An empirical study of low-resource neural machine translation of manipuri in multilingual settings
Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and ther...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Singh, Salam Michael [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Neural computing & applications - Springer London, 1993, 34(2022), 17 vom: 13. Mai, Seite 14823-14844 |
|---|---|
| Übergeordnetes Werk: |
volume:34 ; year:2022 ; number:17 ; day:13 ; month:05 ; pages:14823-14844 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00521-022-07337-8 |
|---|
| Katalog-ID: |
OLC2079345478 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2079345478 | ||
| 003 | DE-627 | ||
| 005 | 20230506053809.0 | ||
| 007 | tu | ||
| 008 | 221220s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00521-022-07337-8 |2 doi | |
| 035 | |a (DE-627)OLC2079345478 | ||
| 035 | |a (DE-He213)s00521-022-07337-8-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 100 | 1 | |a Singh, Salam Michael |e verfasserin |0 (orcid)0000-0002-2249-6081 |4 aut | |
| 245 | 1 | 0 | |a An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 | ||
| 520 | |a Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. | ||
| 650 | 4 | |a Neural machine translation | |
| 650 | 4 | |a Multilingual neural machine translation for low resource | |
| 650 | 4 | |a Cross-lingual embedding | |
| 650 | 4 | |a Manipuri | |
| 700 | 1 | |a Singh, Thoudam Doren |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d Springer London, 1993 |g 34(2022), 17 vom: 13. Mai, Seite 14823-14844 |w (DE-627)165669608 |w (DE-600)1136944-9 |w (DE-576)032873050 |x 0941-0643 |7 nnns |
| 773 | 1 | 8 | |g volume:34 |g year:2022 |g number:17 |g day:13 |g month:05 |g pages:14823-14844 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00521-022-07337-8 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 34 |j 2022 |e 17 |b 13 |c 05 |h 14823-14844 | ||
| author_variant |
s m s sm sms t d s td tds |
|---|---|
| matchkey_str |
article:09410643:2022----::nmiiasuyforsucnuamciernltoomnpr |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s00521-022-07337-8 doi (DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p DE-627 ger DE-627 rakwb eng 004 VZ Singh, Salam Michael verfasserin (orcid)0000-0002-2249-6081 aut An empirical study of low-resource neural machine translation of manipuri in multilingual settings 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri Singh, Thoudam Doren aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 17 vom: 13. Mai, Seite 14823-14844 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 https://doi.org/10.1007/s00521-022-07337-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 17 13 05 14823-14844 |
| spelling |
10.1007/s00521-022-07337-8 doi (DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p DE-627 ger DE-627 rakwb eng 004 VZ Singh, Salam Michael verfasserin (orcid)0000-0002-2249-6081 aut An empirical study of low-resource neural machine translation of manipuri in multilingual settings 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri Singh, Thoudam Doren aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 17 vom: 13. Mai, Seite 14823-14844 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 https://doi.org/10.1007/s00521-022-07337-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 17 13 05 14823-14844 |
| allfields_unstemmed |
10.1007/s00521-022-07337-8 doi (DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p DE-627 ger DE-627 rakwb eng 004 VZ Singh, Salam Michael verfasserin (orcid)0000-0002-2249-6081 aut An empirical study of low-resource neural machine translation of manipuri in multilingual settings 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri Singh, Thoudam Doren aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 17 vom: 13. Mai, Seite 14823-14844 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 https://doi.org/10.1007/s00521-022-07337-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 17 13 05 14823-14844 |
| allfieldsGer |
10.1007/s00521-022-07337-8 doi (DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p DE-627 ger DE-627 rakwb eng 004 VZ Singh, Salam Michael verfasserin (orcid)0000-0002-2249-6081 aut An empirical study of low-resource neural machine translation of manipuri in multilingual settings 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri Singh, Thoudam Doren aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 17 vom: 13. Mai, Seite 14823-14844 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 https://doi.org/10.1007/s00521-022-07337-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 17 13 05 14823-14844 |
| allfieldsSound |
10.1007/s00521-022-07337-8 doi (DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p DE-627 ger DE-627 rakwb eng 004 VZ Singh, Salam Michael verfasserin (orcid)0000-0002-2249-6081 aut An empirical study of low-resource neural machine translation of manipuri in multilingual settings 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri Singh, Thoudam Doren aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 17 vom: 13. Mai, Seite 14823-14844 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 https://doi.org/10.1007/s00521-022-07337-8 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 17 13 05 14823-14844 |
| language |
English |
| source |
Enthalten in Neural computing & applications 34(2022), 17 vom: 13. Mai, Seite 14823-14844 volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 |
| sourceStr |
Enthalten in Neural computing & applications 34(2022), 17 vom: 13. Mai, Seite 14823-14844 volume:34 year:2022 number:17 day:13 month:05 pages:14823-14844 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Neural computing & applications |
| authorswithroles_txt_mv |
Singh, Salam Michael @@aut@@ Singh, Thoudam Doren @@aut@@ |
| publishDateDaySort_date |
2022-05-13T00:00:00Z |
| hierarchy_top_id |
165669608 |
| dewey-sort |
14 |
| id |
OLC2079345478 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2079345478</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506053809.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-022-07337-8</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2079345478</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-022-07337-8-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Singh, Salam Michael</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-2249-6081</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An empirical study of low-resource neural machine translation of manipuri in multilingual settings</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neural machine translation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multilingual neural machine translation for low resource</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-lingual embedding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Manipuri</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Singh, Thoudam Doren</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2022), 17 vom: 13. Mai, Seite 14823-14844</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:17</subfield><subfield code="g">day:13</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:14823-14844</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-022-07337-8</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2022</subfield><subfield code="e">17</subfield><subfield code="b">13</subfield><subfield code="c">05</subfield><subfield code="h">14823-14844</subfield></datafield></record></collection>
|
| author |
Singh, Salam Michael |
| spellingShingle |
Singh, Salam Michael ddc 004 misc Neural machine translation misc Multilingual neural machine translation for low resource misc Cross-lingual embedding misc Manipuri An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| authorStr |
Singh, Salam Michael |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)165669608 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0941-0643 |
| topic_title |
004 VZ An empirical study of low-resource neural machine translation of manipuri in multilingual settings Neural machine translation Multilingual neural machine translation for low resource Cross-lingual embedding Manipuri |
| topic |
ddc 004 misc Neural machine translation misc Multilingual neural machine translation for low resource misc Cross-lingual embedding misc Manipuri |
| topic_unstemmed |
ddc 004 misc Neural machine translation misc Multilingual neural machine translation for low resource misc Cross-lingual embedding misc Manipuri |
| topic_browse |
ddc 004 misc Neural machine translation misc Multilingual neural machine translation for low resource misc Cross-lingual embedding misc Manipuri |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Neural computing & applications |
| hierarchy_parent_id |
165669608 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Neural computing & applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 |
| title |
An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| ctrlnum |
(DE-627)OLC2079345478 (DE-He213)s00521-022-07337-8-p |
| title_full |
An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| author_sort |
Singh, Salam Michael |
| journal |
Neural computing & applications |
| journalStr |
Neural computing & applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
14823 |
| author_browse |
Singh, Salam Michael Singh, Thoudam Doren |
| container_volume |
34 |
| class |
004 VZ |
| format_se |
Aufsätze |
| author-letter |
Singh, Salam Michael |
| doi_str_mv |
10.1007/s00521-022-07337-8 |
| normlink |
(ORCID)0000-0002-2249-6081 |
| normlink_prefix_str_mv |
(orcid)0000-0002-2249-6081 |
| dewey-full |
004 |
| title_sort |
an empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| title_auth |
An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| abstract |
Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 |
| abstractGer |
Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 |
| abstract_unstemmed |
Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
17 |
| title_short |
An empirical study of low-resource neural machine translation of manipuri in multilingual settings |
| url |
https://doi.org/10.1007/s00521-022-07337-8 |
| remote_bool |
false |
| author2 |
Singh, Thoudam Doren |
| author2Str |
Singh, Thoudam Doren |
| ppnlink |
165669608 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00521-022-07337-8 |
| up_date |
2024-07-04T00:33:43.084Z |
| _version_ |
1803606528449576960 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2079345478</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506053809.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-022-07337-8</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2079345478</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-022-07337-8-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Singh, Salam Michael</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-2249-6081</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An empirical study of low-resource neural machine translation of manipuri in multilingual settings</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Machine translation requires a large amount of parallel data for a production level of translation quality. This is one of the significant factors behind the lack of machine translation systems for most spoken/written languages. Likewise, Manipuri is a low resource Indian language, and there is very little digital textual available data for the same. In this work, we attempt to address the low resource neural machine translation for Manipuri and English using other Indian languages in a multilingual setup. We train an LSTM based many-to-many multilingual neural machine translation system that is infused with cross-lingual features. Experimental results show that our method improves over the vanilla many-to-many multilingual and bilingual baselines for both Manipuri to/from English translation tasks. Furthermore, our method also improves over the vanilla many-to-many multilingual system for the translation task of all the other Indian languages to/from English. We also examine the generalizability of our multilingual model by evaluating the translation among the language pairs which do not have a direct link via the zero-shot translation and compare it against the pivot-based translation.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neural machine translation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multilingual neural machine translation for low resource</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-lingual embedding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Manipuri</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Singh, Thoudam Doren</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2022), 17 vom: 13. Mai, Seite 14823-14844</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:17</subfield><subfield code="g">day:13</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:14823-14844</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-022-07337-8</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2022</subfield><subfield code="e">17</subfield><subfield code="b">13</subfield><subfield code="c">05</subfield><subfield code="h">14823-14844</subfield></datafield></record></collection>
|
| score |
7.401025 |