Related papers: Fill in the Blanks: Imputing Missing Sentences for…
Despite the remarkable advancements in machine translation, the current sentence-level paradigm faces challenges when dealing with highly-contextual languages like Japanese. In this paper, we explore how context-awareness can improve the…
In recent years, several studies on neural machine translation (NMT) have attempted to use document-level context by using a multi-encoder and two attention mechanisms to read the current and previous sentences to incorporate the context of…
Self-supervised large language models have demonstrated the ability to perform Machine Translation (MT) via in-context learning, but little is known about where the model performs the task with respect to prompt instructions and…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation…
This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resource language as part of an automated machine translation…
Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…
Low-resource languages pose a challenge for machine translation with large language models (LLMs), which require large amounts of training data. One potential way to circumvent this data dependence is to rely on LLMs' ability to use…
A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the…
Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…
Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context…
Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation…
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its…
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation,…
Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pairs can boost…
This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…
This paper addresses the task of contextual translation using multi-segment models. Specifically we show that increasing model capacity further pushes the limits of this approach and that deeper models are more suited to capture context…
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural…
In recent years, the sequence-to-sequence learning neural networks with attention mechanism have achieved great progress. However, there are still challenges, especially for Neural Machine Translation (NMT), such as lower translation…
Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed contextual drag: the presence of failed attempts in the…