Grammatical error correction: A survey of the state of the art

C Bryant, Z Yuan, MR Qorib, H Cao, HT Ng… - Computational …, 2023 - direct.mit.edu
Abstract Grammatical Error Correction (GEC) is the task of automatically detecting and
correcting errors in text. The task not only includes the correction of grammatical errors, such …

Neural machine translation: A review

F Stahlberg - Journal of Artificial Intelligence Research, 2020 - jair.org
The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

Imagen editor and editbench: Advancing and evaluating text-guided image inpainting

S Wang, C Saharia, C Montgomery… - Proceedings of the …, 2023 - openaccess.thecvf.com
Text-guided image editing can have a transformative impact in supporting creative
applications. A key challenge is to generate edits that are faithful to the input text prompt …

COMET: A neural framework for MT evaluation

R Rei, C Stewart, AC Farinha, A Lavie - arxiv preprint arxiv:2009.09025, 2020 - arxiv.org
We present COMET, a neural framework for training multilingual machine translation
evaluation models which obtains new state-of-the-art levels of correlation with human …

Findings of the 2017 conference on machine translation (wmt17)

O Bojar, R Chatterjee, C Federmann, Y Graham… - 2017 - doras.dcu.ie
This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …

Findings of the 2021 conference on machine translation (WMT21)

F Akhbardeh, A Arkhangorodsky, M Biesialska… - Proceedings of the sixth …, 2021 - cris.fbk.eu
This paper presents the results of the news translation task, the multilingual low-resource
translation for Indo-European languages, the triangular translation task, and the automatic …

Detecting hallucinated content in conditional neural sequence generation

C Zhou, G Neubig, J Gu, M Diab, P Guzman… - arxiv preprint arxiv …, 2020 - arxiv.org
Neural sequence models can generate highly fluent sentences, but recent studies have also
shown that they are also prone to hallucinate additional content not supported by the input …

Seamless: Multilingual Expressive and Streaming Speech Translation

L Barrault, YA Chung, MC Meglioli, D Dale… - arxiv preprint arxiv …, 2023 - arxiv.org
Large-scale automatic speech translation systems today lack key features that help machine-
mediated communication feel seamless when compared to human-to-human dialogue. In …

Understanding and detecting hallucinations in neural machine translation via model introspection

W Xu, S Agrawal, E Briakou, MJ Martindale… - Transactions of the …, 2023 - direct.mit.edu
Neural sequence generation models are known to “hallucinate”, by producing outputs that
are unrelated to the source text. These hallucinations are potentially harmful, yet it remains …

Unsupervised quality estimation for neural machine translation

M Fomicheva, S Sun, L Yankovskaya… - Transactions of the …, 2020 - direct.mit.edu
Quality Estimation (QE) is an important component in making Machine Translation (MT)
useful in real-world applications, as it is aimed to inform the user on the quality of the MT …