Related papers: Robust Machine Translation with Domain Sensitive P…
Neural machine translation (MT) models achieve strong results across a variety of settings, but it is widely believed that they are highly sensitive to "noisy" inputs, such as spelling errors, abbreviations, and other formatting issues. In…
An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…
It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large…
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…
Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are…
Modern Machine Translation (MT) systems perform consistently well on clean, in-domain text. However most human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can…
Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domains. To address this…
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this…
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world…
While NMT has achieved remarkable results in the last 5 years, production systems come with strict quality requirements in arbitrarily niche domains that are not always adequately covered by readily available parallel corpora. This is…
In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level…
Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to…
We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model…
This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong…
In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue…
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…
We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning…
Multimodal neural machine translation (NMT) has become an increasingly important area of research over the years because additional modalities, such as image data, can provide more context to textual data. Furthermore, the viability of…
In this paper we describe the CUNI translation system used for the unsupervised news shared task of the ACL 2019 Fourth Conference on Machine Translation (WMT19). We follow the strategy of Artexte et al. (2018b), creating a seed…
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…