Related papers: Can Latent Alignments Improve Autoregressive Machi…
Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their abilities are…
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training…
The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional target-side monolingual data, can help improve translation…
Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…
Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…
We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel,…
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…
Non-autoregressive Transformers (NATs) reduce the inference latency of Autoregressive Transformers (ATs) by predicting words all at once rather than in sequential order. They have achieved remarkable progress in machine translation as well…
Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the…
An all-too-present bottleneck for text classification model development is the need to annotate training data and this need is multiplied for multilingual classifiers. Fortunately, contemporary machine translation models are both easily…
Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood…
Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping…
Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the former. Despite promising results, Seq2Edit approaches still…
Non-autoregressive neural machine translation (NAT) offers substantial translation speed up compared to autoregressive neural machine translation (AT) at the cost of translation quality. Latent variable modeling has emerged as a promising…
Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share model structure and AT is an easier task than NAT due to the…
Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build…
Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem…
Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest in non-autoregressive (NAR) models, which promise faster…
Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with…