Statistical machine translation

A Lopez - ACM Computing Surveys (CSUR), 2008 - dl.acm.org
Statistical machine translation (SMT) treats the translation of natural language as a machine
learning problem. By examining many samples of human-produced translation, SMT …

[PDF][PDF] Effective approaches to attention-based neural machine translation

MT Luong - arXiv preprint arXiv:1508.04025, 2015 - courses.grainger.illinois.edu
An attentional mechanism has lately been used to improve neural machine translation
(NMT) by selectively focusing on parts of the source sentence during translation. However …

Transfer learning for low-resource neural machine translation

B Zoph, D Yuret, J May, K Knight - arXiv preprint arXiv:1604.02201, 2016 - arxiv.org
The encoder-decoder framework for neural machine translation (NMT) has been shown
effective in large data scenarios, but is much less effective for low-resource languages. We …

Findings of the 2016 conference on machine translation (wmt16)

O Bojar, R Chatterjee, C Federmann… - First conference on …, 2016 - research.ed.ac.uk
This paper presents the results of the WMT16 shared tasks, which included five machine
translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three …

Modeling coverage for neural machine translation

Z Tu, Z Lu, Y Liu, X Liu, H Li - arXiv preprint arXiv:1601.04811, 2016 - arxiv.org
Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by
jointly learning to align and translate. It tends to ignore past alignment information, however …

[PDF][PDF] Leveraging linguistic structure for open domain information extraction

G Angeli, MJJ Premkumar… - Proceedings of the 53rd …, 2015 - aclanthology.org
Relation triples produced by open domain information extraction (open IE) systems are
useful for question answering, inference, and other IE tasks. Traditionally these are extracted …

Achieving open vocabulary neural machine translation with hybrid word-character models

MT Luong, CD Manning - arXiv preprint arXiv:1604.00788, 2016 - arxiv.org
Nearly all previous work on neural machine translation (NMT) has used quite restricted
vocabularies, perhaps with a subsequent method to patch in unknown words. This paper …

[PDF][PDF] Findings of the 2014 workshop on statistical machine translation

O Bojar, C Buck, C Federmann, B Haddow… - Proceedings of the …, 2014 - aclanthology.org
This paper presents the results of the WMT14 shared tasks, which included a standard news
translation task, a separate medical translation task, a task for run-time estimation of …

[PDF][PDF] Bilingual word embeddings for phrase-based machine translation

WY Zou, R Socher, D Cer… - Proceedings of the 2013 …, 2013 - aclanthology.org
We introduce bilingual word embeddings: semantic embeddings associated across two
languages in the context of neural language models. We propose a method to learn …

[PDF][PDF] Building a semantic parser overnight

Y Wang, J Berant, P Liang - … of the 53rd Annual Meeting of the …, 2015 - aclanthology.org
How do we build a semantic parser in a new domain starting with zero training examples?
We introduce a new methodology for this setting: First, we use a simple grammar to generate …