Tokenization is a critical component of the language modeling pipeline, but it is poorly understood. Tokenizers can drastically impact downstream performance, but currently there is mixed evidence about which intrinsic tokenizer evaluations are able to predict which tokenizers will result in a better language model before training the model. In this paper, we analyze approximately 200 language models trained on nine different languages. We evaluate both models and their tokenizers and test whether there is a relationship between any proposed intrinsic tokenizer evaluations and model performance, as measured by a wide variety of benchmarks. Despite the quantity and variety of proposed intrinsic tokenizer metrics, none consistently predicts downstream performance across model families, tasks, and languages. This motivates the need for novel tokenizer evaluation metrics and approaches. Our analysis of a novel linguistically grounded metric introduced in this work shows that new metrics can capture aspects of tokenizer quality that existing metrics miss, though their predictive power is likely to vary across model families and languages.

The Nepali language has distinct linguistic features, especially its complex script (Devanagari script), morphology, and various dialects, which pose a unique challenge for Natural Language Understanding (NLU) tasks. While the Nepali Language Understanding Evaluation (Nep-gLUE) benchmark provides a foundation for evaluating models, it remains limited in scope, covering four tasks. This restricts their utility for comprehensive assessments of Natural Language Processing (NLP) models. To address this limitation, we introduce twelve new datasets, creating a new benchmark, the Nepali Language Understanding Evaluation (NLUE) benchmark for evaluating the performance of models across a diverse set of Natural Language Understanding (NLU) tasks. The added tasks include Single-Sentence Classification, Similarity and Paraphrase Tasks, Natural Language Inference (NLI), and General Masked Evaluation Task (GMET). Through extensive experiments, we demonstrate that existing top models struggle with the added complexity of these tasks. We also find that the best multilingual model outperforms the best monolingual models across most tasks, highlighting the need for more robust solutions tailored to the Nepali language. This expanded benchmark sets a new standard for evaluating, comparing, and advancing models, contributing significantly to the broader goal of advancing NLP research for low-resource languages.

Transformer-based pre-trained language models have dominated the field of Natural Language Processing (NLP) for quite some time now. However, the Nepali language, spoken by approximately 32 million people worldwide, remains significantly underrepresented in this domain. This underrepresentation is primarily attributed to the scarcity of monolingual data corpora and limited available resources for the Nepali language. While existing efforts have predominantly concentrated on basic encoder-based models, there is a notable gap in the exploration of decoder-based architectures. To address this gap, we have collected 27.5 GB of Nepali text data, approximately 2.4x larger than any previously available Nepali language corpus. Leveraging this data, we pre-trained three different models i.e., BERT, RoBERTa, and GPT-2, exclusively for the Nepali Language. Furthermore, we performed instruction tuning and explored its potential for monolingual Nepali data, providing a foundation for future research. Our models outperformed the existing best model by 2 points on Nep-gLUE benchmark, scoring 95.60 and also outperformed existing models on text generation tasks, demonstrating improvements in both understanding and generating Nepali text.