相关论文: Robust Optimization for Multilingual Translation w…

Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of…

Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…

Multilingual language models are widely used to extend NLP systems to low-resource languages. However, concrete evidence for the effects of multilinguality on language modeling performance in individual languages remains scarce. Here, we…

Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…

Despite the recent popularity of Large Language Models (LLMs) in Machine Translation (MT), their performance in low-resource languages (LRLs) still lags significantly behind Neural Machine Translation (NMT) models. In this work, we explore…

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Multilingual machine translation has recently been in vogue given its potential for improving machine translation performance for low-resource languages via transfer learning. Empirical examinations demonstrating the success of existing…

Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…

Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective…

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…

Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setting, where available data is heavily skewed towards…

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…

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data collection for machine learning models for this task is…

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages.…

Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks…

Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However, jointly optimizing all tasks often yields imbalanced learning: agents quickly solve…

Neural Machine Translation models are extremely data and compute-hungry. However, not all data points contribute equally to model training and generalization. Data pruning to remove the low-value data points has the benefit of drastically…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…