Related papers: Evaluating the Supervised and Zero-shot Performanc…
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of…
Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…
Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural)…
In this paper, we investigate whether multilingual neural translation models learn stronger semantic abstractions of sentences than bilingual ones. We test this hypotheses by measuring the perplexity of such models when applied to…
Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decoding from left to right and the other decoding in the opposite…
Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to…
Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradation on rich-resource language pairs. We attribute this…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…
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…
In this paper, we present an extensive investigation of multi-bridge, many-to-many multilingual NMT models (MB-M2M) ie., models trained on non-English language pairs in addition to English-centric language pairs. In addition to validating…
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading…
Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance.…
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly understood, and their mode of transfer remains elusive. In this…
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.…
Neural machine translation (NMT) systems typically employ maximum a posteriori (MAP) decoding to select the highest-scoring translation from the distribution mass. However, recent evidence highlights the inadequacy of MAP decoding, often…
In state-of-the-art Neural Machine Translation (NMT), an attention mechanism is used during decoding to enhance the translation. At every step, the decoder uses this mechanism to focus on different parts of the source sentence to gather the…
Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages…
With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point of research. Despite the commendable performance of general models such as the Transformer in various…