Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020
Recent advancements in Neural Machine Translation (NMT) models have proved to produce a state of the art results on machine translation for low resource Indian languages. This paper describes the neural machine translation systems for the English-Hindi language presented in AdapMT Shared Task ICON 2...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Joshi, Ramchandra Karnavat, Rushabh Jirapure, Kaustubh Joshi, Raviraj |
| description | Recent advancements in Neural Machine Translation (NMT) models have proved to
produce a state of the art results on machine translation for low resource
Indian languages. This paper describes the neural machine translation systems
for the English-Hindi language presented in AdapMT Shared Task ICON 2020. The
shared task aims to build a translation system for Indian languages in specific
domains like Artificial Intelligence (AI) and Chemistry using a small in-domain
parallel corpus. We evaluated the effectiveness of two popular NMT models i.e,
LSTM, and Transformer architectures for the English-Hindi machine translation
task based on BLEU scores. We train these models primarily using the out of
domain data and employ simple domain adaptation techniques based on the
characteristics of the in-domain dataset. The fine-tuning and mixed-domain data
approaches are used for domain adaptation. Our team was ranked first in the
chemistry and general domain En-Hi translation task and second in the AI domain
En-Hi translation task. |
| doi_str_mv | 10.48550/arxiv.2012.12112 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2012_12112</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2012_12112</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-f36622ee2be5d6dc2314979e31807a6d69e8183a87e22cf938f9bcde69b9b55d3</originalsourceid><addsrcrecordid>eNotj71OwzAYAL0woJYHYMIvkGB_bhx7rEKhlfqzZCb6EtvUamJXcYTg7YGU6aY76Qh55CxfqaJgzzh--c8cGIecA-dwT95f4oA-0LXB64STj4FGR4-Hmg7R2D5RF0e6CR-9T-ds64Px9IDd2QdL6xFD6m9OjelCcZozv-6uOh0pMGBLcuewT_bhnwtSv27qapvtT2-7ar3PUJaQOSElgLXQ2sJI04HgK11qK7hiJUojtVVcCVSlBeicFsrptjNW6la3RWHEgjzdsvNgcx39gON38zfazKPiB2dkTAU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020</title><source>arXiv.org</source><creator>Joshi, Ramchandra ; Karnavat, Rushabh ; Jirapure, Kaustubh ; Joshi, Raviraj</creator><creatorcontrib>Joshi, Ramchandra ; Karnavat, Rushabh ; Jirapure, Kaustubh ; Joshi, Raviraj</creatorcontrib><description>Recent advancements in Neural Machine Translation (NMT) models have proved to
produce a state of the art results on machine translation for low resource
Indian languages. This paper describes the neural machine translation systems
for the English-Hindi language presented in AdapMT Shared Task ICON 2020. The
shared task aims to build a translation system for Indian languages in specific
domains like Artificial Intelligence (AI) and Chemistry using a small in-domain
parallel corpus. We evaluated the effectiveness of two popular NMT models i.e,
LSTM, and Transformer architectures for the English-Hindi machine translation
task based on BLEU scores. We train these models primarily using the out of
domain data and employ simple domain adaptation techniques based on the
characteristics of the in-domain dataset. The fine-tuning and mixed-domain data
approaches are used for domain adaptation. Our team was ranked first in the
chemistry and general domain En-Hi translation task and second in the AI domain
En-Hi translation task.</description><identifier>DOI: 10.48550/arxiv.2012.12112</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2020-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2012.12112$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2012.12112$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Joshi, Ramchandra</creatorcontrib><creatorcontrib>Karnavat, Rushabh</creatorcontrib><creatorcontrib>Jirapure, Kaustubh</creatorcontrib><creatorcontrib>Joshi, Raviraj</creatorcontrib><title>Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020</title><description>Recent advancements in Neural Machine Translation (NMT) models have proved to
produce a state of the art results on machine translation for low resource
Indian languages. This paper describes the neural machine translation systems
for the English-Hindi language presented in AdapMT Shared Task ICON 2020. The
shared task aims to build a translation system for Indian languages in specific
domains like Artificial Intelligence (AI) and Chemistry using a small in-domain
parallel corpus. We evaluated the effectiveness of two popular NMT models i.e,
LSTM, and Transformer architectures for the English-Hindi machine translation
task based on BLEU scores. We train these models primarily using the out of
domain data and employ simple domain adaptation techniques based on the
characteristics of the in-domain dataset. The fine-tuning and mixed-domain data
approaches are used for domain adaptation. Our team was ranked first in the
chemistry and general domain En-Hi translation task and second in the AI domain
En-Hi translation task.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71OwzAYAL0woJYHYMIvkGB_bhx7rEKhlfqzZCb6EtvUamJXcYTg7YGU6aY76Qh55CxfqaJgzzh--c8cGIecA-dwT95f4oA-0LXB64STj4FGR4-Hmg7R2D5RF0e6CR-9T-ds64Px9IDd2QdL6xFD6m9OjelCcZozv-6uOh0pMGBLcuewT_bhnwtSv27qapvtT2-7ar3PUJaQOSElgLXQ2sJI04HgK11qK7hiJUojtVVcCVSlBeicFsrptjNW6la3RWHEgjzdsvNgcx39gON38zfazKPiB2dkTAU</recordid><startdate>20201222</startdate><enddate>20201222</enddate><creator>Joshi, Ramchandra</creator><creator>Karnavat, Rushabh</creator><creator>Jirapure, Kaustubh</creator><creator>Joshi, Raviraj</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201222</creationdate><title>Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020</title><author>Joshi, Ramchandra ; Karnavat, Rushabh ; Jirapure, Kaustubh ; Joshi, Raviraj</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-f36622ee2be5d6dc2314979e31807a6d69e8183a87e22cf938f9bcde69b9b55d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Joshi, Ramchandra</creatorcontrib><creatorcontrib>Karnavat, Rushabh</creatorcontrib><creatorcontrib>Jirapure, Kaustubh</creatorcontrib><creatorcontrib>Joshi, Raviraj</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Joshi, Ramchandra</au><au>Karnavat, Rushabh</au><au>Jirapure, Kaustubh</au><au>Joshi, Raviraj</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020</atitle><date>2020-12-22</date><risdate>2020</risdate><abstract>Recent advancements in Neural Machine Translation (NMT) models have proved to
produce a state of the art results on machine translation for low resource
Indian languages. This paper describes the neural machine translation systems
for the English-Hindi language presented in AdapMT Shared Task ICON 2020. The
shared task aims to build a translation system for Indian languages in specific
domains like Artificial Intelligence (AI) and Chemistry using a small in-domain
parallel corpus. We evaluated the effectiveness of two popular NMT models i.e,
LSTM, and Transformer architectures for the English-Hindi machine translation
task based on BLEU scores. We train these models primarily using the out of
domain data and employ simple domain adaptation techniques based on the
characteristics of the in-domain dataset. The fine-tuning and mixed-domain data
approaches are used for domain adaptation. Our team was ranked first in the
chemistry and general domain En-Hi translation task and second in the AI domain
En-Hi translation task.</abstract><doi>10.48550/arxiv.2012.12112</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2012.12112 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2012_12112 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language Computer Science - Learning |
| title | Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020 |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T05%3A14%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Domain%20Adaptation%20of%20NMT%20models%20for%20English-Hindi%20Machine%20Translation%20Task%20at%20AdapMT%20ICON%202020&rft.au=Joshi,%20Ramchandra&rft.date=2020-12-22&rft_id=info:doi/10.48550/arxiv.2012.12112&rft_dat=%3Carxiv_GOX%3E2012_12112%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |