Related papers: Effective Strategies in Zero-Shot Neural Machine T…
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…
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…
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…
Although the multilingual Neural Machine Translation(NMT), which extends Google's multilingual NMT, has ability to perform zero-shot translation and the iterative self-learning algorithm can improve the quality of zero-shot translation, it…
Recently, end-to-end speech translation (ST) has gained significant attention as it avoids error propagation. However, the approach suffers from data scarcity. It heavily depends on direct ST data and is less efficient in making use of…
The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translation. Neural interlingua representations have been shown as an…
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a…
Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation…
An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or…
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We…
Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…
While multilingual neural machine translation has achieved great success, it suffers from the off-target issue, where the translation is in the wrong language. This problem is more pronounced on zero-shot translation tasks. In this work, we…
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…
Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…
Neural machine translation requires large amounts of parallel training text to learn a reasonable-quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is not available. In this…
In this work, we show a novel method for neural machine translation (NMT), using a denoising diffusion probabilistic model (DDPM), adjusted for textual data, following recent advances in the field. We show that it's possible to translate…
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…
Zero-resource cross-lingual transfer approaches aim to apply supervised models from a source language to unlabelled target languages. In this paper we perform an in-depth study of the two main techniques employed so far for cross-lingual…
Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often…
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.…