@inproceedings{di-gangi-federico-2017-monolingual,
title = "Monolingual Embeddings for Low Resourced Neural Machine Translation",
author = "Di Gangi, Mattia Antonino and
Federico, Marcello",
booktitle = "Proceedings of the 14th International Conference on Spoken Language Translation",
month = dec # " 14-15",
year = "2017",
address = "Tokyo, Japan",
publisher = "International Workshop on Spoken Language Translation",
url = "https://aclanthology.org/2017.iwslt-1.14",
pages = "97--104",
abstract = "Neural machine translation (NMT) is the state of the art for machine translation, and it shows the best performance when there is a considerable amount of data available. When only little data exist for a language pair, the model cannot produce good representations for words, particularly for rare words. One common solution consists in reducing data sparsity by segmenting words into sub-words, in order to allow rare words to have shared representations with other words. Taking a different approach, in this paper we present a method to feed an NMT network with word embeddings trained on monolingual data, which are combined with the task-specific embeddings learned at training time. This method can leverage an embedding matrix with a huge number of words, which can therefore extend the word-level vocabulary. Our experiments on two language pairs show good results for the typical low-resourced data scenario (IWSLT in-domain dataset). Our consistent improvements over the baselines represent a positive proof about the possibility to leverage models pre-trained on monolingual data in NMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-gangi-federico-2017-monolingual">
<titleInfo>
<title>Monolingual Embeddings for Low Resourced Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="given">Antonino</namePart>
<namePart type="family">Di Gangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-dec" 14-15"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Spoken Language Translation</title>
</titleInfo>
<originInfo>
<publisher>International Workshop on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural machine translation (NMT) is the state of the art for machine translation, and it shows the best performance when there is a considerable amount of data available. When only little data exist for a language pair, the model cannot produce good representations for words, particularly for rare words. One common solution consists in reducing data sparsity by segmenting words into sub-words, in order to allow rare words to have shared representations with other words. Taking a different approach, in this paper we present a method to feed an NMT network with word embeddings trained on monolingual data, which are combined with the task-specific embeddings learned at training time. This method can leverage an embedding matrix with a huge number of words, which can therefore extend the word-level vocabulary. Our experiments on two language pairs show good results for the typical low-resourced data scenario (IWSLT in-domain dataset). Our consistent improvements over the baselines represent a positive proof about the possibility to leverage models pre-trained on monolingual data in NMT.</abstract>
<identifier type="citekey">di-gangi-federico-2017-monolingual</identifier>
<location>
<url>https://aclanthology.org/2017.iwslt-1.14</url>
</location>
<part>
<date>2017-dec" 14-15"</date>
<extent unit="page">
<start>97</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Monolingual Embeddings for Low Resourced Neural Machine Translation
%A Di Gangi, Mattia Antonino
%A Federico, Marcello
%S Proceedings of the 14th International Conference on Spoken Language Translation
%D 2017
%8 dec" 14 15"
%I International Workshop on Spoken Language Translation
%C Tokyo, Japan
%F di-gangi-federico-2017-monolingual
%X Neural machine translation (NMT) is the state of the art for machine translation, and it shows the best performance when there is a considerable amount of data available. When only little data exist for a language pair, the model cannot produce good representations for words, particularly for rare words. One common solution consists in reducing data sparsity by segmenting words into sub-words, in order to allow rare words to have shared representations with other words. Taking a different approach, in this paper we present a method to feed an NMT network with word embeddings trained on monolingual data, which are combined with the task-specific embeddings learned at training time. This method can leverage an embedding matrix with a huge number of words, which can therefore extend the word-level vocabulary. Our experiments on two language pairs show good results for the typical low-resourced data scenario (IWSLT in-domain dataset). Our consistent improvements over the baselines represent a positive proof about the possibility to leverage models pre-trained on monolingual data in NMT.
%U https://aclanthology.org/2017.iwslt-1.14
%P 97-104
Markdown (Informal)
[Monolingual Embeddings for Low Resourced Neural Machine Translation](https://aclanthology.org/2017.iwslt-1.14) (Di Gangi & Federico, IWSLT 2017)
ACL