{"total":128,"rows":[{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"area":null},{"id":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"area":null},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42,"area":null},{"id":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2212.10168","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","cited_by_count":27,"area":null},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26,"area":null},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21,"area":null},{"id":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2409.11501","title":"Egalitarian Language Representation in Language Models: It All Begins with Tokenizers","created":"2024-09-17","cited_by_count":20,"area":null},{"id":"2205.03018","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","created":"2022-05-06","cited_by_count":19,"area":null},{"id":"2208.12666","title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","created":"2022-08-26","cited_by_count":16,"area":null},{"id":"2210.05109","title":"BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2305.14105","title":"CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2312.12624","title":"Building a Llama2-finetuned LLM for Odia Language Utilizing Domain Knowledge Instruction Set","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2310.18600","title":"MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2405.19462","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2508.08424","title":"Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2301.08008","title":"Improving Machine Translation with Phrase Pair Injection and Corpus Filtering","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2505.14045","title":"From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2204.05814","title":"MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2209.13279","title":"Improving Multilingual Neural Machine Translation System for Indic Languages","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.17377","title":"A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2507.13390","title":"PARAM-1 BharatGen 2.9B Model","created":"2025-07-16","cited_by_count":6,"area":null},{"id":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2308.09862","title":"Breaking Language Barriers: A Question Answering Dataset for Hindi and Marathi","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2312.09508","title":"IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2108.08556","title":"Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021","created":"2021-08-19","cited_by_count":4,"area":null},{"id":"2202.00291","title":"XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages","created":"2022-02-01","cited_by_count":4,"area":null},{"id":"2205.02543","title":"OCR Synthetic Benchmark Dataset for Indic Languages","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2210.06996","title":"DICTDIS: Dictionary Constrained Disambiguation for Improved NMT","created":"2022-10-13","cited_by_count":4,"area":null},{"id":"2307.07948","title":"Model Adaptation for ASR in low-resource Indian Languages","created":"2023-07-16","cited_by_count":4,"area":null},{"id":"2310.09765","title":"MILPaC: A Novel Benchmark for Evaluating Translation of Legal Text to Indian Languages","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2311.03767","title":"Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2403.19142","title":"A Tulu Resource for Machine Translation","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2505.23714","title":"SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2203.01644","title":"UDAAN: Machine Learning based Post-Editing tool for Document Translation","created":"2022-03-03","cited_by_count":3,"area":null},{"id":"2206.05154","title":"Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2302.14635","title":"H-AES: Towards Automated Essay Scoring for Hindi","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2305.13085","title":"Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2501.17265","title":"Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2508.12774","title":"From SALAMANDRA to SALAMANDRATA: BSC Submission for WMT25 General Machine Translation Shared Task","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2205.11976","title":"Universal Dependency Treebank for Odia Language","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2305.12518","title":"VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2308.16075","title":"Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2405.11200","title":"LexGen: Domain-aware Multilingual Lexicon Generation","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2505.18466","title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2506.17789","title":"Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2604.02881","title":"One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.29379","title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2111.07906","title":"IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languages","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2111.11815","title":"CL-NERIL: A Cross-Lingual Model for NER in Indian Languages","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2112.08570","title":"Can Multilinguality benefit Non-autoregressive Machine Translation?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2204.09098","title":"PICT@DravidianLangTech-ACL2022: Neural Machine Translation On Dravidian Languages","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2209.11252","title":"XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2210.12215","title":"Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed data","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2301.00539","title":"Statistical Machine Translation for Indic Languages","created":"2023-01-02","cited_by_count":1,"area":null},{"id":"2302.04790","title":"Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2304.13005","title":"Evaluating Inter-Bilingual Semantic Parsing for Indian Languages","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2305.05214","title":"CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages","created":"2023-05-09","cited_by_count":1,"area":null},{"id":"2306.15399","title":"Quality Estimation of Machine Translated Texts based on Direct Evidence from Training Data","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2312.15181","title":"Multilingual Bias Detection and Mitigation for Indian Languages","created":"2023-12-23","cited_by_count":1,"area":null},{"id":"2401.07847","title":"Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2409.02712","title":"A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2411.19096","title":"Pralekha: Cross-Lingual Document Alignment for Indic Languages","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2501.00874","title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2504.09753","title":"Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2505.21937","title":"Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.19548","title":"Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2507.01234","title":"The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2509.19941","title":"CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.03498","title":"BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2511.23235","title":"Tourism Question Answer System in Indian Language using Domain-Adapted Foundation Models","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2512.01852","title":"BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.14053","title":"NepTam: A Nepali-Tamang Parallel Corpus and Baseline Machine Translation Experiments","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2608.11110","title":"Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2111.03813","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2111.11159","title":"Investigating Cross-Linguistic Gender Bias in Hindi-English Across Domains","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2112.01742","title":"Multitask Finetuning for Improving Neural Machine Translation in Indian Languages","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2207.03256","title":"Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approaches","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2210.11309","title":"The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)","created":"2022-10-20","cited_by_count":0,"area":null}],"next_cursor":"100"}