Existing translation models are typically trained on sentence-level and formal text, limiting their ability to capture everyday conversational dialogue phenomena such as informality, speaker interaction, and discourse coherence. Most existing Indic translation resources and evaluation benchmarks focus on sentence-level or formal text, making it difficult to assess translation quality of dialogue phenomena. In this work, we introduce BaatCheet, a multilingual dialogue corpus named after the Hindi term for conversation or chitchat, containing approximately 49,000 dialogues for dialogue translation across five translation directions. We fine-tune five open-source LLMs across seven training data configurations and find that fine-tuning yields substantial gains over zero- and few-shot baselines. To comprehensively evaluate dialogue translation quality, we employ multiple evaluation strategies, including automatic metrics, LLM-as-judge, and human assessments using an SQM-guided Direct Assessment (DA) Protocol.

We present our submission to the WMT 2026 Shared Task on Low-Resource Indic Language Translation, covering four language pairs (English-Assamese, English-Mizo, English-Khasi, and English-Tagin in both directions) spanning a wide range of resource levels, from moderately-resourced Assamese down to Tagin, which barely appears in existing multilingual MT systems at all. We compare three models (NLLB-200-1.3B, Sarvam-Translate, and TranslateGemma) across three setups: fine-tuning on the official shared-task data alone, fine-tuning with added external parallel data, and a reinforcement-learning stage (RLOO) that optimizes a combined BLEU/chrF++ reward on top of the fine-tuned model. Adding external parallel data helps most for Khasi, improving English-to-Khasi by 18 BLEU, and for Mizo, where our system places first among contrastive submissions in both directions; the same augmentation leaves Assamese essentially unchanged despite contributing twice as many sentence pairs, suggesting that data provenance matters more than volume at these scales. The RLOO system degrades performance on Assamese and Mizo, where supervised fine-tuning had already produced competitive systems, but improves over the primary system on both Khasi directions and on every metric for English-to-Tagin, where it obtains the highest METEOR score of any contrastive submission. Reward-based training therefore appears most useful precisely where supervised fine-tuning has least to work with.

This paper presents an overview of the Shared Task on Patient-Centric Question Answering, organized as part of the NLP-AI4Health workshop at IJCNLP. The task aims to bridge the digital divide in healthcare by developing inclusive systems for two critical domains: Head and Neck Cancer (HNC) and Cystic Fibrosis (CF). We introduce the NLP4Health-2025 Dataset, a novel, large-scale multilingual corpus consisting of more than 45,000 validated multi-turn dialogues between patients and healthcare providers across 10 languages: Assamese, Bangla, Dogri, English, Gujarati, Hindi, Kannada, Marathi, Tamil, and Telugu. Participants were challenged to develop lightweight models (< 3 billion parameters) to perform two core activities: (1) Clinical Summarization, encompassing both abstractive summaries and structured clinical extraction (SCE), and (2) Patient-Centric QA, generating empathetic, factually accurate answers in the dialogue native language. This paper details the hybrid human-agent dataset construction pipeline, task definitions, evaluation metrics, and analyzes the performance of 9 submissions from 6 teams. The results demonstrate the viability of small language models (SLMs) in low-resource medical settings when optimized via techniques like LoRA and RAG.

Developing robust Natural Language Understanding (NLU) for morphologically rich Dravidian languages like Kannada, Malayalam, Tamil, and Telugu presents significant challenges due to their agglutinative nature and syntactic complexity. In this work, we present the Dravidian NLP Suite tackling five core tasks: Morphological Analysis (MA), POS Tagging (POS), Named Entity Recognition (NER), Dependency Parsing (DEP), and Coreference Resolution (CR), trained for monolingual models and multilingual models. To facilitate this, we present the Dravida dataset, meticulously annotated multilingual corpus for these tasks across all four languages. Our experiments demonstrate that a multilingual model, which utilizes shared linguistic features and cross-lingual patterns inherent to the Dravidian family, consistently outperforms its monolingual counterparts across all tasks. These findings suggest that multilingual learning is an effective approach for enhancing Natural Language Understanding (NLU) capabilities, particularly for languages belonging to the same family. To the best of our knowledge, this is the first work to jointly address all these core tasks on the Dravidian languages.

Dravidian languages like Tamil and Telugu are agglutinative languages, they form wordforms by combining two or more elements into a single string with morpho-phonemic changes at the point of concatenation, known as sandhi. This linguistic feature adds complexity to automatic language processing, making the pre-processing of sandhi words essential for NLP applications. We developed extensive sandhi-annotated corpora of 15K for Telugu and Tamil, focusing on the systematic application of sandhi rules which explains the word formation patterns by showing how lexical and functional categories combine to create composite non-compound words. We implemented compact sequence-to-sequence transformer networks for the automatic sandhi processing. To evaluate our models, we manually annotated Telugu and Tamil IN22-Conv Benchmark datasets with sandhi annotations. Our experiments aim to enhance the language processing tasks like machine translation in morphologically rich languages.

This paper addresses the challenges faced by Indian languages in leveraging deep learning for natural language processing (NLP) due to limited resources, annotated datasets, and Transformer-based architectures. We specifically focus on Telugu and aim to construct a Telugu morph analyzer dataset comprising 10,000 sentences. Furthermore, we assess the performance of established multi-lingual Transformer models (m-Bert, XLM-R, IndicBERT) and mono-lingual Transformer models trained from scratch on an extensive Telugu corpus comprising 80,15,588 sentences (BERT-Te). Our findings demonstrate the efficacy of Transformer-based representations pretrained on Telugu data in improving the performance of the Telugu morph analyzer, surpassing existing multi-lingual approaches. This highlights the necessity of developing dedicated corpora, annotated datasets, and machine learning models in a mono-lingual setting. We present benchmark results for the Telugu morph analyzer achieved through simple fine-tuning on our dataset.