arXiv Computation and Language By Amrit Gopinath, Sangeetha Sivanesan

Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs

Read the original on arXiv Computation and Language →

The paper presents a corpus of 1,262 Classical Tamil verse‑commentary pairs and evaluates several neural representation learning models—including recurrent, Transformer, Siamese, mBART‑style encoder‑decoder, and decoder‑only language models—against a TF‑IDF baseline. Experiments reveal limited gains: token‑F1 scores range from 0.02 to 0.20, the encoder‑decoder continues to lower training loss even after validation loss rises, and the decoder‑only model only reproduces authentic word order in 95.5% of minimal‑pair tests but fails to generate held‑out commentary content. The authors release the extraction and evaluation protocol while noting that redistribution of the source commentaries requires permission.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning
Jul 28

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

arXiv:2607. 23319v1 Announce Type: cross Abstract: Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages.

By Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani
arXiv AI
Aug 20

NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages

NE‑BERT is a multilingual encoder trained on about 8.3 million sentences from nine Northeast Indian languages plus Hindi and English. Using weighted sampling and a custom SentencePiece tokenizer, it achieves significantly lower perplexity than IndicBERT‑V2, MuRIL, and mBERT, and improves tokenization fertility. The model also addresses vocabulary fragmentation in extremely low‑resource languages through aggressive upsampling, and its effectiveness is validated on part‑of‑speech tagging for three of the languages.

By Badal Nyalang
arXiv Computation and Language
Aug 28

KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training

KinyaEmbed is the first sentence‑embedding model specifically designed for Kinyarwanda, built on KinyaBERT‑large and trained through a four‑stage curriculum that incorporates paraphrase pairs, translated MNLI triplets, OPUS‑100 translation pairs, and high‑quality KinyaCOMET pairs. It outperforms existing multilingual embeddings on the SemRel2024‑rw benchmark, achieving a Spearman ψ of 0.7298, and introduces the Wiki‑RW‑STS benchmark of 300 contamination‑free Kinyarwanda sentence pairs. All model checkpoints, filtered pairs, and the new benchmark are publicly released.

By Ireddi Rakshitha, Devavarapu Yashwanth, Ntakirutimana Pierre
arXiv Computation and Language
Sep 1

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

The paper compares generative and encoder-based neural models for multilingual Named Entity Recognition (NER) across the eleven languages of the Naamapadam benchmark. Five classic model families, four decoder-only large language models fine‑tuned with LoRA and 4‑bit NF4 quantisation, and nine generative models in zero‑to‑5‑shot inference were evaluated under strict CoNLL span‑level metrics. Encoder-based models (mBERT and XLM‑R) achieved substantially higher F1 scores—up to 0.675 on Hindi—than any generative architecture, with gaps of 7.5–40 percentage points; the best few‑shot result reached only 28% of the encoder baseline. The study identifies three language clusters (encoder‑dominant, partial‑coverage, and failure‑zone) and offers deployment guidelines based on transfer learning and low‑resource NLP principles.

By Jakkala Mahesh, Jatavath Shravan Kumar, Komalla Shivani, Sujoy Sarkar