@inproceedings{dhanani-rafi-2020-attention,
title = "Attention Transformer Model for Translation of Similar Languages",
author = "Dhanani, Farhan and
Rafi, Muhammad",
editor = {Barrault, Lo{\"\i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Graham, Yvette and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.43",
pages = "387--392",
abstract = "This paper illustrates our approach to the shared task on similar language translation in the fifth conference on machine translation (WMT-20). Our motivation comes from the latest state of the art neural machine translation in which Transformers and Recurrent Attention models are effectively used. A typical sequence-sequence architecture consists of an encoder and a decoder Recurrent Neural Network (RNN). The encoder recursively processes a source sequence and reduces it into a fixed-length vector (context), and the decoder generates a target sequence, token by token, conditioned on the same context. In contrast, the advantage of transformers is to reduce the training time by offering a higher degree of parallelism at the cost of freedom for sequential order. With the introduction of Recurrent Attention, it allows the decoder to focus effectively on order of the source sequence at different decoding steps. In our approach, we have combined the recurrence based layered encoder-decoder model with the Transformer model. Our Attention Transformer model enjoys the benefits of both Recurrent Attention and Transformer to quickly learn the most probable sequence for decoding in the target language. The architecture is especially suited for similar languages (languages coming from the same family). We have submitted our system for both Indo-Aryan Language forward (Hindi to Marathi) and reverse (Marathi to Hindi) pair. Our system trains on the parallel corpus of the training dataset provided by the organizers and achieved an average BLEU point of 3.68 with 97.64 TER score for the Hindi-Marathi, along with 9.02 BLEU point and 88.6 TER score for Marathi-Hindi testing set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhanani-rafi-2020-attention">
<titleInfo>
<title>Attention Transformer Model for Translation of Similar Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farhan</namePart>
<namePart type="family">Dhanani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Rafi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper illustrates our approach to the shared task on similar language translation in the fifth conference on machine translation (WMT-20). Our motivation comes from the latest state of the art neural machine translation in which Transformers and Recurrent Attention models are effectively used. A typical sequence-sequence architecture consists of an encoder and a decoder Recurrent Neural Network (RNN). The encoder recursively processes a source sequence and reduces it into a fixed-length vector (context), and the decoder generates a target sequence, token by token, conditioned on the same context. In contrast, the advantage of transformers is to reduce the training time by offering a higher degree of parallelism at the cost of freedom for sequential order. With the introduction of Recurrent Attention, it allows the decoder to focus effectively on order of the source sequence at different decoding steps. In our approach, we have combined the recurrence based layered encoder-decoder model with the Transformer model. Our Attention Transformer model enjoys the benefits of both Recurrent Attention and Transformer to quickly learn the most probable sequence for decoding in the target language. The architecture is especially suited for similar languages (languages coming from the same family). We have submitted our system for both Indo-Aryan Language forward (Hindi to Marathi) and reverse (Marathi to Hindi) pair. Our system trains on the parallel corpus of the training dataset provided by the organizers and achieved an average BLEU point of 3.68 with 97.64 TER score for the Hindi-Marathi, along with 9.02 BLEU point and 88.6 TER score for Marathi-Hindi testing set.</abstract>
<identifier type="citekey">dhanani-rafi-2020-attention</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.43</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>387</start>
<end>392</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention Transformer Model for Translation of Similar Languages
%A Dhanani, Farhan
%A Rafi, Muhammad
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Graham, Yvette
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F dhanani-rafi-2020-attention
%X This paper illustrates our approach to the shared task on similar language translation in the fifth conference on machine translation (WMT-20). Our motivation comes from the latest state of the art neural machine translation in which Transformers and Recurrent Attention models are effectively used. A typical sequence-sequence architecture consists of an encoder and a decoder Recurrent Neural Network (RNN). The encoder recursively processes a source sequence and reduces it into a fixed-length vector (context), and the decoder generates a target sequence, token by token, conditioned on the same context. In contrast, the advantage of transformers is to reduce the training time by offering a higher degree of parallelism at the cost of freedom for sequential order. With the introduction of Recurrent Attention, it allows the decoder to focus effectively on order of the source sequence at different decoding steps. In our approach, we have combined the recurrence based layered encoder-decoder model with the Transformer model. Our Attention Transformer model enjoys the benefits of both Recurrent Attention and Transformer to quickly learn the most probable sequence for decoding in the target language. The architecture is especially suited for similar languages (languages coming from the same family). We have submitted our system for both Indo-Aryan Language forward (Hindi to Marathi) and reverse (Marathi to Hindi) pair. Our system trains on the parallel corpus of the training dataset provided by the organizers and achieved an average BLEU point of 3.68 with 97.64 TER score for the Hindi-Marathi, along with 9.02 BLEU point and 88.6 TER score for Marathi-Hindi testing set.
%U https://aclanthology.org/2020.wmt-1.43
%P 387-392
Markdown (Informal)
[Attention Transformer Model for Translation of Similar Languages](https://aclanthology.org/2020.wmt-1.43) (Dhanani & Rafi, WMT 2020)
ACL