Related papers: CUNI systems for WMT21: Multilingual Low-Resource …
Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility. However, NMT still struggles to translate properly in low-resource settings specifically on distant…
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can further…
Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat translation). Although the dataset-specific models have achieved…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
We describe our NMT systems submitted to the WMT19 shared task in English-Czech news translation. Our systems are based on the Transformer model implemented in either Tensor2Tensor (T2T) or Marian framework. We aimed at improving the…
Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal…
Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…
In this paper, we present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our systems employ the framework of UniTE, which combined three…
An effective method to improve extremely low-resource neural machine translation is multilingual training, which can be improved by leveraging monolingual data to create synthetic bilingual corpora using the back-translation method. This…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
The 2019 WMT Biomedical translation task involved translating Medline abstracts. We approached this using transfer learning to obtain a series of strong neural models on distinct domains, and combining them into multi-domain ensembles. We…
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages;…
The rapid advancement of Large Language Models (LLMs) has transformed various domains, particularly computer science (CS) education. These models exhibit remarkable capabilities in code-related tasks and problem-solving, raising questions…
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently…
Transformers have achieved great success in machine translation, but transformer-based NMT models often require millions of bilingual parallel corpus for training. In this paper, we propose a novel architecture named as attention link (AL)…
In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically…
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…
Low-resource languages, such as Baltic languages, benefit from Large Multilingual Models (LMs) that possess remarkable cross-lingual transfer performance capabilities. This work is an interpretation and analysis study into cross-lingual…
Recent studies have suggested that large language models (LLMs) underperform on mathematical and computer science tasks when these problems are translated from Romanian into English, compared to their original Romanian format. Accurate…