Related papers: Multilingual Multi-Domain Adaptation Approaches fo…

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

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…

Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena. Many works have been published…

Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. In this paper, we propose a non-tuning paradigm, resolving…

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse…

Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left to right, without considering the right context. This paper…

Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving. However, traditional multilingual translation usually…

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…

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…

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate…

Massively multilingual pre-trained language models (MMPLMs) are developed in recent years demonstrating superpowers and the pre-knowledge they acquire for downstream tasks. This work investigates whether MMPLMs can be applied to clinical…

Neural machine translation (NMT) systems require large amounts of high quality in-domain parallel corpora for training. State-of-the-art NMT systems still face challenges related to out-of-vocabulary words and dealing with low-resource…

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…

We introduce a Multi-modal Neural Machine Translation model in which a doubly-attentive decoder naturally incorporates spatial visual features obtained using pre-trained convolutional neural networks, bridging the gap between image…

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…