Related papers: Bridging the Gap between Training and Inference fo…

In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source…

Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if…

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and…

In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English. This is considered as the multimodal image caption…

Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks…

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though…

Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its…

Standard context-aware neural machine translation (NMT) typically relies on parallel document-level data, exploiting both source and target contexts. Concatenation-based approaches in particular, still a strong baseline for document-level…

One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective method for recalling previously seen…

This paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. The generator aims to generate sentences…

Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on…

Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation…

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first…

Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…

A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather". The meaning of these expressions is not composed by the meaning of their constituent words, and NMT models…

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus…

The recently proposed neural network joint model (NNJM) (Devlin et al., 2014) augments the n-gram target language model with a heuristically chosen source context window, achieving state-of-the-art performance in SMT. In this paper, we give…

In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This…

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach,…

The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen…