@inproceedings{pu-simaan-2022-passing,
title = "Passing Parser Uncertainty to the Transformer: Labeled Dependency Distributions for Neural Machine Translation",
author = "Liu, Dongqi and
Sima{'}an, Khalil",
editor = {Moniz, Helena and
Macken, Lieve and
Rufener, Andrew and
Barrault, Lo{\"i}c and
Costa-juss{\`a}, Marta R. and
Declercq, Christophe and
Koponen, Maarit and
Kemp, Ellie and
Pilos, Spyridon and
Forcada, Mikel L. and
Scarton, Carolina and
Van den Bogaert, Joachim and
Daems, Joke and
Tezcan, Arda and
Vanroy, Bram and
Fonteyne, Margot},
booktitle = "Proceedings of the 23rd Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2022",
address = "Ghent, Belgium",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2022.eamt-1.7/",
pages = "41--50",
abstract = "Existing syntax-enriched neural machine translation (NMT) models work either with the single most-likely unlabeled parse or the set of n-best unlabeled parses coming out of an external parser. Passing a single or n-best parses to the NMT model risks propagating parse errors. Furthermore, unlabeled parses represent only syntactic groupings without their linguistically relevant categories. In this paper we explore the question: Does passing both parser uncertainty and labeled syntactic knowledge to the Transformer improve its translation performance? This paper contributes a novel method for infusing the whole labeled dependency distributions (LDD) of the source sentence`s dependency forest into the self-attention mechanism of the encoder of the Transformer. A range of experimental results on three language pairs demonstrate that the proposed approach outperforms both the vanilla Transformer as well as the single best-parse Transformer model across several evaluation metrics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pu-simaan-2022-passing">
<titleInfo>
<title>Passing Parser Uncertainty to the Transformer: Labeled Dependency Distributions for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongqi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Sima’an</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Rufener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">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">Christophe</namePart>
<namePart type="family">Declercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Kemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spyridon</namePart>
<namePart type="family">Pilos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">Vanroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Fonteyne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Ghent, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing syntax-enriched neural machine translation (NMT) models work either with the single most-likely unlabeled parse or the set of n-best unlabeled parses coming out of an external parser. Passing a single or n-best parses to the NMT model risks propagating parse errors. Furthermore, unlabeled parses represent only syntactic groupings without their linguistically relevant categories. In this paper we explore the question: Does passing both parser uncertainty and labeled syntactic knowledge to the Transformer improve its translation performance? This paper contributes a novel method for infusing the whole labeled dependency distributions (LDD) of the source sentence‘s dependency forest into the self-attention mechanism of the encoder of the Transformer. A range of experimental results on three language pairs demonstrate that the proposed approach outperforms both the vanilla Transformer as well as the single best-parse Transformer model across several evaluation metrics.</abstract>
<identifier type="citekey">pu-simaan-2022-passing</identifier>
<location>
<url>https://aclanthology.org/2022.eamt-1.7/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>41</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Passing Parser Uncertainty to the Transformer: Labeled Dependency Distributions for Neural Machine Translation
%A Liu, Dongqi
%A Sima’an, Khalil
%Y Moniz, Helena
%Y Macken, Lieve
%Y Rufener, Andrew
%Y Barrault, Loïc
%Y Costa-jussà, Marta R.
%Y Declercq, Christophe
%Y Koponen, Maarit
%Y Kemp, Ellie
%Y Pilos, Spyridon
%Y Forcada, Mikel L.
%Y Scarton, Carolina
%Y Van den Bogaert, Joachim
%Y Daems, Joke
%Y Tezcan, Arda
%Y Vanroy, Bram
%Y Fonteyne, Margot
%S Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
%D 2022
%8 June
%I European Association for Machine Translation
%C Ghent, Belgium
%F pu-simaan-2022-passing
%X Existing syntax-enriched neural machine translation (NMT) models work either with the single most-likely unlabeled parse or the set of n-best unlabeled parses coming out of an external parser. Passing a single or n-best parses to the NMT model risks propagating parse errors. Furthermore, unlabeled parses represent only syntactic groupings without their linguistically relevant categories. In this paper we explore the question: Does passing both parser uncertainty and labeled syntactic knowledge to the Transformer improve its translation performance? This paper contributes a novel method for infusing the whole labeled dependency distributions (LDD) of the source sentence‘s dependency forest into the self-attention mechanism of the encoder of the Transformer. A range of experimental results on three language pairs demonstrate that the proposed approach outperforms both the vanilla Transformer as well as the single best-parse Transformer model across several evaluation metrics.
%U https://aclanthology.org/2022.eamt-1.7/
%P 41-50
Markdown (Informal)
[Passing Parser Uncertainty to the Transformer: Labeled Dependency Distributions for Neural Machine Translation](https://aclanthology.org/2022.eamt-1.7/) (Liu & Sima’an, EAMT 2022)
ACL