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 …
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 …
(NMT) by selectively focusing on parts of the source sentence during translation. However …
Transfer learning for low-resource neural machine translation
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 …
effective in large data scenarios, but is much less effective for low-resource languages. We …
Findings of the 2016 conference on machine translation (wmt16)
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 …
translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three …
Modeling coverage for neural machine translation
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 …
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 …
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 …
vocabularies, perhaps with a subsequent method to patch in unknown words. This paper …
[PDF][PDF] Findings of the 2014 workshop on statistical machine translation
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 …
translation task, a separate medical translation task, a task for run-time estimation of …
[PDF][PDF] Bilingual word embeddings for phrase-based machine translation
We introduce bilingual word embeddings: semantic embeddings associated across two
languages in the context of neural language models. We propose a method to learn …
languages in the context of neural language models. We propose a method to learn …
[PDF][PDF] Building a semantic parser overnight
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 …
We introduce a new methodology for this setting: First, we use a simple grammar to generate …