LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language
- URL: http://arxiv.org/abs/2405.07745v1
- Date: Mon, 13 May 2024 13:41:59 GMT
- Title: LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language
- Authors: Cagri Toraman,
- Abstract summary: This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages.
We assess various strategies, including continual training, instruction fine-tuning, task-specific fine-tuning, and vocabulary extension.
The results show that continual training improves language comprehension, as reflected in perplexity scores, and task-specific tuning generally enhances performance of downstream tasks.
- Score: 2.9914612342004503
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and multilingual pretraining. Monolingual pretraining is expensive due to hardware requirements, and multilingual models often have uneven performance across languages. This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, instruction fine-tuning, task-specific fine-tuning, and vocabulary extension. The results show that continual training improves language comprehension, as reflected in perplexity scores, and task-specific tuning generally enhances performance of downstream tasks. However, extending the vocabulary shows no substantial benefits. Additionally, while larger models improve task performance with few-shot tuning, multilingual models perform worse than their monolingual counterparts when adapted.
Related papers
- Targeted Multilingual Adaptation for Low-resource Language Families [17.212424929235624]
We study best practices for adapting a pre-trained model to a language family.
Our adapted models significantly outperform mono- and multilingual baselines.
Low-resource languages can be aggressively up-sampled during training at little detriment to performance in high-resource languages.
arXiv Detail & Related papers (2024-05-20T23:38:06Z) - When Is Multilinguality a Curse? Language Modeling for 250 High- and
Low-Resource Languages [25.52470575274251]
We pre-train over 10,000 monolingual and multilingual language models for over 250 languages.
We find that in moderation, adding multilingual data improves low-resource language modeling performance.
As dataset sizes increase, adding multilingual data begins to hurt performance for both low-resource and high-resource languages.
arXiv Detail & Related papers (2023-11-15T18:47:42Z) - The Less the Merrier? Investigating Language Representation in
Multilingual Models [8.632506864465501]
We investigate the linguistic representation of different languages in multilingual models.
We observe from our experiments that community-centered models perform better at distinguishing between languages in the same family for low-resource languages.
arXiv Detail & Related papers (2023-10-20T02:26:34Z) - Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
arXiv Detail & Related papers (2023-06-13T08:08:08Z) - Language-Family Adapters for Low-Resource Multilingual Neural Machine
Translation [129.99918589405675]
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks.
Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive.
We propose training language-family adapters on top of mBART-50 to facilitate cross-lingual transfer.
arXiv Detail & Related papers (2022-09-30T05:02:42Z) - Lifting the Curse of Multilinguality by Pre-training Modular
Transformers [72.46919537293068]
multilingual pre-trained models suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages.
We introduce language-specific modules, which allows us to grow the total capacity of the model, while keeping the total number of trainable parameters per language constant.
Our approach enables adding languages post-hoc with no measurable drop in performance, no longer limiting the model usage to the set of pre-trained languages.
arXiv Detail & Related papers (2022-05-12T17:59:56Z) - Specializing Multilingual Language Models: An Empirical Study [50.7526245872855]
Contextualized word representations from pretrained multilingual language models have become the de facto standard for addressing natural language tasks.
For languages rarely or never seen by these models, directly using such models often results in suboptimal representation or use of data.
arXiv Detail & Related papers (2021-06-16T18:13:55Z) - UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks.
Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages.
We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
arXiv Detail & Related papers (2020-12-31T11:37:28Z) - When Being Unseen from mBERT is just the Beginning: Handling New
Languages With Multilingual Language Models [2.457872341625575]
Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP.
We show that such models behave in multiple ways on unseen languages.
arXiv Detail & Related papers (2020-10-24T10:15:03Z) - Learning to Scale Multilingual Representations for Vision-Language Tasks [51.27839182889422]
The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date.
We evaluate on multilingual image-sentence retrieval and outperform prior work by 3-4% with less than 1/5th the training parameters compared to other word embedding methods.
arXiv Detail & Related papers (2020-04-09T01:03:44Z)
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.