Related papers: Sequence-to-Sequence Imputation of Missing Sensor …
Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial. Previous works utilize linear interpolation or a fusion network to integrate external language models. However, these approaches…
The advancement of sensing technology has driven the widespread application of high-dimensional data. However, issues such as missing entries during acquisition and transmission negatively impact the accuracy of subsequent tasks. Tensor…
Despite being virtually ubiquitous, sequence-to-sequence models are challenged by their lack of diversity and inability to be externally controlled. In this paper, we speculate that a fundamental shortcoming of sequence generation models is…
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the…
We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual representations, which we apply to text recognition. To account for the sequence-to-sequence structure, each feature map is divided into different…
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…
Predictive learning uses a known state to generate a future state over a period of time. It is a challenging task to predict spatiotemporal sequence because the spatiotemporal sequence varies both in time and space. The mainstream method is…
The primary paradigm in Neural Combinatorial Optimization (NCO) are construction methods, where a neural network is trained to sequentially add one solution component at a time until a complete solution is constructed. We observe that the…
Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…
This study proposes an unsupervised sequence-to-sequence learning approach that automatically assesses the motion-induced reliability degradation of the cardiac volume signal (CVS) in multi-channel electrical impedance-based hemodynamic…
Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…
In the upcoming years, artificial intelligence (AI) is going to transform the practice of medicine in most of its specialties. Deep learning can help achieve better and earlier problem detection, while reducing errors on diagnosis. By…
In-flight sensor fault diagnosis and recursive combination of residual signals via the Dempster-Shafer (DS) theory have been considered in this study. In particular, a novel evidence-based combination rule of residual errors as a function…
Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose…
Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i)…
We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…
Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the success of BERT, we…
The vanilla sequence-to-sequence learning (seq2seq) reads and encodes a source sequence into a fixed-length vector only once, suffering from its insufficiency in modeling structural correspondence between the source and target sequence.…
Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the…
We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a…