@inproceedings{barzdins-etal-2016-character,
title = "Character-Level Neural Translation for Multilingual Media Monitoring in the {SUMMA} Project",
author = "Barzdins, Guntis and
Renals, Steve and
Gosko, Didzis",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1282/",
pages = "1789--1793",
abstract = "The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into storylines. Storyline clustering of stories covering the same events is an essential task for inquisitorial media monitoring. We address these two problems jointly by engaging the low-dimensional semantic representation capabilities of the sequence to sequence neural translation models. To enable joint multi-task learning for multilingual neural translation of morphologically rich languages we replace the attention mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation model on the character-level rather than on the word-level. The story segmentation and storyline clustering problem is tackled by examining the low-dimensional vectors produced as a side-product of the neural translation process. The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barzdins-etal-2016-character">
<titleInfo>
<title>Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guntis</namePart>
<namePart type="family">Barzdins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Renals</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Didzis</namePart>
<namePart type="family">Gosko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into storylines. Storyline clustering of stories covering the same events is an essential task for inquisitorial media monitoring. We address these two problems jointly by engaging the low-dimensional semantic representation capabilities of the sequence to sequence neural translation models. To enable joint multi-task learning for multilingual neural translation of morphologically rich languages we replace the attention mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation model on the character-level rather than on the word-level. The story segmentation and storyline clustering problem is tackled by examining the low-dimensional vectors produced as a side-product of the neural translation process. The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem.</abstract>
<identifier type="citekey">barzdins-etal-2016-character</identifier>
<location>
<url>https://aclanthology.org/L16-1282/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1789</start>
<end>1793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
%A Barzdins, Guntis
%A Renals, Steve
%A Gosko, Didzis
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F barzdins-etal-2016-character
%X The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into storylines. Storyline clustering of stories covering the same events is an essential task for inquisitorial media monitoring. We address these two problems jointly by engaging the low-dimensional semantic representation capabilities of the sequence to sequence neural translation models. To enable joint multi-task learning for multilingual neural translation of morphologically rich languages we replace the attention mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation model on the character-level rather than on the word-level. The story segmentation and storyline clustering problem is tackled by examining the low-dimensional vectors produced as a side-product of the neural translation process. The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem.
%U https://aclanthology.org/L16-1282/
%P 1789-1793
Markdown (Informal)
[Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project](https://aclanthology.org/L16-1282/) (Barzdins et al., LREC 2016)
ACL