MorphTok: Morphologically Grounded Tokenization for Indian Languages

Tokenization is a crucial step in NLP, especially with the rise of large language models (LLMs), impacting downstream performance, computational cost, and efficiency. Existing LLMs rely on the classical Byte-pair Encoding (BPE) algorithm for subword tokenization that greedily merges frequent character bigrams. This often leads to segmentation that does not align with linguistically meaningful units. To address this, we propose morphology-aware segmentation as a pre-tokenization step prior to applying BPE. To facilitate morphology-aware segmentation, we create a novel dataset for Hindi and Marathi, incorporating sandhi splitting to enhance the subword tokenization. Experiments on downstream tasks show that morphologically grounded tokenization improves performance for machine translation and language modeling. Additionally, to handle the ambiguity in the Unicode characters for diacritics, particularly dependent vowels in syllable-based writing systems, we introduce Constrained BPE (CBPE), an extension to the traditional BPE algorithm that incorporates script-specific constraints. Specifically, CBPE handles dependent vowels. Our results show that CBPE achieves a 1.68\% reduction in fertility scores while maintaining comparable or improved downstream performance in machine translation, offering a computationally efficient alternative to standard BPE. Moreover, to evaluate segmentation across different tokenization algorithms, we introduce a new human evaluation metric, \textit{EvalTok}, enabling more human-grounded assessment.

NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task

This paper describes NLIP Lab's multilingual machine translation system for the WAT24 shared task on multilingual Indic MT task for 22 scheduled languages belonging to 4 language families. We explore pre-training for Indic languages using alignment agreement objectives. We utilize bi-lingual dictionaries to substitute words from source sentences. Furthermore, we fine-tuned language direction-specific multilingual translation models using small and high-quality seed data. Our primary submission is a 243M parameters multilingual translation model covering 22 Indic languages. In the IN22-Gen benchmark, we achieved an average chrF++ score of 46.80 and 18.19 BLEU score for the En-Indic direction. In the Indic-En direction, we achieved an average chrF++ score of 56.34 and 30.82 BLEU score. In the In22-Conv benchmark, we achieved an average chrF++ score of 43.43 and BLEU score of 16.58 in the En-Indic direction, and in the Indic-En direction, we achieved an average of 52.44 and 29.77 for chrF++ and BLEU respectively. Our model\footnote{Our code and models are available at \url{https://github.com/maharajbrahma/WAT2024-MultiIndicMT}} is competitive with IndicTransv1 (474M parameter model).

NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task

In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng $\leftrightarrow$ {as, kha, lus, mni} as participating language pairs. In this shared task, we explore the finetuning of a pre-trained model motivated by the pre-trained objective of aligning embeddings closer by alignment augmentation \cite{lin-etal-2020-pre} for 22 scheduled Indian languages. Our primary system is based on language-specific finetuning on a pre-trained model. We achieve chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for eng$\rightarrow$as, eng$\rightarrow$kha, eng$\rightarrow$lus, eng$\rightarrow$mni respectively. We also explore multilingual training with/without language grouping and layer-freezing. Our code, models, and generated translations are available here: https://github.com/pramitsahoo/WMT2024-LRILT.