Related papers: Rephrasing the Reference for Non-Autoregressive Ma…
Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's prediction, instead of its own previous predictions. In order to…
Autoregressive sequence Generation models have achieved state-of-the-art performance in areas like machine translation and image captioning. These models are autoregressive in that they generate each word by conditioning on previously…
End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…
Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…
The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional…
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the…
In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translation model, to…
Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic…
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…
Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though…
Retrieval-Augmented Machine Translation (RAMT) is attracting growing attention. This is because RAMT not only improves translation metrics, but is also assumed to implement some form of domain adaptation. In this contribution, we study…
Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through…
We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class…
Autoregressive (AR) models have been the dominating approach to conditional sequence generation, but are suffering from the issue of high inference latency. Non-autoregressive (NAR) models have been recently proposed to reduce the latency…
This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…
This paper proposes and evaluates the hybrid autoregressive transducer (HAT) model, a time-synchronous encoderdecoder model that preserves the modularity of conventional automatic speech recognition systems. The HAT model provides a way to…
Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance…
Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…
Neural machine translation (NMT) systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring inter-sentence information. This may make the translation of a sentence ambiguous or…
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…