Related papers: Joint Training for Neural Machine Translation Mode…
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all…
The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture…
With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However,…
Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we…
We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained…
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…
Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an…
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this…
We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the…
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…
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…
Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT),…
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised…
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel…
Machine translation (MT) involving Indigenous languages, including those possibly endangered, is challenging due to lack of sufficient parallel data. We describe an approach exploiting bilingual and multilingual pretrained MT models in a…
Multilingual neural machine translation (NMT), which translates multiple languages using a single model, is of great practical importance due to its advantages in simplifying the training process, reducing online maintenance costs, and…
Back translation, as a technique for extending a dataset, is widely used by researchers in low-resource language translation tasks. It typically translates from the target to the source language to ensure high-quality translation results.…
As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge. In this paper, we propose and explore three…