Sprachkontrolle im Spiegel der Maschinellen Übersetzung
| Titel: | Sprachkontrolle im Spiegel der Maschinellen Übersetzung : Untersuchung zur Wechselwirkung ausgewählter Regeln der Kontrollierten Sprache mit verschiedenen Ansätzen der Maschinellen Übersetzung |
|---|---|
| Beteiligt: | |
| Veröffentlicht: | [Erscheinungsort nicht ermittelbar] : Language Science Press ; Language Science Press [Imprint], 2022 |
| Umfang: | 1 Online-Ressource |
| Format: | E-Book |
| Sprache: | Englisch |
| RVK-Notation: | |
| ISBN: | 9783961103942 ; 9783985540525 |
X
alg: 53099096 001A $06055:26-06-25 001B $01999:15-08-25 $t07:15:02.000 001D $06055:26-06-25 001U $0utf8 001X $00 002@ $0Oax 002C $aText $btxt $2rdacontent 002D $aComputermedien $bc $2rdamedia 002E $aOnline-Ressource $bcr $2rdacarrier 003@ $0530990962 004A $A978-3-96110-394-2 004A $A978-3-9855405-2-5 004R $020.500.12657/61708 007A $0530990962 $aHEB 007I $0oapen-20.500.12657/61708 009Q $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $xR 010@ $aeng 011@ $a2022 013D $RWissenschaftliche Literatur $#Dissertations, Academic $#Thèses et écrits académiques $74113937-9 $8Hochschulschrift [Ts1] $9085338818 017B $aZDB-94-OAL 021A $aSprachkontrolle im Spiegel der Maschinellen Übersetzung $dUntersuchung zur Wechselwirkung ausgewählter Regeln der Kontrollierten Sprache mit verschiedenen Ansätzen der Maschinellen Übersetzung 028C $aMarzouk $BHerausgeber $dShaimaa $4edt 033A $p[Erscheinungsort nicht ermittelbar] $nLanguage Science Press ; Language Science Press [Imprint] 033E $pThe Hague $nOapen Foundation 034D $a1 Online-Ressource 037J $aOpen Access $2star $uhttps://purl.org/coar/access_right/c_abf2 $fUnrestricted online access 044K $RÜbersetzung $RComputerlinguistik $RComputerunterstützte Übersetzung $#Machine translating $#Traduction automatique $#Traduzione automatica $#Traducción automática $#Automatische Sprachenübersetzung $#Automatische Sprachübersetzung $#Automatisches Übersetzen $#Automatische Übersetzung $#Maschinelle Sprachübersetzung $#Maschinenübersetzung $74003966-3 $8Maschinelle Übersetzung [Ts1] $9085002364 044K $RTerminologiearbeit $#Terminology $#Terminologie $#Terminologie Kontrolle $#Terminologiekontrolle $74136260-3 $8Terminologische Kontrolle [Ts1] $9085505943 045E $c020 $c004 $c400 045Z $8ES 710 [Tkv] $9407873511 047A $aSacherschließung maschinell aus paralleler Ausg. übernommen 047I $aExamining the general impact of the Controlled Languages rules in the context of Machine Translation has been an area of research for many years. The present study focuses on the following question: How do the Controlled Language (CL) rules impact the Machine Translation (MT) output individually? Analyzing a German corpus-based test suite of technical texts that have been translated into English by different MT systems, the study endeavors to answer this question at different levels: the general impact of CL rules (rule- and system-independent), their impact at rule level (system-independent), their impact at system level (rule-independent), and at rule and system level. The results of five MT systems (a rule-based system, a statistical system, two differently constructed hybrid systems, and a neural system) are analyzed and contrasted. For this, a mixed-methods triangulation approach that includes error annotation, human evaluation, and automatic evaluation was applied. The data were analyzed both qualitatively and quantitatively based on the following parameters: number and type of MT errors, style and content quality, and scores from two automatic evaluation metrics. In line with many studies, the results show a general positive impact of the applied CL rules on the MT output. However, at rule level, only four rules proved to have positive effects on all parameters; three rules had negative effects on the parameters; and two rules did not show any significant impact. At rule and system level, the rules affected the MT systems differently, as expected. Some rules that had a positive impact on earlier MT approaches did not show the same impact on the neural MT approach. Furthermore, the neural MT delivered distinctly better results than earlier MT approaches, namely the highest error-free, style and content quality rates both before and after the rules application, which indicates that the neural MT offers a promising solution that no longer requires CL rules for improving the MT output, what in turn allows for a more natural style. lok: 53099096 3 exp: 53099096 3 1 #EPN 201B/01 $029-06-25 $t00:20:13.581 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262691 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 5 exp: 53099096 5 1 #EPN 201B/01 $015-08-25 $t07:15:02.000 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262705 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 8 exp: 53099096 8 1 #EPN 201B/01 $029-06-25 $t00:20:13.587 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262713 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 10 exp: 53099096 10 1 #EPN 201B/01 $029-06-25 $t00:20:13.590 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262721 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 11 exp: 53099096 11 1 #EPN 201B/01 $029-06-25 $t00:20:13.593 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $0130926273X 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 13 exp: 53099096 13 1 #EPN 201B/01 $029-06-25 $t00:20:13.595 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262748 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 20 exp: 53099096 20 1 #EPN 201B/01 $029-06-25 $t00:20:13.598 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262756 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 21 exp: 53099096 21 1 #EPN 201B/01 $029-06-25 $t00:20:13.600 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262764 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 23 exp: 53099096 23 1 #EPN 201B/01 $029-06-25 $t00:20:13.603 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262772 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 24 exp: 53099096 24 1 #EPN 201B/01 $029-06-25 $t00:20:13.605 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262780 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 25 exp: 53099096 25 1 #EPN 201B/01 $029-06-25 $t00:20:13.608 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262799 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 36 exp: 53099096 36 1 #EPN 201B/01 $029-06-25 $t00:20:13.611 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262802 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 49 exp: 53099096 49 1 #EPN 201B/01 $029-06-25 $t00:20:13.614 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262810 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 51 exp: 53099096 51 1 #EPN 201B/01 $029-06-25 $t00:20:13.617 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262829 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 59 exp: 53099096 59 1 #EPN 201B/01 $029-06-25 $t00:20:13.619 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262837 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 74 exp: 53099096 74 1 #EPN 201B/01 $029-06-25 $t00:20:13.622 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262845 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 76 exp: 53099096 76 1 #EPN 201B/01 $029-06-25 $t00:20:13.625 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262853 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 107 exp: 53099096 107 1 #EPN 201B/01 $029-06-25 $t00:20:13.628 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262861 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 108 exp: 53099096 108 1 #EPN 201B/01 $029-06-25 $t00:20:13.630 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $0130926287X 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 204 exp: 53099096 204 1 #EPN 201B/01 $029-06-25 $t00:20:13.634 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262888 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR lok: 53099096 205 exp: 53099096 205 1 #EPN 201B/01 $029-06-25 $t00:20:13.636 201C/01 $028-06-25 201U/01 $0utf8 203@/01 $01309262896 208@/01 $a28-06-25 $bl 209S/01 $S0 $uhttps://library.oapen.org/handle/20.500.12657/61708 $XR
| LEADER | 00000cam a22000002c 4500 | ||
|---|---|---|---|
| 001 | 530990962 | ||
| 003 | DE-603 | ||
| 005 | 20250815071502.0 | ||
| 007 | cr|||||||||||| | ||
| 008 | 250626s2022 xx |||| om u00||u|eng c | ||
| 020 | |a 9783961103942 | ||
| 020 | |a 9783985540525 | ||
| 024 | 7 | |a 20.500.12657/61708 |2 hdl | |
| 035 | |a (DE-599)HEB530990962 | ||
| 040 | |a DE-603 |b ger |c DE-603 |d DE-603 | ||
| 041 | |a eng | ||
| 084 | |a 020 |a 004 |a 400 |q DE-101 |2 sdnb | ||
| 084 | |a ES 710 |0 (DE-625)27878: |0 (DE-603)407873511 |2 rvk | ||
| 245 | 0 | 0 | |a Sprachkontrolle im Spiegel der Maschinellen Übersetzung |b Untersuchung zur Wechselwirkung ausgewählter Regeln der Kontrollierten Sprache mit verschiedenen Ansätzen der Maschinellen Übersetzung |
| 264 | 1 | |a [Erscheinungsort nicht ermittelbar] |b Language Science Press ; Language Science Press [Imprint] |c 2022 | |
| 264 | 2 | |a The Hague |b Oapen Foundation | |
| 300 | |a 1 Online-Ressource | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Examining the general impact of the Controlled Languages rules in the context of Machine Translation has been an area of research for many years. The present study focuses on the following question: How do the Controlled Language (CL) rules impact the Machine Translation (MT) output individually? Analyzing a German corpus-based test suite of technical texts that have been translated into English by different MT systems, the study endeavors to answer this question at different levels: the general impact of CL rules (rule- and system-independent), their impact at rule level (system-independent), their impact at system level (rule-independent), and at rule and system level. The results of five MT systems (a rule-based system, a statistical system, two differently constructed hybrid systems, and a neural system) are analyzed and contrasted. For this, a mixed-methods triangulation approach that includes error annotation, human evaluation, and automatic evaluation was applied. The data were analyzed both qualitatively and quantitatively based on the following parameters: number and type of MT errors, style and content quality, and scores from two automatic evaluation metrics. In line with many studies, the results show a general positive impact of the applied CL rules on the MT output. However, at rule level, only four rules proved to have positive effects on all parameters; three rules had negative effects on the parameters; and two rules did not show any significant impact. At rule and system level, the rules affected the MT systems differently, as expected. Some rules that had a positive impact on earlier MT approaches did not show the same impact on the neural MT approach. Furthermore, the neural MT delivered distinctly better results than earlier MT approaches, namely the highest error-free, style and content quality rates both before and after the rules application, which indicates that the neural MT offers a promising solution that no longer requires CL rules for improving the MT output, what in turn allows for a more natural style. | ||
| 650 | 7 | |a Maschinelle Übersetzung |0 (DE-588)4003966-3 |0 (DE-603)085002364 |2 gnd | |
| 650 | 7 | |a Terminologische Kontrolle |0 (DE-588)4136260-3 |0 (DE-603)085505943 |2 gnd | |
| 655 | 7 | |a Hochschulschrift |2 gnd-content |0 (DE-588)4113937-9 |0 (DE-603)085338818 | |
| 700 | 1 | |a Marzouk, Shaimaa |e Herausgeber |4 edt | |
| 856 | |u https://library.oapen.org/handle/20.500.12657/61708 |x Resolving-System |z kostenfrei | ||
| 912 | |a ZDB-94-OAL | ||
| 924 | 1 | |9 603 |a (DE-603)1309262691 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262705 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262713 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262721 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)130926273X |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262748 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262756 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262764 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262772 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262780 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262799 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262802 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262810 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262829 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262837 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262845 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262853 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262861 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)130926287X |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262888 |b DE-603 |c HES |d d | |
| 924 | 1 | |9 603 |a (DE-603)1309262896 |b DE-603 |c HES |d d | |
