Related papers: End-to-End Training for Back-Translation with Cate…

We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence…

Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences.…

We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial…

Non-autoregressive models generate target words in a parallel way, which achieve a faster decoding speed but at the sacrifice of translation accuracy. To remedy a flawed translation by non-autoregressive models, a promising approach is to…

Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency. Non-AutoRegressive Translation…

Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translation (BT) or forward translation (FT, or selftraining), into…

In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling…

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…

The rapid expansion of English technical terminology presents a significant challenge to traditional expert-based standardization, particularly in rapidly developing areas such as artificial intelligence and quantum computing. Manual…

A neural machine translation (NMT) system is expensive to train, especially with high-resource settings. As the NMT architectures become deeper and wider, this issue gets worse and worse. In this paper, we aim to improve the efficiency of…

Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from…

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright…

Direct neural machine translation (direct NMT) is a type of NMT system that translates text between two non-English languages. Direct NMT systems often face limitations due to the scarcity of parallel data between non-English language…

Neural machine translation (NMT) is sensitive to domain shift. In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained…

A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have…

We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…

While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual…

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Recent advances, such as GPT and BERT, have shown success in incorporating a pre-trained transformer language model and fine-tuning operation to improve downstream NLP systems. However, this framework still has some fundamental problems in…