Related papers: One For All & All For One: Bypassing Hyperparamete…

Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning. However, due to the mixture of multilingual data during the pre-training of LLM, the…

Multilingual pretrained language models (MPLMs) have demonstrated substantial performance improvements in zero-shot cross-lingual transfer across various natural language understanding tasks by finetuning MPLMs on task-specific labelled…

Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks. However, existing approaches essentially capture the co-occurrence among…

We study several methods for full or partial sharing of the decoder parameters of multilingual NMT models. We evaluate both fully supervised and zero-shot translation performance in 110 unique translation directions using only the WMT 2019…

In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language. While most prior work has used a single source model or a few carefully selected models, here we consider a `massive'…

Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on…

In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. We assume a strict setting with no access to…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method…

Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Nevertheless, in this work,…

Translation Quality Estimation (QE) is the task of predicting the quality of machine translation (MT) output without any reference. This task has gained increasing attention as an important component in the practical applications of MT. In…

Cross-language entity linking grounds mentions in multiple languages to a single-language knowledge base. We propose a neural ranking architecture for this task that uses multilingual BERT representations of the mention and the context in a…

While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve…

The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised…

Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We…

Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…

This study examines the cross-linguistic effectiveness of transfer learning for low-resource machine translation by fine-tuning models initially trained on typologically similar high-resource languages, using limited data from the target…

Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra…

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…