相关论文: Gradient-Informed Training for Low-Resource Multil…

Cross-lingual transfer learning is an invaluable tool for overcoming data scarcity, yet selecting a suitable transfer language remains a challenge. The precise roles of linguistic typology, training data, and model architecture in transfer…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on…

Multitask learning is a methodology to boost generalization performance and also reduce computational intensity and memory usage. However, learning multiple tasks simultaneously can be more difficult than learning a single task because it…

We relax the constraint of a shared language between agents in a semantic and goal-oriented communication system to explore the effect of language mismatch in distributed task solving. We propose a mathematical framework, which provides a…

In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between…

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…

The rise of digital misinformation has heightened interest in using multilingual Large Language Models (LLMs) for fact-checking. This study systematically evaluates translation bias and the effectiveness of LLMs for cross-lingual claim…

Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent…

Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…

Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale.…

The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language. In this paper, we propose a novel standpoint to investigate the above issue: using…

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple…

The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems. Fine-tuning a multilingual pre-trained model (e.g., mBART (Liu et al., 2020)) on the translation task is a good…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Natural language processing of Low-Resource Languages (LRL) is often challenged by the lack of data. Therefore, achieving accurate machine translation (MT) in a low-resource environment is a real problem that requires practical solutions.…

Many-to-one neural machine translation systems improve over one-to-one systems when training data is scarce. In this paper, we design and test a novel algorithm for selecting the language of minibatches when training such systems. The…

Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potential in productivity and communication, they overwhelmingly…

Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills…

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

Pre-trained multilingual language models have become an important building block in multilingual natural language processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level…