Related papers: Utilizing Lexical Similarity between Related, Low-…

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…

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…

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless,…

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word…

State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are…

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo,…

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…

Large language models (LLMs) demonstrate remarkable ability in cross-lingual tasks. Understanding how LLMs acquire this ability is crucial for their interpretability. To quantify the cross-lingual ability of LLMs accurately, we propose a…

In this paper, we introduce a novel approach to generate synthetic data for training Neural Machine Translation systems. The proposed approach transforms a given parallel corpus between a written language and a target language to a parallel…

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

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…

Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream applications, from modernizing large legacy codebases to augmenting data for low-resource…

Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our…

Multilingual machine translation addresses the task of translating between multiple source and target languages. We propose task-specific attention models, a simple but effective technique for improving the quality of sequence-to-sequence…

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In…

Multilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cross-lingual supervision, transfer performance can further be…