@inproceedings{tokarchuk-niculae-2022-target,
title = "On Target Representation in Continuous-output Neural Machine Translation",
author = "Tokarchuk, Evgeniia and
Niculae, Vlad",
editor = "Gella, Spandana and
He, He and
Majumder, Bodhisattwa Prasad and
Can, Burcu and
Giunchiglia, Eleonora and
Cahyawijaya, Samuel and
Min, Sewon and
Mozes, Maximilian and
Li, Xiang Lorraine and
Augenstein, Isabelle and
Rogers, Anna and
Cho, Kyunghyun and
Grefenstette, Edward and
Rimell, Laura and
Dyer, Chris",
booktitle = "Proceedings of the 7th Workshop on Representation Learning for NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.repl4nlp-1.24/",
doi = "10.18653/v1/2022.repl4nlp-1.24",
pages = "227--235",
abstract = "Continuous generative models proved their usefulness in high-dimensional data, such as image and audio generation. However, continuous models for text generation have received limited attention from the community. In this work, we study continuous text generation using Transformers for neural machine translation (NMT). We argue that the choice of embeddings is crucial for such models, so we aim to focus on one particular aspect{\textquotedblright}:{\textquotedblright} target representation via embeddings. We explore pretrained embeddings and also introduce knowledge transfer from the discrete Transformer model using embeddings in Euclidean and non-Euclidean spaces. Our results on the WMT Romanian-English and English-Turkish benchmarks show such transfer leads to the best-performing continuous model."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tokarchuk-niculae-2022-target">
<titleInfo>
<title>On Target Representation in Continuous-output Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evgeniia</namePart>
<namePart type="family">Tokarchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vlad</namePart>
<namePart type="family">Niculae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleonora</namePart>
<namePart type="family">Giunchiglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Mozes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="given">Lorraine</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Continuous generative models proved their usefulness in high-dimensional data, such as image and audio generation. However, continuous models for text generation have received limited attention from the community. In this work, we study continuous text generation using Transformers for neural machine translation (NMT). We argue that the choice of embeddings is crucial for such models, so we aim to focus on one particular aspect”:” target representation via embeddings. We explore pretrained embeddings and also introduce knowledge transfer from the discrete Transformer model using embeddings in Euclidean and non-Euclidean spaces. Our results on the WMT Romanian-English and English-Turkish benchmarks show such transfer leads to the best-performing continuous model.</abstract>
<identifier type="citekey">tokarchuk-niculae-2022-target</identifier>
<identifier type="doi">10.18653/v1/2022.repl4nlp-1.24</identifier>
<location>
<url>https://aclanthology.org/2022.repl4nlp-1.24/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>227</start>
<end>235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Target Representation in Continuous-output Neural Machine Translation
%A Tokarchuk, Evgeniia
%A Niculae, Vlad
%Y Gella, Spandana
%Y He, He
%Y Majumder, Bodhisattwa Prasad
%Y Can, Burcu
%Y Giunchiglia, Eleonora
%Y Cahyawijaya, Samuel
%Y Min, Sewon
%Y Mozes, Maximilian
%Y Li, Xiang Lorraine
%Y Augenstein, Isabelle
%Y Rogers, Anna
%Y Cho, Kyunghyun
%Y Grefenstette, Edward
%Y Rimell, Laura
%Y Dyer, Chris
%S Proceedings of the 7th Workshop on Representation Learning for NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F tokarchuk-niculae-2022-target
%X Continuous generative models proved their usefulness in high-dimensional data, such as image and audio generation. However, continuous models for text generation have received limited attention from the community. In this work, we study continuous text generation using Transformers for neural machine translation (NMT). We argue that the choice of embeddings is crucial for such models, so we aim to focus on one particular aspect”:” target representation via embeddings. We explore pretrained embeddings and also introduce knowledge transfer from the discrete Transformer model using embeddings in Euclidean and non-Euclidean spaces. Our results on the WMT Romanian-English and English-Turkish benchmarks show such transfer leads to the best-performing continuous model.
%R 10.18653/v1/2022.repl4nlp-1.24
%U https://aclanthology.org/2022.repl4nlp-1.24/
%U https://doi.org/10.18653/v1/2022.repl4nlp-1.24
%P 227-235
Markdown (Informal)
[On Target Representation in Continuous-output Neural Machine Translation](https://aclanthology.org/2022.repl4nlp-1.24/) (Tokarchuk & Niculae, RepL4NLP 2022)
ACL