Related papers: Utilizing Lexical Similarity between Related, Low-…
Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations. This paper studies the role of subword segmentation in cross-lingual transfer. We systematically compare the…
Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…
Machine translation (MT) for low-resource languages such as Ge'ez, an ancient language that is no longer the native language of any community, faces challenges such as out-of-vocabulary words, domain mismatches, and lack of sufficient…
Using top-ranked documents in response to a query has been shown to be an effective approach to improve the quality of query translation in dictionary-based cross-language information retrieval. In this paper, we propose a new method for…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising results. However, there…
We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages. The specifically designed…
Based on multilingual pre-trained models, cross-lingual transfer with prompt learning has shown promising effectiveness, where soft prompt learned in a source language is transferred to target languages for downstream tasks, particularly in…
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for…
Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom…
Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language similarity in this…
The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…
In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This…
We propose an approach to build a neural machine translation system with no supervised resources (i.e., no parallel corpora) using multimodal embedded representation over texts and images. Based on the assumption that text documents are…
The primary objective of simultaneous machine translation (SiMT) is to minimize latency while preserving the quality of the final translation. Drawing inspiration from CPU branch prediction techniques, we propose incorporating branch…
The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…
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…