Multilingual sentiment analysis: from formal to informal and scarce resource languages

SL Lo, E Cambria, R Chiong, D Cornforth - Artificial Intelligence Review, 2017 - Springer
The ability to analyse online user-generated content related to sentiments (eg, thoughts and
opinions) on products or policies has become a de-facto skillset for many companies and …

Phrase-based & neural unsupervised machine translation

G Lample, M Ott, A Conneau, L Denoyer… - arXiv preprint arXiv …, 2018 - arxiv.org
Machine translation systems achieve near human-level performance on some languages,
yet their effectiveness strongly relies on the availability of large amounts of parallel …

Six challenges for neural machine translation

P Koehn, R Knowles - arXiv preprint arXiv:1706.03872, 2017 - arxiv.org
We explore six challenges for neural machine translation: domain mismatch, amount of
training data, rare words, long sentences, word alignment, and beam search. We show both …

[引用][C] Neural machine translation

P Koehn - 2020 - books.google.com
Deep learning is revolutionizing how machine translation systems are built today. This book
introduces the challenge of machine translation and evaluation-including historical …

Adversarial training for unsupervised bilingual lexicon induction

M Zhang, Y Liu, H Luan, M Sun - … of the 55th Annual Meeting of …, 2017 - aclanthology.org
Word embeddings are well known to capture linguistic regularities of the language on which
they are trained. Researchers also observe that these regularities can transfer across …

[图书][B] Statistical machine translation

P Koehn - 2009 - books.google.com
The dream of automatic language translation is now closer thanks to recent advances in the
techniques that underpin statistical machine translation. This class-tested textbook from an …

Bilingual lexicon induction with semi-supervision in non-isometric embedding spaces

B Patra, JRA Moniz, S Garg, MR Gormley… - arXiv preprint arXiv …, 2019 - arxiv.org
Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned
bilingual lexicons or on distribution matching, often with an assumption about the isometry of …

Data and parameter scaling laws for neural machine translation

MA Gordon, K Duh, J Kaplan - Proceedings of the 2021 …, 2021 - aclanthology.org
We observe that the development cross-entropy loss of supervised neural machine
translation models scales like a power law with the amount of training data and the number …

[图书][B] Healthcare data analytics

CK Reddy, CC Aggarwal - 2015 - books.google.com
Supplying a comprehensive overview of healthcare analytics research, Healthcare Data
Analytics provides an understanding of the analytical techniques currently available to solve …

Not low-resource anymore: Aligner ensembling, batch filtering, and new datasets for Bengali-English machine translation

T Hasan, A Bhattacharjee, K Samin, M Hasan… - arXiv preprint arXiv …, 2020 - arxiv.org
Despite being the seventh most widely spoken language in the world, Bengali has received
much less attention in machine translation literature due to being low in resources. Most …