Posted Content•
OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
TL;DR: OpenHands as mentioned in this paper uses pose extracted through pretrained models as the standard modality of data to reduce training time and enable efficient inference, and provides standardized pose datasets for 6 sign languages - American, Argentinian, Chinese, Greek, Indian, and Turkish.
Abstract: AI technologies for Natural Languages have made tremendous progress recently.
However, commensurate progress has not been made on Sign Languages, in
particular, in recognizing signs as individual words or as complete sentences.
We introduce OpenHands, a library where we take four key ideas from the NLP
community for low-resource languages and apply them to sign languages for
word-level recognition. First, we propose using pose extracted through
pretrained models as the standard modality of data to reduce training time and
enable efficient inference, and we release standardized pose datasets for 6
different sign languages - American, Argentinian, Chinese, Greek, Indian, and
Turkish. Second, we train and release checkpoints of 4 pose-based isolated sign
language recognition models across all 6 languages, providing baselines and
ready checkpoints for deployment. Third, to address the lack of labelled data,
we propose self-supervised pretraining on unlabelled data. We curate and
release the largest pose-based pretraining dataset on Indian Sign Language
(Indian-SL). Fourth, we compare different pretraining strategies and for the
first time establish that pretraining is effective for sign language
recognition by demonstrating (a) improved fine-tuning performance especially in
low-resource settings, and (b) high crosslingual transfer from Indian-SL to few
other sign languages. We open-source all models and datasets in OpenHands with
a hope that it makes research in sign languages more accessible, available here
at https://github.com/AI4Bharat/OpenHands .
Citations
More filters
04 Jun 2023
TL;DR: In this article , a deep learning framework that leverages multi-modal appearance and skeleton-based information was proposed for automatic sign language recognition (SLR) from RGB video, where a modified version of ResNet2+1D network was used to capture appearance information, where spatial and temporal convolutions were substituted by their deformable counterparts.
Abstract: Automatic sign language recognition (SLR) remains challenging, especially when employing RGB video alone (i.e., with no depth or special glove-based input) and under a signer-independent (SI) framework, due to inter-personal signing variation. In this paper, we address SI isolated SLR from RGB video, proposing an innovative deep-learning framework that leverages multi-modal appearanceand skeleton-based information. Specifically, we propose three components for the first time in SLR: (i) a modified version of the ResNet2+1D network to capture signing appearance information, where spatial and temporal convolutions are substituted by their deformable counterparts, accomplishing both prevalent spatial modeling potential and motion-aware modeling adaptability; (ii) a novel spatio-temporal graph convolutional network (ST-GCN) that integrates a GCN variant, involving weight and affinity modulation for modeling diverse correlations between different body joints beyond the physical human skeleton structure, followed by a self-attention layer and a temporal convolution; and (iii) the “PIXIE” 3D human pose and shape regressor to generate 3D joint-rotation parameterization used for ST-GCN graph construction. Both appearance- and skeleton-based streams are ensembled in the proposed system and evaluated on two datasets of isolated signs, one in Turkish and one in Greek. Our system outperforms the state-of-the-art on the second set, yielding 53% relative error rate reduction (2.45% absolute), while it performs on par with the best reported system on the first.
1 citations
References
More filters
Posted Content•
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Abstract: We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications.
BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).
29,480 citations
Posted Content•
TL;DR: In this paper, the Skip-gram model is used to learn high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships and improve both the quality of the vectors and the training speed.
Abstract: The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indifference to word order and their inability to represent idiomatic phrases. For example, the meanings of "Canada" and "Air" cannot be easily combined to obtain "Air Canada". Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.
11,343 citations
Posted Content•
TL;DR: A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
7,019 citations
Posted Content•
TL;DR: This work proposes a universal unsupervised learning approach to extract useful representations from high-dimensional data, which it calls Contrastive Predictive Coding, and demonstrates that the approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
Abstract: While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations from high-dimensional data, which we call Contrastive Predictive Coding. The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models. We use a probabilistic contrastive loss which induces the latent space to capture information that is maximally useful to predict future samples. It also makes the model tractable by using negative sampling. While most prior work has focused on evaluating representations for a particular modality, we demonstrate that our approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
5,444 citations
Proceedings Article•
20 Jun 2020TL;DR: It is shown for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.
Abstract: We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data.
2,186 citations