Can Perplexity Predict Fine-Tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali

Recent language models use subwording mechanisms to handle Out-of-Vocabulary(OOV) words seen during test time and, their generation capacity is generally measured using perplexity, an intrinsic metric. It is known that increasing the subword granularity results in a decrease of perplexity value. However, the study of how subwording affects the understanding capacity of language models has been very few and only limited to a handful of languages. To reduce this gap we used 6 different tokenization schemes to pretrain relatively small language models in Nepali and used the representations learned to finetune on several downstream tasks. Although byte-level BPE algorithm has been used in recent models like GPT, RoBERTa we show that on average they are sub-optimal in comparison to algorithms such as SentencePiece in finetuning performances for Nepali. Additionally, similar recent studies have focused on the Bert-based language model. We, however, pretrain and finetune sequential transformer-based language models.

Contextual Spelling Correction with Language Model for Low-resource Setting

The task of Spell Correction(SC) in low-resource languages presents a significant challenge due to the availability of only a limited corpus of data and no annotated spelling correction datasets. To tackle these challenges a small-scale word-based transformer LM is trained to provide the SC model with contextual understanding. Further, the probabilistic error rules are extracted from the corpus in an unsupervised way to model the tendency of error happening(error model). Then the combination of LM and error model is used to develop the SC model through the well-known noisy channel framework. The effectiveness of this approach is demonstrated through experiments on the Nepali language where there is access to just an unprocessed corpus of textual data.