Cross-modality Data Augmentation for End-to-End Sign Language Translation

• URL: http://arxiv.org/abs/2305.11096v4
• Date: Tue, 4 Jun 2024 08:27:40 GMT
• Title: Cross-modality Data Augmentation for End-to-End Sign Language Translation
• Authors: Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Hui Xiong,
• Abstract summary: End-to-end sign language translation (SLT) aims to convert sign language videos into spoken language texts directly without intermediate representations. It has been a challenging task due to the modality gap between sign videos and texts and the data scarcity of labeled data. We propose a novel Cross-modality Data Augmentation (XmDA) framework to transfer the powerful gloss-to-text translation capabilities to end-to-end sign language translation.
• Score: 66.46877279084083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end sign language translation (SLT) aims to convert sign language videos into spoken language texts directly without intermediate representations. It has been a challenging task due to the modality gap between sign videos and texts and the data scarcity of labeled data. Due to these challenges, the input and output distributions of end-to-end sign language translation (i.e., video-to-text) are less effective compared to the gloss-to-text approach (i.e., text-to-text). To tackle these challenges, we propose a novel Cross-modality Data Augmentation (XmDA) framework to transfer the powerful gloss-to-text translation capabilities to end-to-end sign language translation (i.e. video-to-text) by exploiting pseudo gloss-text pairs from the sign gloss translation model. Specifically, XmDA consists of two key components, namely, cross-modality mix-up and cross-modality knowledge distillation. The former explicitly encourages the alignment between sign video features and gloss embeddings to bridge the modality gap. The latter utilizes the generation knowledge from gloss-to-text teacher models to guide the spoken language text generation. Experimental results on two widely used SLT datasets, i.e., PHOENIX-2014T and CSL-Daily, demonstrate that the proposed XmDA framework significantly and consistently outperforms the baseline models. Extensive analyses confirm our claim that XmDA enhances spoken language text generation by reducing the representation distance between videos and texts, as well as improving the processing of low-frequency words and long sentences.

Related papers

• Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing [21.183453511034767]
  We propose several advances by leveraging pre-trained large language models (LLMs), data augmentation, and novel label-smoothing loss function. Our approach surpasses state-of-the-art performance in em Gloss2Text translation.
  arXiv  Detail & Related papers  (2024-07-01T15:46:45Z)
• Is context all you need? Scaling Neural Sign Language Translation to Large Domains of Discourse [34.70927441846784]
  Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. We propose a novel multi-modal transformer architecture that tackles the translation task in a context-aware manner, as a human would. We report significant improvements on state-of-the-art translation performance using contextual information, nearly doubling the reported BLEU-4 scores of baseline approaches.
  arXiv  Detail & Related papers  (2023-08-18T15:27:22Z)
• Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining [56.26550923909137]
  Gloss-Free Sign Language Translation (SLT) is a challenging task due to its cross-domain nature. We propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-) Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual and Text Decoder from
  arXiv  Detail & Related papers  (2023-07-27T10:59:18Z)
• SLTUNET: A Simple Unified Model for Sign Language Translation [40.93099095994472]
  We propose a simple unified neural model designed to support multiple sign-to-gloss, gloss-to-text and sign-to-text translation tasks. Jointly modeling different tasks endows SLTUNET with the capability to explore the cross-task relatedness that could help narrow the modality gap. We show in experiments that SLTUNET achieves competitive and even state-of-the-art performance on ENIX-2014T and CSL-Daily.
  arXiv  Detail & Related papers  (2023-05-02T20:41:59Z)
• Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation [36.40377483258876]
  Sign language gloss translation aims to translate the sign glosses into spoken language texts. Back translation (BT) generates pseudo-parallel data by translating in-domain spoken language texts into sign glosses. We propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale spoken language text data.
  arXiv  Detail & Related papers  (2022-10-13T14:25:08Z)
• A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation [54.29679610921429]
  Existing sign language datasets contain only about 10K-20K pairs of sign videos, gloss annotations and texts. Data is thus a bottleneck for training effective sign language translation models. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks.
  arXiv  Detail & Related papers  (2022-03-08T18:59:56Z)
• SimulSLT: End-to-End Simultaneous Sign Language Translation [55.54237194555432]
  Existing sign language translation methods need to read all the videos before starting the translation. We propose SimulSLT, the first end-to-end simultaneous sign language translation model. SimulSLT achieves BLEU scores that exceed the latest end-to-end non-simultaneous sign language translation model.
  arXiv  Detail & Related papers  (2021-12-08T11:04:52Z)
• Improving Sign Language Translation with Monolingual Data by Sign Back-Translation [105.83166521438463]
  We propose a sign back-translation (SignBT) approach, which incorporates massive spoken language texts into sign training. With a text-to-gloss translation model, we first back-translate the monolingual text to its gloss sequence. Then, the paired sign sequence is generated by splicing pieces from an estimated gloss-to-sign bank at the feature level.
  arXiv  Detail & Related papers  (2021-05-26T08:49:30Z)
• Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation [59.38247587308604]
  We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation. We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T dataset. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models.
  arXiv  Detail & Related papers  (2020-03-30T21:35:09Z)

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.