Related papers: ConECT Dataset: Overcoming Data Scarcity in Contex…
We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions. Since human A/B testing is commonly used, we assume commercial systems improve over time, which enables us…
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a…
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…
In-Image Machine Translation (IIMT) powers cross-border e-commerce product listings; existing research focuses on machine translation evaluation, while visual rendering quality is critical for user engagement. When facing context-dense…
While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data. Recent efforts have tried to…
While some remarkable progress has been made in neural machine translation (NMT) research, there have not been many reports on its development and evaluation in practice. This paper tries to fill this gap by presenting some of our findings…
E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent modelling, yet there is…
In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…
Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation…
Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be…
This paper investigates the development and evaluation of machine translation models from Cantonese to English, where we propose a novel approach to tackle low-resource language translations. The main objectives of the study are to develop…
The advent of context-aware NMT has resulted in promising improvements in the overall translation quality and specifically in the translation of discourse phenomena such as pronouns. Previous works have mainly focused on the use of past…
Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated without context from outside the sentence. Specifically, we…
It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation…
Starting from the 1950s, Machine Translation (MT) was challenged by different scientific solutions, which included rule-based methods, example-based and statistical models (SMT), to hybrid models, and very recent years the neural models…
Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…
We test the natural expectation that using MT in professional translation saves human processing time. The last such study was carried out by Sanchez-Torron and Koehn (2016) with phrase-based MT, artificially reducing the translation…
Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap…