arXiv subjects

Sujoy Sarkar

Publications and source records attributed to Sujoy Sarkar.

3 recordsLinked to original sources

arXiv2026

Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam

Language is humanity's most consequential technology, yet for over a billion speakers across India's twenty-two constitutionally recognised languages, its digital layer remains structurally incomplete. Named Entity Recognition (NER), the foundational step in transforming raw text into machine-interpretable knowledge, has been studied exhaustively for English but remains largely unsolved across most Indic languages. This paper presents a rigorous comparative study of generative and encoder-based neural architectures for NER on all eleven languages of the Naamapadam benchmark. We evaluate five classic model families spanning sequence-to-sequence transformers and multilingual encoders; four decoder-only large language models (LLMs) fine-tuned with LoRA and 4-bit NF4 quantisation; and nine generative models in zero-to-5-shot inference. Under strict CoNLL span-level evaluation, encoder-based models (mBERT and XLM-R, both F1=0.675 on Hindi) substantially outperform every generative architecture in ten of eleven languages, with gaps of 7.5-40 percentage points against the strongest competitor (Gemma-2-2B: avg F1=0.427). The best few-shot result reaches only 28% of the encoder baseline. We identify three language clusters--encoder-dominant, partial-coverage, and failure-zone; and provide actionable deployment guidelines grounded in transfer learning and low-resource NLP principles.

cs.CL↗

arXiv2026

Pad\=artha: Ontology-Grounded Fine-Grained NER Benchmark for Classical Sanskrit

Annotation schemas are not neutral. When applied to classical literature, tag sets developed for modern journalistic texts impose source-culture definitions on texts they were never designed to describe. We instead ground a schema in the tradition of the text itself introducing \textit{Pad\=artha}, the first ontology-grounded fine-grained Named Entity Recognition (NER) benchmark for Sanskrit, built on the \textit{Mah\=abh\=arata} epic. Our tag set derives from \textit{Ny\=aya-Vai\'sesika}, a classical Indian ontological system, yielding 18 fine-grained categories organized under 10 ontological nodes and mapped onto five standard coarse tags, ensuring interoperability with existing benchmarks. Expert annotators label over 12.6K entries from a scholarly index of named entities, linked to corresponding mentions in the \textit{Mah\=an\=ama} corpus, producing fine-grained annotations for 108,335 entity mentions across 73,632 verses, along with a 5,000-verse expert-verified test set sampled to stress rare mentions. We present the first systematic benchmarking of generative NER against traditional architectures for Sanskrit, finding that fine-tuned generative models perform comparably to task-specific systems. However, all systems show a sharp decline from coarse to fine granularity and struggle with out-of-entity mentions unseen during training. The limitation is not due to data scarcity alone, as fine-tuned models recall unseen entities far worse than seen ones and tend to default to the majority sense under lexical ambiguity.

cs.CL↗

arXiv2025

Mah\={a}n\={a}ma: A Unique Testbed for Literary Entity Discovery and Linking

High lexical variation, ambiguous references, and long-range dependencies make entity resolution in literary texts particularly challenging. We present Mah\={a}n\={a}ma, the first large-scale dataset for end-to-end Entity Discovery and Linking (EDL) in Sanskrit, a morphologically rich and under-resourced language. Derived from the Mah\={a}bh\={a}rata, the world's longest epic, the dataset comprises over 109K named entity mentions mapped to 5.5K unique entities, and is aligned with an English knowledge base to support cross-lingual linking. The complex narrative structure of Mah\={a}n\={a}ma, coupled with extensive name variation and ambiguity, poses significant challenges to resolution systems. Our evaluation reveals that current coreference and entity linking models struggle when evaluated on the global context of the test set. These results highlight the limitations of current approaches in resolving entities within such complex discourse. Mah\=an\=ama thus provides a unique benchmark for advancing entity resolution, especially in literary domains.

cs.CL↗