Related papers: Unsupervised Paraphrasing without Translation
While a source sentence can be translated in many ways, most machine translation (MT) models are trained with only a single reference. Previous work has shown that using synthetic paraphrases can improve MT. This paper investigates best…
Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…
Neural networks are capable of translating between languages -- in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation (UMT). Given this…
Cross-lingual word embeddings aim to capture common linguistic regularities of different languages, which benefit various downstream tasks ranging from machine translation to transfer learning. Recently, it has been shown that these…
Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and…
Paraphrases, the rewordings of the same semantic meaning, are useful for improving generalization and translation. However, prior works only explore paraphrases at the word or phrase level, not at the sentence or corpus level. Unlike…
Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT…
Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple `direct transfer' of a learned model based on a multilingual input encoding has provided a strong benchmark.…
Back-translation based approaches have recently lead to significant progress in unsupervised sequence-to-sequence tasks such as machine translation or style transfer. In this work, we extend the paradigm to the problem of learning a…
Traditionally, Machine Translation (MT) Evaluation has been treated as a regression problem -- producing an absolute translation-quality score. This approach has two limitations: i) the scores lack interpretability, and human annotators…
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for…
Metaphorical expressions are difficult linguistic phenomena, challenging diverse Natural Language Processing tasks. Previous works showed that paraphrasing a metaphor as its literal counterpart can help machines better process metaphors on…
Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e models are trained on sentences with their translations and accompanying images). However, this type of data is costly to collect, limiting the…
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to incorporate a new…
This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation. We discuss how the data size affects the performance…
Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms.…
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…
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via…
Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these methods require…