EMMeTT: Efficient Multimodal Machine Translation Training

• URL: http://arxiv.org/abs/2409.13523v1
• Date: Fri, 20 Sep 2024 14:03:23 GMT
• Title: EMMeTT: Efficient Multimodal Machine Translation Training
• Authors: Piotr Żelasko, Zhehuai Chen, Mengru Wang, Daniel Galvez, Oleksii Hrinchuk, Shuoyang Ding, Ke Hu, Jagadeesh Balam, Vitaly Lavrukhin, Boris Ginsburg,
• Abstract summary: We propose a joint multimodal training regime of Speech-LLM to include automatic speech translation (AST) To handle joint multimodal training, we propose a novel training framework called EMMeTT. The resultant Multimodal Translation Model produces strong text and speech translation results at the same time.
• Score: 26.295981183965566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint multimodal training regime of Speech-LLM to include automatic speech translation (AST). We investigate two different foundation model architectures, decoder-only GPT and encoder-decoder T5, extended with Canary-1B's speech encoder. To handle joint multimodal training, we propose a novel training framework called EMMeTT. EMMeTT improves training efficiency with the following: balanced sampling across languages, datasets, and modalities; efficient sequential data iteration; and a novel 2D bucketing scheme for multimodal data, complemented by a batch size optimizer (OOMptimizer). We show that a multimodal training consistently helps with both architectures. Moreover, SALM-T5 trained with EMMeTT retains the original NMT capability while outperforming AST baselines on four-language subsets of FLORES and FLEURS. The resultant Multimodal Translation Model produces strong text and speech translation results at the same time.

Related papers

• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing [17.92378239787507]
  We present a decoder-only Discrete Multimodal Language Model (DMLM) DMLM can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision) Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training.
  arXiv  Detail & Related papers  (2024-06-04T20:08:25Z)
• TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages [96.8603701943286]
  Tri-Modal Translation (TMT) model translates between arbitrary modalities spanning speech, image, and text. We tokenize speech and image data into discrete tokens, which provide a unified interface across modalities. TMT outperforms single model counterparts consistently.
  arXiv  Detail & Related papers  (2024-02-25T07:46:57Z)
• AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling [115.89786751297348]
  We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities. We build a multimodal text-centric dataset for multimodal alignment pre-training. We show that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities.
  arXiv  Detail & Related papers  (2024-02-19T15:33:10Z)
• CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation [31.911593690549633]
  multimodal machine translation (MMT) systems enhance neural machine translation (NMT) with visual knowledge. Previous works face a challenge in training powerful MMT models from scratch due to the scarcity of annotated multilingual vision-language data. We propose CLIPTrans, which simply adapts the independently pre-trained multimodal M-CLIP and the multilingual mBART.
  arXiv  Detail & Related papers  (2023-08-29T11:29:43Z)
• Multilingual Multimodal Learning with Machine Translated Text [27.7207234512674]
  We investigate whether machine translating English multimodal data can be an effective proxy for the lack of readily available multilingual data. We propose two metrics for automatically removing such translations from the resulting datasets. In experiments on five tasks across 20 languages in the IGLUE benchmark, we show that translated data can provide a useful signal for multilingual multimodal learning.
  arXiv  Detail & Related papers  (2022-10-24T11:41:20Z)
• Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation [74.158365847236]
  SixT++ is a strong many-to-English NMT model that supports 100 source languages but is trained once with a parallel dataset from only six source languages. It significantly outperforms CRISS and m2m-100, two strong multilingual NMT systems, with an average gain of 7.2 and 5.0 BLEU respectively.
  arXiv  Detail & Related papers  (2021-10-16T10:59:39Z)
• Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders [74.89326277221072]
  How to improve the cross-lingual transfer of NMT model with multilingual pretrained encoder is under-explored. We propose SixT, a simple yet effective model for this task. Our model achieves better performance on many-to-English testsets than CRISS and m2m-100.
  arXiv  Detail & Related papers  (2021-04-18T07:42:45Z)
• Multi-task Learning for Multilingual Neural Machine Translation [32.81785430242313]
  We propose a multi-task learning framework that jointly trains the model with the translation task on bitext data and two denoising tasks on the monolingual data. We show that the proposed approach can effectively improve the translation quality for both high-resource and low-resource languages.
  arXiv  Detail & Related papers  (2020-10-06T06:54:12Z)
• InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining [76.32065400614162]
  We propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6. The model owns strong capability of modeling interaction between the information flows of different modalities. We propose a large-scale dataset for multi-modal pretraining in Chinese, and we develop the Chinese InterBERT which is the first Chinese multi-modal pretrained model.
  arXiv  Detail & Related papers  (2020-03-30T03:13:22Z)

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.