ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models
Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to morphologically inconsistent languages such as Roman Urdu remains underexplored. Roman Urdu spelling variation causes severe sub-word fragmentation, averaging 1.50 sub-words per token. We propose \textit{ROMEVA} (Roman Urdu Embedding-preserving Vocabulary Adaptation), which combines sub-word-average initialization and a PCA-guided anchor loss to stabilize embeddings during vocabulary expansion. Using a 36,130-comment Roman Urdu corpus, we add 500 highly fragmented tokens to mBERT and compare naive fine-tuning, sub-word-aware fine-tuning, and \textit{ROMEVA}. While \textit{ROMEVA} most effectively preserves the pretrained embedding space, naive fine-tuning achieves the strongest downstream sentiment classification performance. These findings reveal a disconnect between embedding stability and downstream performance, suggesting that stronger adaptation may be preferable to strict embedding preservation in morphologically inconsistent languages.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Evaluating the Wordnet and CoRoLa-based Word Embedding Vectors for Romanian as Resources in the Task of Microworlds Lexicon Expansion
Within a larger frame of facilitating human-robot interaction, we present here the creation of a core vocabulary to be learned by a robot. It is extracted from two tokenised and lemmatized scenarios pertaining to two ima…
On Romanization for Model Transfer Between Scripts in Neural Machine Translation
Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabu…
Machine TranslationTransfer LearningTranslationIITP-MT at WAT2021: Indic-English Multilingual Neural Machine Translation using Romanized Vocabulary
This paper describes the systems submitted to WAT 2021 MultiIndicMT shared task by IITP-MT team. We submit two multilingual Neural Machine Translation (NMT) systems (Indic-to-English and English-to-Indic). We romanize al…
Machine TranslationNMTTranslationRomanization-based Large-scale Adaptation of Multilingual Language Models
Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. However, their large-scale deployment to many languages, besides pretraining data scarcit…
Cross-Lingual TransferTransliterationRomanization Encoding For Multilingual ASR
We introduce romanization encoding for script-heavy languages to optimize multilingual and code-switching Automatic Speech Recognition (ASR) systems. By adopting romanization encoding alongside a balanced concatenated to…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2