@inproceedings{gupta-etal-2021-investigating,
title = "Investigating Active Learning in Interactive Neural Machine Translation",
author = "Gupta, Kamal and
Boppana, Dhanvanth and
Haque, Rejwanul and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Duh, Kevin and
Guzm{\'a}n, Francisco",
booktitle = "Proceedings of Machine Translation Summit XVIII: Research Track",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-research.2",
pages = "10--22",
abstract = "Interactive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in active learning (AL) exist to update the neural MT (NMT) model in the interactive-predictive scenario. In this paper and we explore term based (named entity count (NEC)) and quality based (quality estimation (QE) and sentence similarity (Sim)) sampling techniques {--} which are used to find the ideal candidates from the incoming data {--} for human supervision and MT model{'}s weight updation. We carried out experiments with three language pairs and viz. German-English and Spanish-English and Hindi-English. Our proposed sampling technique yields 1.82 and 0.77 and 0.81 BLEU points improvements for German-English and Spanish-English and Hindi-English and respectively and over random sampling based baseline. It also improves the present state-of-the-art by 0.35 and 0.12 BLEU points for German-English and Spanish-English and respectively. Human editing effort in terms of number-of-words-changed also improves by 5 and 4 points for German-English and Spanish-English and respectively and compared to the state-of-the-art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2021-investigating">
<titleInfo>
<title>Investigating Active Learning in Interactive Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamal</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhanvanth</namePart>
<namePart type="family">Boppana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rejwanul</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XVIII: Research Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzmán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interactive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in active learning (AL) exist to update the neural MT (NMT) model in the interactive-predictive scenario. In this paper and we explore term based (named entity count (NEC)) and quality based (quality estimation (QE) and sentence similarity (Sim)) sampling techniques – which are used to find the ideal candidates from the incoming data – for human supervision and MT model’s weight updation. We carried out experiments with three language pairs and viz. German-English and Spanish-English and Hindi-English. Our proposed sampling technique yields 1.82 and 0.77 and 0.81 BLEU points improvements for German-English and Spanish-English and Hindi-English and respectively and over random sampling based baseline. It also improves the present state-of-the-art by 0.35 and 0.12 BLEU points for German-English and Spanish-English and respectively. Human editing effort in terms of number-of-words-changed also improves by 5 and 4 points for German-English and Spanish-English and respectively and compared to the state-of-the-art.</abstract>
<identifier type="citekey">gupta-etal-2021-investigating</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-research.2</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>10</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Active Learning in Interactive Neural Machine Translation
%A Gupta, Kamal
%A Boppana, Dhanvanth
%A Haque, Rejwanul
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of Machine Translation Summit XVIII: Research Track
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F gupta-etal-2021-investigating
%X Interactive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in active learning (AL) exist to update the neural MT (NMT) model in the interactive-predictive scenario. In this paper and we explore term based (named entity count (NEC)) and quality based (quality estimation (QE) and sentence similarity (Sim)) sampling techniques – which are used to find the ideal candidates from the incoming data – for human supervision and MT model’s weight updation. We carried out experiments with three language pairs and viz. German-English and Spanish-English and Hindi-English. Our proposed sampling technique yields 1.82 and 0.77 and 0.81 BLEU points improvements for German-English and Spanish-English and Hindi-English and respectively and over random sampling based baseline. It also improves the present state-of-the-art by 0.35 and 0.12 BLEU points for German-English and Spanish-English and respectively. Human editing effort in terms of number-of-words-changed also improves by 5 and 4 points for German-English and Spanish-English and respectively and compared to the state-of-the-art.
%U https://aclanthology.org/2021.mtsummit-research.2
%P 10-22
Markdown (Informal)
[Investigating Active Learning in Interactive Neural Machine Translation](https://aclanthology.org/2021.mtsummit-research.2) (Gupta et al., MTSummit 2021)
ACL