Related papers: Morphological Constraints for Phrase Pivot Statist…
Parallel data are an important part of a reliable Statistical Machine Translation (SMT) system. The more of these data are available, the better the quality of the SMT system. However, for some language pairs such as Persian-English,…
Current research in zero-shot translation is plagued by several issues such as high compute requirements, increased training time and off target translations. Proposed remedies often come at the cost of additional data or compute…
Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs,…
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is…
Most languages lack sufficient data for large-scale monolingual pretraining, creating a "data wall." Multilingual pretraining helps but is limited by language imbalance and the "curse of multilinguality." An alternative is to translate…
Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages. Having long been multilingual, the…
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge…
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…
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and…
This paper addresses an important problem in Example-Based Machine Translation (EBMT), namely how to measure similarity between a sentence fragment and a set of stored examples. A new method is proposed that measures similarity according to…
Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…
We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing…
Training code-switched language models is difficult due to lack of data and complexity in the grammatical structure. Linguistic constraint theories have been used for decades to generate artificial code-switching sentences to cope with this…
The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a…
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are…
Despite the tremendous success of Neural Machine Translation (NMT), its performance on low-resource language pairs still remains subpar, partly due to the limited ability to handle previously unseen inputs, i.e., generalization. In this…
While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve…
We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source…
Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements…
Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs.…