Advances in natural language processing
J Hirschberg, CD Manning - Science, 2015 - science.org
Natural language processing employs computational techniques for the purpose of learning,
understanding, and producing human language content. Early computational approaches to …
understanding, and producing human language content. Early computational approaches to …
A survey of deep learning techniques for neural machine translation
In recent years, natural language processing (NLP) has got great development with deep
learning techniques. In the sub-field of machine translation, a new approach named Neural …
learning techniques. In the sub-field of machine translation, a new approach named Neural …
A call for clarity in reporting BLEU scores
M Post - arXiv preprint arXiv:1804.08771, 2018 - arxiv.org
The field of machine translation faces an under-recognized problem because of
inconsistency in the reporting of scores from its dominant metric. Although people refer to" …
inconsistency in the reporting of scores from its dominant metric. Although people refer to" …
Multi30k: Multilingual english-german image descriptions
We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent
advances in image description have been demonstrated on English-language datasets …
advances in image description have been demonstrated on English-language datasets …
Good-enough compositional data augmentation
J Andreas - arXiv preprint arXiv:1904.09545, 2019 - arxiv.org
We propose a simple data augmentation protocol aimed at providing a compositional
inductive bias in conditional and unconditional sequence models. Under this protocol …
inductive bias in conditional and unconditional sequence models. Under this protocol …
On using monolingual corpora in neural machine translation
Recent work on end-to-end neural network-based architectures for machine translation has
shown promising results for En-Fr and En-De translation. Arguably, one of the major factors …
shown promising results for En-Fr and En-De translation. Arguably, one of the major factors …
Minimum risk training for neural machine translation
We propose minimum risk training for end-to-end neural machine translation. Unlike
conventional maximum likelihood estimation, minimum risk training is capable of optimizing …
conventional maximum likelihood estimation, minimum risk training is capable of optimizing …
[PDF][PDF] PPDB: The paraphrase database
J Ganitkevitch, B Van Durme… - Proceedings of the …, 2013 - aclanthology.org
We present the 1.0 release of our paraphrase database, PPDB. Its English portion, PPDB:
Eng, contains over 220 million paraphrase pairs, consisting of 73 million phrasal and 8 …
Eng, contains over 220 million paraphrase pairs, consisting of 73 million phrasal and 8 …
Semi-supervised learning for neural machine translation
Y Cheng, Y Cheng - Joint training for neural machine translation, 2019 - Springer
While end-to-end neural machine translation (NMT) has made remarkable progress
recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel …
recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel …
[图书][B] Handbook of natural language processing
N Indurkhya, FJ Damerau - 2010 - taylorfrancis.com
The Handbook of Natural Language Processing, Second Edition presents practical tools
and techniques for implementing natural language processing in computer systems. Along …
and techniques for implementing natural language processing in computer systems. Along …