Attention-based neural machine translation a systematic mapping study

Neuroverkkokonekääntäminen on kasvava konekääntämisen erityisala. Tällä hetkellä suosituin neuroverkkokääntämistekniikka lienee kiintopisteneuroverkkokääntäminen (engl. Attentional Neural Machine Translation, suomennos oma), jossa neuroverkko kiinnittää huomiota käännettävän lauseen tiettyihin osiin...

Full description

Bibliographic Details
Main Author: Koivuniemi, Milla
Other Authors: Informaatioteknologian tiedekunta, Faculty of Information Technology, Informaatioteknologia, Information Technology, Jyväskylän yliopisto, University of Jyväskylä
Format: Master's thesis
Language:eng
Published: 2020
Subjects:
Online Access: https://jyx.jyu.fi/handle/123456789/69682
_version_ 1826225743524265984
author Koivuniemi, Milla
author2 Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_facet Koivuniemi, Milla Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä Koivuniemi, Milla Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_sort Koivuniemi, Milla
datasource_str_mv jyx
description Neuroverkkokonekääntäminen on kasvava konekääntämisen erityisala. Tällä hetkellä suosituin neuroverkkokääntämistekniikka lienee kiintopisteneuroverkkokääntäminen (engl. Attentional Neural Machine Translation, suomennos oma), jossa neuroverkko kiinnittää huomiota käännettävän lauseen tiettyihin osiin vähentäen näin verkon kuormitusta. Tämä pro gradu -tutkielma on kirjallisuuskartoitus kiintopisteneuroverkkokääntämisestä, jossa tehdään läpileikkaus käytetyimmistä neuroverkon ominaisuuksista sekä käännösten laadusta. Erityishuomion kohteena on tunnettu kehityskohde, pienen aineiston kielet (engl. low-resource languages), eli kielet, joille on tarjolla vain verrattain pienikokoisia rinnakkaiskorpuksia eli kieliaineistoja. Tutkielman tulosten perusteella kiintopisteneuroverkkokääntäminen on tehokasta ja tuottaa sujuvia käännöksiä. Kokonaisuutena tämä kirjallisuuskartoitus tuottaa uutta kiinnostavaa tietoa neuroverkkokonekääntämisen tutkimuksen nykytilasta sekä luo pohjan erilaisille mielenkiintoisille jatkotutkimusaiheille. Neural machine translation (NMT) is an emerging field of study in machine translation. The leading model for doing neural machine translation seems to be attention-based NMT, in which a part of the source sequence is selected and paid attention to in order to reduce the burden of the encoder. The present thesis is a literature mapping of attentional NMT. The study provides a crosscut of current research in attentional NMT, going over the most popular network features as well as translation quality. Special attention is given to a known problem area, translation of low-resource languages, i.e., languages with only small parallel corpora available. Judging by the papers reviewed, attentional NMT is efficient and produces fluent translation. As a whole, this mapping study produces new and valuable information about the state of research in NMT and provides foundation for different interesting topics for further research.
first_indexed 2020-06-03T20:02:38Z
format Pro gradu
free_online_boolean 1
fullrecord [{"key": "dc.contributor.advisor", "value": "Nieminen, Paavo", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.advisor", "value": "Kaijanaho, Antti-Juhani", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Koivuniemi, Milla", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2020-06-03T12:33:27Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2020-06-03T12:33:27Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2020", "language": "", "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/69682", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Neuroverkkokonek\u00e4\u00e4nt\u00e4minen on kasvava konek\u00e4\u00e4nt\u00e4misen erityisala. T\u00e4ll\u00e4 hetkell\u00e4 suosituin neuroverkkok\u00e4\u00e4nt\u00e4mistekniikka lienee kiintopisteneuroverkkok\u00e4\u00e4nt\u00e4minen (engl. Attentional Neural Machine Translation, suomennos oma), jossa neuroverkko kiinnitt\u00e4\u00e4 huomiota k\u00e4\u00e4nnett\u00e4v\u00e4n lauseen tiettyihin osiin v\u00e4hent\u00e4en n\u00e4in verkon kuormitusta. T\u00e4m\u00e4 pro gradu -tutkielma on kirjallisuuskartoitus kiintopisteneuroverkkok\u00e4\u00e4nt\u00e4misest\u00e4, jossa tehd\u00e4\u00e4n l\u00e4pileikkaus k\u00e4ytetyimmist\u00e4 neuroverkon ominaisuuksista\nsek\u00e4 k\u00e4\u00e4nn\u00f6sten laadusta. Erityishuomion kohteena on tunnettu kehityskohde, pienen aineiston kielet (engl. low-resource languages), eli kielet, joille on tarjolla vain verrattain pienikokoisia rinnakkaiskorpuksia eli kieliaineistoja. Tutkielman tulosten perusteella kiintopisteneuroverkkok\u00e4\u00e4nt\u00e4minen on tehokasta ja tuottaa sujuvia k\u00e4\u00e4nn\u00f6ksi\u00e4. Kokonaisuutena t\u00e4m\u00e4 kirjallisuuskartoitus tuottaa uutta kiinnostavaa tietoa neuroverkkokonek\u00e4\u00e4nt\u00e4misen tutkimuksen nykytilasta sek\u00e4 luo pohjan erilaisille mielenkiintoisille jatkotutkimusaiheille.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Neural machine translation (NMT) is an emerging field of study in machine translation. The leading model for doing neural machine translation seems to be attention-based NMT, in which a part of the source sequence is selected and paid attention to in order to reduce the burden of the encoder. The present thesis is a literature mapping of attentional NMT. The study provides a crosscut of current research in attentional NMT, going over the most popular network features as well as translation quality. Special attention is given to a known problem area, translation of low-resource languages, i.e., languages with only small parallel corpora available. Judging by the papers reviewed, attentional NMT is efficient and produces fluent translation. As a whole, this mapping study produces new and valuable information about the state of research in NMT and provides foundation for different interesting topics for further research.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Paivi Vuorio (paelvuor@jyu.fi) on 2020-06-03T12:33:27Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2020-06-03T12:33:27Z (GMT). No. of bitstreams: 0\n Previous issue date: 2020", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "86", "language": "", "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "eng", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.subject.other", "value": "neural machine translation", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "natural language processing", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "attention-based neural machine translation", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "systematic literature mapping", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "neuroverkkok\u00e4\u00e4nt\u00e4minen", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "luonnollisen kielen prosessointi", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "kiintopisteneuroverkkok\u00e4\u00e4nt\u00e4minen", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "systemaattinen kirjallisuuskartoitus", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Attention-based neural machine translation : a systematic mapping study", "language": "", "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202006033937", "language": "", "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master\u2019s thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Informaatioteknologia", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Information Technology", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietotekniikka", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Mathematical Information Technology", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": "", "element": "contractresearch", "qualifier": "funding", "schema": "yvv"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "602", "language": "", "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "k\u00e4\u00e4nt\u00e4minen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neuroverkot", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "translating", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neural networks", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}, {"key": "dc.type.okm", "value": "G2", "language": null, "element": "type", "qualifier": "okm", "schema": "dc"}]
id jyx.123456789_69682
language eng
last_indexed 2025-02-18T10:55:38Z
main_date 2020-01-01T00:00:00Z
main_date_str 2020
online_boolean 1
online_urls_str_mv {"url":"https:\/\/jyx.jyu.fi\/bitstreams\/6a9580a8-8c2b-4980-9a19-0e04e1a2cdb0\/download","text":"URN:NBN:fi:jyu-202006033937.pdf","source":"jyx","mediaType":"application\/pdf"}
publishDate 2020
record_format qdc
source_str_mv jyx
spellingShingle Koivuniemi, Milla Attention-based neural machine translation : a systematic mapping study neural machine translation natural language processing attention-based neural machine translation systematic literature mapping neuroverkkokääntäminen luonnollisen kielen prosessointi kiintopisteneuroverkkokääntäminen systemaattinen kirjallisuuskartoitus Tietotekniikka Mathematical Information Technology 602 kääntäminen neuroverkot translating neural networks
title Attention-based neural machine translation : a systematic mapping study
title_full Attention-based neural machine translation : a systematic mapping study
title_fullStr Attention-based neural machine translation : a systematic mapping study Attention-based neural machine translation : a systematic mapping study
title_full_unstemmed Attention-based neural machine translation : a systematic mapping study Attention-based neural machine translation : a systematic mapping study
title_short Attention-based neural machine translation
title_sort attention based neural machine translation a systematic mapping study
title_sub a systematic mapping study
title_txtP Attention-based neural machine translation : a systematic mapping study
topic neural machine translation natural language processing attention-based neural machine translation systematic literature mapping neuroverkkokääntäminen luonnollisen kielen prosessointi kiintopisteneuroverkkokääntäminen systemaattinen kirjallisuuskartoitus Tietotekniikka Mathematical Information Technology 602 kääntäminen neuroverkot translating neural networks
topic_facet 602 Mathematical Information Technology Tietotekniikka attention-based neural machine translation kiintopisteneuroverkkokääntäminen kääntäminen luonnollisen kielen prosessointi natural language processing neural machine translation neural networks neuroverkkokääntäminen neuroverkot systemaattinen kirjallisuuskartoitus systematic literature mapping translating
url https://jyx.jyu.fi/handle/123456789/69682 http://www.urn.fi/URN:NBN:fi:jyu-202006033937
work_keys_str_mv AT koivuniemimilla attentionbasedneuralmachinetranslationasystematicmappingstudy