Paraphrase generation is the task of given a word sequence generating another word sequence that keeps the same meaning than the original one. Generating new paraphrases can be used to enhance machine translation systems both at training and test phases. This project proposes to exploit latest sequence-to-sequence deep learning techniques to model paraphrase generation and integrate it in a state-of-the-art neural machine translation system. As part of this project, the enhanced neural machine translation system will be participating in the WMT 2018 international evaluaDeep Learning algorithms have a big impact in such areas as speech and image recognition or natural language processing. Machine Translation included. In recent years Neural ...
Paraphrasing and translation have previously been treated as unconnected natural lan¬ guage process...
We present a methodology that explores how sentence structure is reflected in neural representations...
[EN] Machine Translation (MT) is one of the most active areas in Artificial Intelligence, particula...
[EN] A paraphrase is a restatement of the meaning of a text or passage using other words. There are ...
In this paper, we investigate whether multilingual neural translation models learn stronger semantic...
Machine Translation is the translation of text or speech by a computer with no human involvement. It...
[EN] From the outset, automatic translation was dominated by systems based on linguistic informatio...
Use different words to express/convey the same message is a necessity in any natural language and, a...
We present PARABANK, a large-scale English paraphrase dataset that surpasses prior work in both quan...
In recent years, Neural Machine Translation (NMT) has achieved state-of-the-art performance in trans...
Paraphrase generation is an important problem in NLP, especially in question answering, information ...
This paper presents FISKMÖ, a project that focuses on the development of resources and tools for cro...
Natural languages are known for their expressive richness. Many sentences can be used to represent t...
Natural language allows for the same meaning (semantics) to be expressed in multiple different ways,...
We propose to achieve explainable neural machine translation (NMT) by changing the output representa...
Paraphrasing and translation have previously been treated as unconnected natural lan¬ guage process...
We present a methodology that explores how sentence structure is reflected in neural representations...
[EN] Machine Translation (MT) is one of the most active areas in Artificial Intelligence, particula...
[EN] A paraphrase is a restatement of the meaning of a text or passage using other words. There are ...
In this paper, we investigate whether multilingual neural translation models learn stronger semantic...
Machine Translation is the translation of text or speech by a computer with no human involvement. It...
[EN] From the outset, automatic translation was dominated by systems based on linguistic informatio...
Use different words to express/convey the same message is a necessity in any natural language and, a...
We present PARABANK, a large-scale English paraphrase dataset that surpasses prior work in both quan...
In recent years, Neural Machine Translation (NMT) has achieved state-of-the-art performance in trans...
Paraphrase generation is an important problem in NLP, especially in question answering, information ...
This paper presents FISKMÖ, a project that focuses on the development of resources and tools for cro...
Natural languages are known for their expressive richness. Many sentences can be used to represent t...
Natural language allows for the same meaning (semantics) to be expressed in multiple different ways,...
We propose to achieve explainable neural machine translation (NMT) by changing the output representa...
Paraphrasing and translation have previously been treated as unconnected natural lan¬ guage process...
We present a methodology that explores how sentence structure is reflected in neural representations...
[EN] Machine Translation (MT) is one of the most active areas in Artificial Intelligence, particula...