TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data

• URL: http://arxiv.org/abs/2405.09913v2
• Date: Sun, 15 Dec 2024 10:20:21 GMT
• Title: TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
• Authors: Yihong Liu, Chunlan Ma, Haotian Ye, Hinrich Schütze,
• Abstract summary: This paper proposes a simple but effective framework: Transliterate-Merge-literation (TransMI) TransMI can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training. Our experiments demonstrate that TransMI not only preserves the mPLM's ability to handle non-transliterated data, but also enables it to effectively process transliterated data, thereby facilitating crosslingual transfer across scripts.
• Score: 50.40191599304911
• License:
• Abstract: Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as transliteration brings about new subwords not covered in existing multilingual pretrained language models (mPLMs). This is undesirable because it requires a large computation budget. A more promising way is to make full use of available mPLMs. To this end, this paper proposes a simple but effective framework: Transliterate-Merge-Initialize (TransMI). TransMI can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training. TransMI has three stages: (a) transliterate the vocabulary of an mPLM into a common script; (b) merge the new vocabulary with the original vocabulary; and (c) initialize the embeddings of the new subwords. We apply TransMI to three strong recent mPLMs. Our experiments demonstrate that TransMI not only preserves the mPLM's ability to handle non-transliterated data, but also enables it to effectively process transliterated data, thereby facilitating crosslingual transfer across scripts. The results show consistent improvements of 3% to 34% for different mPLMs and tasks. We make our code and models publicly available at \url{https://github.com/cisnlp/TransMI}.

Related papers

• InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation [9.655135415596414]
  Code translation aims to convert a program from one programming language (PL) to another. Recent studies show that even advanced techniques such as large language models (LLMs) still struggle with the task. We introduce InterTrans, an LLM-based automated code translation approach.
  arXiv  Detail & Related papers  (2024-11-01T22:31:32Z)
• Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts [50.40191599304911]
  We investigate whether transliteration is also effective in improving LLMs' performance for low-resource languages written in non-Latin scripts. We propose three prompt templates, where the target-language text is represented in (1) its original script, (2) Latin script, or (3) both. Our findings show that the effectiveness of transliteration varies by task type and model size.
  arXiv  Detail & Related papers  (2024-07-02T14:51:20Z)
• Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment [50.27950279695363]
  The transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method.
  arXiv  Detail & Related papers  (2024-06-28T08:59:24Z)
• TransLLaMa: LLM-based Simultaneous Translation System [18.27477980076409]
  We show that a Decoder-only large language model (LLMs) can control input segmentation directly by generating a special "wait" token. This obviates the need for a separate policy and enables the LLM to perform English-German and English-Russian SiMT tasks. We also evaluated closed-source models such as GPT-4, which displayed encouraging results in performing the SiMT task without prior training.
  arXiv  Detail & Related papers  (2024-02-07T07:39:27Z)
• Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching [9.435669487585917]
  We focus on Maltese, a Semitic language, with substantial influences from Arabic, Italian, and English, and notably written in Latin script. We present a novel dataset annotated with word-level etymology. We show that conditional transliteration based on word etymology yields the best results, surpassing fine-tuning with raw Maltese or Maltese processed with non-selective pipelines.
  arXiv  Detail & Related papers  (2024-01-30T11:04:36Z)
• Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer [92.80671770992572]
  Cross-lingual transfer is a central task in multilingual NLP. Earlier efforts on this task use parallel corpora, bilingual dictionaries, or other annotated alignment data. We propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer.
  arXiv  Detail & Related papers  (2023-09-19T19:30:56Z)
• Romanization-based Large-scale Adaptation of Multilingual Language Models [124.57923286144515]
  Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. We study and compare a plethora of data- and parameter-efficient strategies for adapting the mPLMs to romanized and non-romanized corpora of 14 diverse low-resource languages. Our results reveal that UROMAN-based transliteration can offer strong performance for many languages, with particular gains achieved in the most challenging setups.
  arXiv  Detail & Related papers  (2023-04-18T09:58:34Z)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.