Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs Article Swipe
Amr Hendy
,
Esraa A. Gad
,
Mohamed Abdelghaffar
,
Jailan S. ElMosalami
,
Mohamed Afify
,
Ahmed Y. Tawfik
,
Hany Hassan Awadalla
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.13284
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.13284
This paper describes our submission to the constrained track of WMT21 shared news translation task. We focus on the three relatively low resource language pairs Bengali to and from Hindi, English to and from Hausa, and Xhosa to and from Zulu. To overcome the limitation of relatively low parallel data we train a multilingual model using a multitask objective employing both parallel and monolingual data. In addition, we augment the data using back translation. We also train a bilingual model incorporating back translation and knowledge distillation then combine the two models using sequence-to-sequence mapping. We see around 70% relative gain in BLEU point for English to and from Hausa, and around 25% relative improvements for both Bengali to and from Hindi, and Xhosa to and from Zulu compared to bilingual baselines.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2111.13284
- https://arxiv.org/pdf/2111.13284
- OA Status
- green
- Cited By
- 1
- References
- 13
- OpenAlex ID
- https://openalex.org/W3217576620
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3217576620Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2111.13284Digital Object Identifier
- Title
-
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language PairsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-11-26Full publication date if available
- Authors
-
Amr Hendy, Esraa A. Gad, Mohamed Abdelghaffar, Jailan S. ElMosalami, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan AwadallaList of authors in order
- Landing page
-
https://arxiv.org/abs/2111.13284Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2111.13284Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2111.13284Direct OA link when available
- Concepts
-
Bengali, Zulu, Computer science, Task (project management), Natural language processing, Hindi, Artificial intelligence, Machine translation, Hausa, Xhosa, Focus (optics), Contrast (vision), WordNet, Linguistics, Management, Physics, Philosophy, Optics, EconomicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- References (count)
-
13Number of works referenced by this work
Full payload
| id | https://openalex.org/W3217576620 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2111.13284 |
| ids.doi | https://doi.org/10.48550/arxiv.2111.13284 |
| ids.mag | 3217576620 |
| ids.openalex | https://openalex.org/W3217576620 |
| fwci | |
| type | preprint |
| title | Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10028 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9994999766349792 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Topic Modeling |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9966999888420105 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C19235068 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8894577026367188 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q9610 |
| concepts[0].display_name | Bengali |
| concepts[1].id | https://openalex.org/C2778105672 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7822465896606445 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q10179 |
| concepts[1].display_name | Zulu |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.7812983393669128 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C2780451532 |
| concepts[3].level | 2 |
| concepts[3].score | 0.691043496131897 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[3].display_name | Task (project management) |
| concepts[4].id | https://openalex.org/C204321447 |
| concepts[4].level | 1 |
| concepts[4].score | 0.6901291608810425 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[4].display_name | Natural language processing |
| concepts[5].id | https://openalex.org/C519982507 |
| concepts[5].level | 2 |
| concepts[5].score | 0.674736738204956 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1568 |
| concepts[5].display_name | Hindi |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.6413190364837646 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C203005215 |
| concepts[7].level | 2 |
| concepts[7].score | 0.624055027961731 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q79798 |
| concepts[7].display_name | Machine translation |
| concepts[8].id | https://openalex.org/C153924320 |
| concepts[8].level | 2 |
| concepts[8].score | 0.6085870265960693 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q56475 |
| concepts[8].display_name | Hausa |
| concepts[9].id | https://openalex.org/C2777578687 |
| concepts[9].level | 2 |
| concepts[9].score | 0.5754446983337402 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q13218 |
| concepts[9].display_name | Xhosa |
| concepts[10].id | https://openalex.org/C192209626 |
| concepts[10].level | 2 |
| concepts[10].score | 0.556108832359314 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q190909 |
| concepts[10].display_name | Focus (optics) |
| concepts[11].id | https://openalex.org/C2776502983 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4286682605743408 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q690182 |
| concepts[11].display_name | Contrast (vision) |
| concepts[12].id | https://openalex.org/C157659113 |
| concepts[12].level | 2 |
| concepts[12].score | 0.4235479235649109 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q533822 |
| concepts[12].display_name | WordNet |
| concepts[13].id | https://openalex.org/C41895202 |
| concepts[13].level | 1 |
| concepts[13].score | 0.32622092962265015 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[13].display_name | Linguistics |
| concepts[14].id | https://openalex.org/C187736073 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[14].display_name | Management |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C138885662 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[16].display_name | Philosophy |
| concepts[17].id | https://openalex.org/C120665830 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[17].display_name | Optics |
| concepts[18].id | https://openalex.org/C162324750 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[18].display_name | Economics |
| keywords[0].id | https://openalex.org/keywords/bengali |
| keywords[0].score | 0.8894577026367188 |
| keywords[0].display_name | Bengali |
| keywords[1].id | https://openalex.org/keywords/zulu |
| keywords[1].score | 0.7822465896606445 |
| keywords[1].display_name | Zulu |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.7812983393669128 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/task |
| keywords[3].score | 0.691043496131897 |
| keywords[3].display_name | Task (project management) |
| keywords[4].id | https://openalex.org/keywords/natural-language-processing |
| keywords[4].score | 0.6901291608810425 |
| keywords[4].display_name | Natural language processing |
| keywords[5].id | https://openalex.org/keywords/hindi |
| keywords[5].score | 0.674736738204956 |
| keywords[5].display_name | Hindi |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.6413190364837646 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/machine-translation |
| keywords[7].score | 0.624055027961731 |
| keywords[7].display_name | Machine translation |
| keywords[8].id | https://openalex.org/keywords/hausa |
| keywords[8].score | 0.6085870265960693 |
| keywords[8].display_name | Hausa |
| keywords[9].id | https://openalex.org/keywords/xhosa |
| keywords[9].score | 0.5754446983337402 |
| keywords[9].display_name | Xhosa |
| keywords[10].id | https://openalex.org/keywords/focus |
| keywords[10].score | 0.556108832359314 |
| keywords[10].display_name | Focus (optics) |
| keywords[11].id | https://openalex.org/keywords/contrast |
| keywords[11].score | 0.4286682605743408 |
| keywords[11].display_name | Contrast (vision) |
| keywords[12].id | https://openalex.org/keywords/wordnet |
| keywords[12].score | 0.4235479235649109 |
| keywords[12].display_name | WordNet |
| keywords[13].id | https://openalex.org/keywords/linguistics |
| keywords[13].score | 0.32622092962265015 |
| keywords[13].display_name | Linguistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2111.13284 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2111.13284 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2111.13284 |
| locations[1].id | mag:3217576620 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | arXiv (Cornell University) |
| locations[1].landing_page_url | http://export.arxiv.org/pdf/2111.13284v1 |
| locations[2].id | doi:10.48550/arxiv.2111.13284 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2111.13284 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5007758583 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Amr Hendy |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[0].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[0].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[0].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Amr Hendy |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | (Microsoft) |
| authorships[1].author.id | https://openalex.org/A5064043933 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Esraa A. Gad |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[1].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[1].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[1].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Esraa A. Gad |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | (Microsoft) |
| authorships[2].author.id | https://openalex.org/A5040098231 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Mohamed Abdelghaffar |
| authorships[2].countries | GB |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[2].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[2].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[2].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[2].institutions[0].country_code | GB |
| authorships[2].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Mohamed Abdelghaffar |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | (Microsoft) |
| authorships[3].author.id | https://openalex.org/A5020195877 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Jailan S. ElMosalami |
| authorships[3].countries | GB |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[3].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[3].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[3].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[3].institutions[0].type | company |
| authorships[3].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[3].institutions[0].country_code | GB |
| authorships[3].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jailan S. ElMosalami |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | (Microsoft) |
| authorships[4].author.id | https://openalex.org/A5021938376 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4445-9767 |
| authorships[4].author.display_name | Mohamed Afify |
| authorships[4].countries | GB |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[4].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[4].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[4].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[4].institutions[0].type | company |
| authorships[4].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[4].institutions[0].country_code | GB |
| authorships[4].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Mohamed Afify |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | (Microsoft) |
| authorships[5].author.id | https://openalex.org/A5048873489 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-3561-3248 |
| authorships[5].author.display_name | Ahmed Y. Tawfik |
| authorships[5].countries | GB |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[5].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[5].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[5].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[5].institutions[0].type | company |
| authorships[5].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[5].institutions[0].country_code | GB |
| authorships[5].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Ahmed Y. Tawfik |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | (Microsoft) |
| authorships[6].author.id | https://openalex.org/A5030937723 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Hany Hassan Awadalla |
| authorships[6].countries | GB |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[6].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[6].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[6].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[6].institutions[0].type | company |
| authorships[6].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[6].institutions[0].country_code | GB |
| authorships[6].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Hany Hassan Awadalla |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | (Microsoft) |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2111.13284 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Natural Language Processing Techniques |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2111.13284 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2111.13284 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2111.13284 |
| primary_location.id | pmh:oai:arXiv.org:2111.13284 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2111.13284 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2111.13284 |
| publication_date | 2021-11-26 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W3105214104, https://openalex.org/W2963247703, https://openalex.org/W2555745756, https://openalex.org/W2885250264, https://openalex.org/W2251743902, https://openalex.org/W2963250244, https://openalex.org/W2963532001, https://openalex.org/W3107826490, https://openalex.org/W3120929527, https://openalex.org/W2587694128, https://openalex.org/W2550821151, https://openalex.org/W2963216553, https://openalex.org/W3105038888 |
| referenced_works_count | 13 |
| abstract_inverted_index.a | 52, 56, 77 |
| abstract_inverted_index.In | 65 |
| abstract_inverted_index.To | 41 |
| abstract_inverted_index.We | 15, 74, 94 |
| abstract_inverted_index.in | 100 |
| abstract_inverted_index.of | 9, 45 |
| abstract_inverted_index.on | 17 |
| abstract_inverted_index.to | 5, 26, 31, 37, 105, 117, 123, 128 |
| abstract_inverted_index.we | 50, 67 |
| abstract_inverted_index.25% | 111 |
| abstract_inverted_index.70% | 97 |
| abstract_inverted_index.and | 27, 32, 35, 38, 62, 83, 106, 109, 118, 121, 124 |
| abstract_inverted_index.for | 103, 114 |
| abstract_inverted_index.low | 21, 47 |
| abstract_inverted_index.our | 3 |
| abstract_inverted_index.see | 95 |
| abstract_inverted_index.the | 6, 18, 43, 69, 88 |
| abstract_inverted_index.two | 89 |
| abstract_inverted_index.BLEU | 101 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.Zulu | 126 |
| abstract_inverted_index.also | 75 |
| abstract_inverted_index.back | 72, 81 |
| abstract_inverted_index.both | 60, 115 |
| abstract_inverted_index.data | 49, 70 |
| abstract_inverted_index.from | 28, 33, 39, 107, 119, 125 |
| abstract_inverted_index.gain | 99 |
| abstract_inverted_index.news | 12 |
| abstract_inverted_index.then | 86 |
| abstract_inverted_index.WMT21 | 10 |
| abstract_inverted_index.Xhosa | 36, 122 |
| abstract_inverted_index.Zulu. | 40 |
| abstract_inverted_index.data. | 64 |
| abstract_inverted_index.focus | 16 |
| abstract_inverted_index.model | 54, 79 |
| abstract_inverted_index.pairs | 24 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.point | 102 |
| abstract_inverted_index.task. | 14 |
| abstract_inverted_index.three | 19 |
| abstract_inverted_index.track | 8 |
| abstract_inverted_index.train | 51, 76 |
| abstract_inverted_index.using | 55, 71, 91 |
| abstract_inverted_index.Hausa, | 34, 108 |
| abstract_inverted_index.Hindi, | 29, 120 |
| abstract_inverted_index.around | 96, 110 |
| abstract_inverted_index.models | 90 |
| abstract_inverted_index.shared | 11 |
| abstract_inverted_index.Bengali | 25, 116 |
| abstract_inverted_index.English | 30, 104 |
| abstract_inverted_index.augment | 68 |
| abstract_inverted_index.combine | 87 |
| abstract_inverted_index.compared | 127 |
| abstract_inverted_index.language | 23 |
| abstract_inverted_index.mapping. | 93 |
| abstract_inverted_index.overcome | 42 |
| abstract_inverted_index.parallel | 48, 61 |
| abstract_inverted_index.relative | 98, 112 |
| abstract_inverted_index.resource | 22 |
| abstract_inverted_index.addition, | 66 |
| abstract_inverted_index.bilingual | 78, 129 |
| abstract_inverted_index.describes | 2 |
| abstract_inverted_index.employing | 59 |
| abstract_inverted_index.knowledge | 84 |
| abstract_inverted_index.multitask | 57 |
| abstract_inverted_index.objective | 58 |
| abstract_inverted_index.baselines. | 130 |
| abstract_inverted_index.limitation | 44 |
| abstract_inverted_index.relatively | 20, 46 |
| abstract_inverted_index.submission | 4 |
| abstract_inverted_index.constrained | 7 |
| abstract_inverted_index.monolingual | 63 |
| abstract_inverted_index.translation | 13, 82 |
| abstract_inverted_index.distillation | 85 |
| abstract_inverted_index.improvements | 113 |
| abstract_inverted_index.multilingual | 53 |
| abstract_inverted_index.translation. | 73 |
| abstract_inverted_index.incorporating | 80 |
| abstract_inverted_index.sequence-to-sequence | 92 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8399999737739563 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |