paper-with-me

Papers

IIITH-BUT system for IWSLT 2025 low-resource Bhojpuri to Hindi speech translation

2025-06-05 · Bhavana Akkiraju, Aishwarya Pothula, Santosh Kesiraju, Anil Kumar Vuppala

This paper presents the submission of IIITH-BUT to the IWSLT 2025 shared task on speech translation for the low-resource Bhojpuri-Hindi language pair. We explored the impact of hyperparameter optimisation and data augmentation techniques on the performance of the SeamlessM4T model fine-tuned for this specific task. We systematically investigated a range of hyperparameters including learning rate schedules, number of update steps, warm-up steps, label smoothing, and batch sizes; and report their effect on translation quality. To address data scarcity, we applied speed perturbation and SpecAugment and studied their effect on translation quality. We also examined the use of cross-lingual signal through joint training with Marathi and Bhojpuri speech data. Our experiments reveal that careful selection of hyperparameters and the application of simple yet effective augmentation techniques significantly improve performance in low-resource settings. We also analysed the translation hypotheses to understand various kinds of errors that impacted the translation quality in terms of BLEU.

📄 PDF Abstract BibTeX arXiv:2506.04714

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationTranslation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Unsupervised Approach for Zero-Shot Experiments: Bhojpuri–Hindi and Magahi–Hindi@LoResMT 2020

2020-12-01 · loresmt (AACL) 2020 12 · Amit Kumar, Rajesh Kumar Mundotiya, Anil Kumar Singh

This paper reports a Machine Translation (MT) system submitted by the NLPRL team for the Bhojpuri–Hindi and Magahi–Hindi language pairs at LoResMT 2020 shared task. We used an unsupervised domain adaptation approach that…

Domain AdaptationMachine TranslationTranslationUnsupervised Domain Adaptation

Development of a Dataset and a Deep Learning Baseline Named Entity Recognizer for Three Low Resource Languages: Bhojpuri, Maithili and Magahi

2020-09-14 · Rajesh Kumar Mundotiya, Shantanu Kumar, Ajeet kumar, Umesh Chandra Chaudhary 외

In Natural Language Processing (NLP) pipelines, Named Entity Recognition (NER) is one of the preliminary problems, which marks proper nouns and other named entities such as Location, Person, Organization, Disease etc. Su…

Machine Translationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Learning cross-lingual phonological and orthagraphic adaptations: a case study in improving neural machine translation between low-resource languages

2018-11-21 · Saurav Jha, Akhilesh Sudhakar, Anil Kumar Singh

Out-of-vocabulary (OOV) words can pose serious challenges for machine translation (MT) tasks, and in particular, for low-resource language (LRL) pairs, i.e., language pairs for which few or no parallel corpora exist. Our…

Machine TranslationNMTTranslation

Linguistic Resources for Bhojpuri, Magahi and Maithili: Statistics about them, their Similarity Estimates, and Baselines for Three Applications

2020-04-29 · Rajesh Kumar Mundotiya, Manish Kumar Singh, Rahul Kapur, Swasti Mishra 외

Corpus preparation for low-resource languages and for development of human language technology to analyze or computationally process them is a laborious task, primarily due to the unavailability of expert linguists who a…

ChunkingPOSPOS Tagging

When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages

2023-05-23 · Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot 외

Most existing approaches for unsupervised bilingual lexicon induction (BLI) depend on good quality static or contextual embeddings requiring large monolingual corpora for both languages. However, unsupervised BLI is most…

Bilingual Lexicon InductionLanguage ModelingLanguage Modelling