimal Pair-Based Evaluation of Code-Switching","created":"2025-06-02","cited_by_count":8},{"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":"2108.04616","title":"Hope Speech detection in under-resourced Kannada language","created":"2021-08-10","cited_by_count":7},{"id":"2208.08629","title":"MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation","created":"2022-08-18","cited_by_count":7},{"id":"2210.06990","title":"Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text","created":"2022-10-11","cited_by_count":7},{"id":"2305.16724","title":"Code-Switched Text Synthesis in Unseen Language Pairs","created":"2023-05-26","cited_by_count":7},{"id":"2310.18023","title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","created":"2023-10-27","cited_by_count":7},{"id":"2403.04872","title":"Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text","created":"2024-03-07","cited_by_count":7},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","cited_by_count":7},{"id":"2503.21670","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","created":"2025-03-27","cited_by_count":7},{"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":"2306.10348","title":"Typo-Robust Representation Learning for Dense Retrieval","created":"2023-06-17","cited_by_count":6},{"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":"2108.05838","title":"Combining (second-order) graph-based and headed-span-based projective dependency parsing","created":"2021-08-12","cited_by_count":5},{"id":"2109.02938","title":"Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT","created":"2021-09-07","cited_by_count":5},{"id":"2111.01231","title":"Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching","created":"2021-11-01","cited_by_count":5},{"id":"2211.07514","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","created":"2022-11-14","cited_by_count":5},{"id":"2310.18387","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","created":"2023-10-27","cited_by_count":5},{"id":"2401.16895","title":"Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching","created":"2024-01-30","cited_by_count":5},{"id":"2403.16771","title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","created":"2024-03-25","cited_by_count":5},{"id":"2410.18836","title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages","created":"2024-10-24","cited_by_count":5},{"id":"2411.09073","title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","created":"2024-11-13","cited_by_count":5},{"id":"2006.14465","title":"IIT Gandhinagar at SemEval-2020 Task 9: Code-Mixed Sentiment Classification Using Candidate Sentence Generation and Selection","created":"2020-06-25","cited_by_count":4},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4},{"id":"2206.07318","title":"CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data","created":"2022-06-15","cited_by_count":4},{"id":"2305.05295","title":"Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data","created":"2023-05-09","cited_by_count":4},{"id":"2310.12648","title":"Towards Real-World Streaming Speech Translation for Code-Switched Speech","created":"2023-10-19","cited_by_count":4},{"id":"2312.10793","title":"Demystifying Instruction Mixing for Fine-tuning Large Language Models","created":"2023-12-17","cited_by_count":4}],"next_cursor":"100"}