Raviraj Joshi

Identifiers

• name variant Raviraj Joshi 0.60 · backfill

Papers (82)

1. Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi cs.CL · 2026 · author #4
2. L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models cs.CL · 2026 · author #5
3. IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages cs.CL · 2026 · author #5
4. Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition cs.CL · 2025 · author #5
5. L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages cs.CL · 2025 · author #5
6. L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models cs.CL · 2025 · author #3
7. Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking cs.CL · 2025 · author #5
8. MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models cs.CL · 2025 · author #6
9. Improving the Efficiency of Long Document Classification using Sentence Ranking Approach cs.CL · 2025 · author #4
10. L3Cube-MahaEmotions: A Marathi Emotion Recognition Dataset with Synthetic Annotations using CoTR prompting and Large Language Models cs.CL · 2025 · author #2
11. IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages cs.CL · 2025 · author #5
12. Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models cs.CL · 2025 · author #135
13. Topic Modeling in Marathi cs.CL · 2025 · author #2
14. On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages cs.CL · 2025 · author #5
15. On Importance of Code-Mixed Embeddings for Hate Speech Identification cs.CL · 2024 · author #5
16. Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning cs.CL · 2024 · author #5
17. Non-Contextual BERT or FastText? A Comparative Analysis cs.CL · 2024 · author #5
18. On Limitations of LLM as Annotator for Low Resource Languages cs.CL · 2024 · author #5
19. Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus cs.CL · 2024 · author #1
20. Long Range Named Entity Recognition for Marathi Documents cs.CL · 2024 · author #6
21. L3Cube-MahaSum: A Comprehensive Dataset and BART Models for Abstractive Text Summarization in Marathi cs.CL · 2024 · author #5
22. Automated Assessment of Multimodal Answer Sheets in the STEM domain cs.AI · 2024 · author #6
23. Towards Building Efficient Sentence BERT Models using Layer Pruning cs.CL · 2024 · author #3
24. On Importance of Pruning and Distillation for Efficient Low Resource NLP cs.CL · 2024 · author #5
25. L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context cs.CL · 2024 · author #5
26. Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages cs.CL · 2024 · author #3
27. A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations cs.CL · 2024 · author #3
28. LLM Pruning and Distillation in Practice: The Minitron Approach cs.CL · 2024 · author #3
29. Leveraging Parameter Efficient Training Methods for Low Resource Text Classification: A Case Study in Marathi cs.CL · 2024 · author #5
30. Compact Language Models via Pruning and Knowledge Distillation cs.CL · 2024 · author #3
31. Curating Stopwords in Marathi: A TF-IDF Approach for Improved Text Analysis and Information Retrieval cs.CL · 2024 · author #4
32. Universal Cross-Lingual Text Classification cs.CL · 2024 · author #6
33. TextGram: Towards a better domain-adaptive pretraining cs.CL · 2024 · author #5
34. L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi cs.CL · 2024 · author #5
35. MahaSQuAD: Bridging Linguistic Divides in Marathi Question-Answering cs.CL · 2024 · author #5
36. L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages cs.CL · 2024 · author #5
37. L3Cube-MahaSocialNER: A Social Media based Marathi NER Dataset and BERT models cs.CL · 2023 · author #5
38. On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi cs.CL · 2023 · author #5
39. Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning cs.LG · 2023 · author #1
40. Code-Mixed Text to Speech Synthesis under Low-Resource Constraints cs.LG · 2023 · author #1
41. SenTest: Evaluating Robustness of Sentence Encoders cs.CL · 2023 · author #6
42. mahaNLP: A Marathi Natural Language Processing Library cs.CL · 2023 · author #5
43. Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages cs.CL · 2023 · author #2
44. Robust Sentiment Analysis for Low Resource languages Using Data Augmentation Approaches: A Case Study in Marathi cs.CL · 2023 · author #6
45. My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks cs.CL · 2023 · author #5
46. L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models cs.CL · 2023 · author #5
47. Enhancing Low Resource NER Using Assisting Language And Transfer Learning cs.CL · 2023 · author #5
48. Leveraging Language Identification to Enhance Code-Mixed Text Classification cs.CL · 2023 · author #5
49. Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data cs.CL · 2023 · author #5
50. L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT cs.CL · 2023 · author #5
51. A Twitter BERT Approach for Offensive Language Detection in Marathi cs.CL · 2022 · author #5
52. Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages cs.CL · 2022 · author #5
53. L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages cs.CL · 2022 · author #1
54. L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi cs.CL · 2022 · author #5
55. Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection cs.CL · 2022 · author #5
56. Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification cs.CL · 2022 · author #5
57. A Review of Challenges in Machine Learning based Automated Hate Speech Detection cs.CL · 2022 · author #3
58. On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode cs.SD · 2022 · author #1
59. A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data eess.AS · 2022 · author #1
60. L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library cs.CL · 2022 · author #1
61. Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi cs.CL · 2022 · author #3
62. L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models cs.CL · 2022 · author #2
63. L3Cube-MahaNER: A Marathi Named Entity Recognition Dataset and BERT models cs.CL · 2022 · author #5
64. L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT models cs.CL · 2022 · author #5
65. Mono vs Multilingual BERT: A Case Study in Hindi and Marathi Named Entity Recognition cs.CL · 2022 · author #5
66. L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources cs.CL · 2022 · author #1
67. Hierarchical Neural Network Approaches for Long Document Classification cs.CL · 2022 · author #5
68. On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations cs.CL · 2022 · author #4
69. Attention based end to end Speech Recognition for Voice Search in Hindi and English eess.AS · 2021 · author #1
70. Comparative Study of Long Document Classification cs.CL · 2021 · author #6
71. Hate and Offensive Speech Detection in Hindi and Marathi cs.CL · 2021 · author #5
72. Contextual Hate Speech Detection in Code Mixed Text using Transformer Based Approaches cs.CL · 2021 · author #2
73. SISA: Securing Images by Selective Alteration cs.CR · 2021 · author #3
74. L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset cs.CL · 2021 · author #5
75. ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models cs.CL · 2021 · author #7
76. ICodeNet -- A Hierarchical Neural Network Approach for Source Code Author Identification cs.LG · 2021 · author #4
77. Experimental Evaluation of Deep Learning models for Marathi Text Classification cs.CL · 2021 · author #6
78. Evaluation of Deep Learning Models for Hostility Detection in Hindi Text cs.CL · 2021 · author #4
79. Evaluating Deep Learning Approaches for Covid19 Fake News Detection cs.LG · 2021 · author #5
80. Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020 cs.CL · 2020 · author #4
81. Evaluating Input Representation for Language Identification in Hindi-English Code Mixed Text cs.CL · 2020 · author #2
82. Deep Learning for Hindi Text Classification: A Comparison cs.IR · 2020 · author #3

Mentions

• 2504.03624 #135 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2509.02514 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2509.02503 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2508.21569 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2506.00863 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2508.17490 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2508.17444 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2506.07248 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2505.03688 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2410.14815 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2411.17637 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2411.17661 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2502.02100 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2501.00733 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.04512 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2408.11796 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2411.18577 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2411.18571 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2407.14679 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.08706 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2410.09192 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2410.09184 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.15749 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.14168 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.14162 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2409.02712 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2408.03172 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2406.11029 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2406.11028 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2404.18228 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2404.18216 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2401.02254 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2404.13364 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2401.00170 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2312.01306 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2312.01107 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2312.01103 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2311.17722 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2311.02579 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2310.02249 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2310.00734 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2306.14030 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2306.13888 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2306.06477 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2306.04964 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2305.15722 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2304.11434 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2203.12907 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2211.11418 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2212.10039 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2212.05702 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2210.04267 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2211.11187 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2204.08669 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2209.12943 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2209.05294 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2206.12829 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2201.00318 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2206.13240 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2201.06774 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2205.14728 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2203.13778 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2204.08398 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2204.06029 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2202.01159 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2111.00702 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2102.00238 #7 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2111.10208 #1 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2101.04899 #6 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2011.11263 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2110.12200 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2110.09338 #2 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2106.11770 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2103.11408 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2102.00230 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2101.04144 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2101.04012 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2012.12112 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2001.10340 #3 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2606.28796 #4 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2606.24825 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi
• 2606.22841 #5 · arxiv_oai · confidence 0.70 Raviraj Joshi

Frequent Coauthors

• Geetanjali Kale 8 shared papers
• Ananya Joshi 6 shared papers
• Isha Joshi 6 shared papers
• Abhishek Velankar 4 shared papers
• Aditya Kane 4 shared papers
• Hrushikesh Patil 4 shared papers
• Omkar Gokhale 4 shared papers
• Ramchandra Joshi 4 shared papers
• Shantanu Patankar 4 shared papers
• Tanmay Chavan 4 shared papers
• Aabha Pingle 3 shared papers
• Abhay Shanbhag 3 shared papers
• Abhishek Phaltankar 3 shared papers
• Aditya Vyawahare 3 shared papers
• Aishwarya Mirashi 3 shared papers
• Amogh Thakurdesai 3 shared papers
• Aparna Ranade 3 shared papers
• Apurva Wani 3 shared papers
• Arnav Ladkat 3 shared papers
• Bryan Catanzaro 3 shared papers