Zeroshot Crosslingual Transfer of a Gloss Language Model for Semantic Change Detection Article Swipe
Maxim Rachinskiy
,
Nikolay Arefyev
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.28995/2075-7182-2021-20-578-586
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.28995/2075-7182-2021-20-578-586
Consulting word definitions from a dictionary is a familiar way for a human to find out which senses a particular word has.We hypothesize that a system that can select a proper definition for a particular word occurrence can also naturally solve Semantic Change Detection (SCD) task.To verify our hypothesis, we followed an approach previously proposed for Word Sense Disambiguation (WSD) and trained a system that embeds word definitions and word occurrences into the same vector space.In this space, the embedding of the most appropriate definition has the largest dot product with a contextualized word embedding.The system is trained on an English WSD corpus.To make it work for the Russian language, we replaced BERT with the multilingual XLMR language model and exploited its zeroshot crosslingual transferability.Despite not finetuning the encoder model on any Russian data, this system achieves the second place in the competition, and likely works for any of one hundred other languages XLMR was pretrained on, though the performance may vary.We then measure the impact of such WSD pretraining and show that this procedure is crucial for our results.Since our model was trained to choose a proper definition for a word, we propose an algorithm for the interpretation and visualization of the semantic changes through time.By employing additional labeled data in Russian and training a simple regression model, that converts the distances between output contextualized embeddings into more humanlike scores of sense similarity between word occurrences, we further improve our results and achieve the first place in the competition.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.28995/2075-7182-2021-20-578-586
- https://doi.org/10.28995/2075-7182-2021-20-578-586
- OA Status
- bronze
- Cited By
- 5
- References
- 12
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3206615630
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3206615630Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.28995/2075-7182-2021-20-578-586Digital Object Identifier
- Title
-
Zeroshot Crosslingual Transfer of a Gloss Language Model for Semantic Change DetectionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-06-19Full publication date if available
- Authors
-
Maxim Rachinskiy, Nikolay ArefyevList of authors in order
- Landing page
-
https://doi.org/10.28995/2075-7182-2021-20-578-586Publisher landing page
- PDF URL
-
https://doi.org/10.28995/2075-7182-2021-20-578-586Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
bronzeOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.28995/2075-7182-2021-20-578-586Direct OA link when available
- Concepts
-
Computer science, Natural language processing, Artificial intelligence, Word (group theory), Word embedding, Semantic similarity, Encoder, Language model, Similarity (geometry), Embedding, Linguistics, Philosophy, Operating system, Image (mathematics)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
5Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 2, 2023: 3Per-year citation counts (last 5 years)
- References (count)
-
12Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3206615630 |
|---|---|
| doi | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| ids.doi | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| ids.mag | 3206615630 |
| ids.openalex | https://openalex.org/W3206615630 |
| fwci | 0.70551788 |
| type | article |
| title | Zeroshot Crosslingual Transfer of a Gloss Language Model for Semantic Change Detection |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 586 |
| biblio.first_page | 578 |
| 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 | 0.9991999864578247 |
| 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 | 0.9988999962806702 |
| 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/T12090 |
| topics[2].field.id | https://openalex.org/fields/33 |
| topics[2].field.display_name | Social Sciences |
| topics[2].score | 0.9922999739646912 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3316 |
| topics[2].subfield.display_name | Cultural Studies |
| topics[2].display_name | Language and cultural evolution |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8362892866134644 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C204321447 |
| concepts[1].level | 1 |
| concepts[1].score | 0.7508759498596191 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[1].display_name | Natural language processing |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6824299097061157 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C90805587 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6110633611679077 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q10944557 |
| concepts[3].display_name | Word (group theory) |
| concepts[4].id | https://openalex.org/C2777462759 |
| concepts[4].level | 3 |
| concepts[4].score | 0.48549845814704895 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q18395344 |
| concepts[4].display_name | Word embedding |
| concepts[5].id | https://openalex.org/C130318100 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4771444499492645 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2268914 |
| concepts[5].display_name | Semantic similarity |
| concepts[6].id | https://openalex.org/C118505674 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4485989511013031 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[6].display_name | Encoder |
| concepts[7].id | https://openalex.org/C137293760 |
| concepts[7].level | 2 |
| concepts[7].score | 0.44838759303092957 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[7].display_name | Language model |
| concepts[8].id | https://openalex.org/C103278499 |
| concepts[8].level | 3 |
| concepts[8].score | 0.42342591285705566 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q254465 |
| concepts[8].display_name | Similarity (geometry) |
| concepts[9].id | https://openalex.org/C41608201 |
| concepts[9].level | 2 |
| concepts[9].score | 0.36212265491485596 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[9].display_name | Embedding |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.1802065074443817 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C111919701 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[12].display_name | Operating system |
| concepts[13].id | https://openalex.org/C115961682 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[13].display_name | Image (mathematics) |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8362892866134644 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/natural-language-processing |
| keywords[1].score | 0.7508759498596191 |
| keywords[1].display_name | Natural language processing |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6824299097061157 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/word |
| keywords[3].score | 0.6110633611679077 |
| keywords[3].display_name | Word (group theory) |
| keywords[4].id | https://openalex.org/keywords/word-embedding |
| keywords[4].score | 0.48549845814704895 |
| keywords[4].display_name | Word embedding |
| keywords[5].id | https://openalex.org/keywords/semantic-similarity |
| keywords[5].score | 0.4771444499492645 |
| keywords[5].display_name | Semantic similarity |
| keywords[6].id | https://openalex.org/keywords/encoder |
| keywords[6].score | 0.4485989511013031 |
| keywords[6].display_name | Encoder |
| keywords[7].id | https://openalex.org/keywords/language-model |
| keywords[7].score | 0.44838759303092957 |
| keywords[7].display_name | Language model |
| keywords[8].id | https://openalex.org/keywords/similarity |
| keywords[8].score | 0.42342591285705566 |
| keywords[8].display_name | Similarity (geometry) |
| keywords[9].id | https://openalex.org/keywords/embedding |
| keywords[9].score | 0.36212265491485596 |
| keywords[9].display_name | Embedding |
| keywords[10].id | https://openalex.org/keywords/linguistics |
| keywords[10].score | 0.1802065074443817 |
| keywords[10].display_name | Linguistics |
| language | en |
| locations[0].id | doi:10.28995/2075-7182-2021-20-578-586 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4393918129 |
| locations[0].source.issn | 2075-7182 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 2075-7182 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Kompʹûternaâ lingvistika i intellektualʹnye tehnologii |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Computational Linguistics and Intellectual Technologies |
| locations[0].landing_page_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5047584522 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Maxim Rachinskiy |
| authorships[0].countries | RU |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I118501908 |
| authorships[0].affiliations[0].raw_affiliation_string | HSE University Moscow, Russia |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I118501908, https://openalex.org/I19880235 |
| authorships[0].affiliations[1].raw_affiliation_string | Lomonosov Moscow State University HSE University Moscow, Russia |
| authorships[0].affiliations[2].institution_ids | https://openalex.org/I4210141363 |
| authorships[0].affiliations[2].raw_affiliation_string | Samsung Research Center Russia |
| authorships[0].institutions[0].id | https://openalex.org/I19880235 |
| authorships[0].institutions[0].ror | https://ror.org/010pmpe69 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I19880235 |
| authorships[0].institutions[0].country_code | RU |
| authorships[0].institutions[0].display_name | Lomonosov Moscow State University |
| authorships[0].institutions[1].id | https://openalex.org/I118501908 |
| authorships[0].institutions[1].ror | https://ror.org/055f7t516 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I118501908 |
| authorships[0].institutions[1].country_code | RU |
| authorships[0].institutions[1].display_name | National Research University Higher School of Economics |
| authorships[0].institutions[2].id | https://openalex.org/I4210141363 |
| authorships[0].institutions[2].ror | https://ror.org/051an6p98 |
| authorships[0].institutions[2].type | company |
| authorships[0].institutions[2].lineage | https://openalex.org/I4210141363 |
| authorships[0].institutions[2].country_code | RU |
| authorships[0].institutions[2].display_name | Samsung (Russia) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Maxim Rachinskiy |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | HSE University Moscow, Russia, Lomonosov Moscow State University HSE University Moscow, Russia, Samsung Research Center Russia |
| authorships[1].author.id | https://openalex.org/A5047490968 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Nikolay Arefyev |
| authorships[1].countries | RU |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I118501908, https://openalex.org/I19880235 |
| authorships[1].affiliations[0].raw_affiliation_string | Lomonosov Moscow State University HSE University Moscow, Russia |
| authorships[1].affiliations[1].institution_ids | https://openalex.org/I118501908 |
| authorships[1].affiliations[1].raw_affiliation_string | HSE University Moscow, Russia |
| authorships[1].affiliations[2].institution_ids | https://openalex.org/I4210141363 |
| authorships[1].affiliations[2].raw_affiliation_string | Samsung Research Center Russia |
| authorships[1].institutions[0].id | https://openalex.org/I19880235 |
| authorships[1].institutions[0].ror | https://ror.org/010pmpe69 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I19880235 |
| authorships[1].institutions[0].country_code | RU |
| authorships[1].institutions[0].display_name | Lomonosov Moscow State University |
| authorships[1].institutions[1].id | https://openalex.org/I118501908 |
| authorships[1].institutions[1].ror | https://ror.org/055f7t516 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I118501908 |
| authorships[1].institutions[1].country_code | RU |
| authorships[1].institutions[1].display_name | National Research University Higher School of Economics |
| authorships[1].institutions[2].id | https://openalex.org/I4210141363 |
| authorships[1].institutions[2].ror | https://ror.org/051an6p98 |
| authorships[1].institutions[2].type | company |
| authorships[1].institutions[2].lineage | https://openalex.org/I4210141363 |
| authorships[1].institutions[2].country_code | RU |
| authorships[1].institutions[2].display_name | Samsung (Russia) |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Nikolay Arefyev |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | HSE University Moscow, Russia, Lomonosov Moscow State University HSE University Moscow, Russia, Samsung Research Center Russia |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| open_access.oa_status | bronze |
| open_access.any_repository_has_fulltext | False |
| created_date | 2021-10-25T00:00:00 |
| display_name | Zeroshot Crosslingual Transfer of a Gloss Language Model for Semantic Change Detection |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9991999864578247 |
| 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 |
| related_works | https://openalex.org/W2081900870, https://openalex.org/W4390516098, https://openalex.org/W2037549926, https://openalex.org/W2181948922, https://openalex.org/W4286432911, https://openalex.org/W2966570129, https://openalex.org/W3099449837, https://openalex.org/W2774861092, https://openalex.org/W4301351852, https://openalex.org/W2622845166 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 3 |
| locations_count | 1 |
| best_oa_location.id | doi:10.28995/2075-7182-2021-20-578-586 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4393918129 |
| best_oa_location.source.issn | 2075-7182 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 2075-7182 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Kompʹûternaâ lingvistika i intellektualʹnye tehnologii |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Computational Linguistics and Intellectual Technologies |
| best_oa_location.landing_page_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| primary_location.id | doi:10.28995/2075-7182-2021-20-578-586 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4393918129 |
| primary_location.source.issn | 2075-7182 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 2075-7182 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Kompʹûternaâ lingvistika i intellektualʹnye tehnologii |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Computational Linguistics and Intellectual Technologies |
| primary_location.landing_page_url | https://doi.org/10.28995/2075-7182-2021-20-578-586 |
| publication_date | 2021-06-19 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W3023517664, https://openalex.org/W3139344803, https://openalex.org/W1971220772, https://openalex.org/W2081580037, https://openalex.org/W2740782137, https://openalex.org/W2965373594, https://openalex.org/W3093195051, https://openalex.org/W2035717317, https://openalex.org/W4288028050, https://openalex.org/W3034675880, https://openalex.org/W4287271288, https://openalex.org/W2951465421 |
| referenced_works_count | 12 |
| abstract_inverted_index.a | 4, 7, 11, 18, 24, 29, 33, 62, 91, 186, 190, 215 |
| abstract_inverted_index.an | 51, 99, 194 |
| abstract_inverted_index.in | 140, 211, 247 |
| abstract_inverted_index.is | 6, 96, 175 |
| abstract_inverted_index.it | 104 |
| abstract_inverted_index.of | 80, 148, 166, 201, 231 |
| abstract_inverted_index.on | 98, 130 |
| abstract_inverted_index.to | 13, 184 |
| abstract_inverted_index.we | 49, 110, 192, 237 |
| abstract_inverted_index.WSD | 101, 168 |
| abstract_inverted_index.and | 60, 68, 119, 143, 170, 199, 213, 242 |
| abstract_inverted_index.any | 131, 147 |
| abstract_inverted_index.can | 27, 37 |
| abstract_inverted_index.dot | 88 |
| abstract_inverted_index.for | 10, 32, 55, 106, 146, 177, 189, 196 |
| abstract_inverted_index.has | 85 |
| abstract_inverted_index.its | 121 |
| abstract_inverted_index.may | 160 |
| abstract_inverted_index.not | 125 |
| abstract_inverted_index.on, | 156 |
| abstract_inverted_index.one | 149 |
| abstract_inverted_index.our | 47, 178, 180, 240 |
| abstract_inverted_index.out | 15 |
| abstract_inverted_index.the | 72, 78, 81, 86, 107, 114, 127, 137, 141, 158, 164, 197, 202, 221, 244, 248 |
| abstract_inverted_index.was | 154, 182 |
| abstract_inverted_index.way | 9 |
| abstract_inverted_index.BERT | 112 |
| abstract_inverted_index.Word | 56 |
| abstract_inverted_index.XLMR | 116, 153 |
| abstract_inverted_index.also | 38 |
| abstract_inverted_index.data | 210 |
| abstract_inverted_index.find | 14 |
| abstract_inverted_index.from | 3 |
| abstract_inverted_index.into | 71, 227 |
| abstract_inverted_index.make | 103 |
| abstract_inverted_index.more | 228 |
| abstract_inverted_index.most | 82 |
| abstract_inverted_index.same | 73 |
| abstract_inverted_index.show | 171 |
| abstract_inverted_index.such | 167 |
| abstract_inverted_index.that | 23, 26, 64, 172, 219 |
| abstract_inverted_index.then | 162 |
| abstract_inverted_index.this | 76, 134, 173 |
| abstract_inverted_index.with | 90, 113 |
| abstract_inverted_index.word | 1, 20, 35, 66, 69, 93, 235 |
| abstract_inverted_index.work | 105 |
| abstract_inverted_index.(SCD) | 44 |
| abstract_inverted_index.(WSD) | 59 |
| abstract_inverted_index.Sense | 57 |
| abstract_inverted_index.data, | 133 |
| abstract_inverted_index.first | 245 |
| abstract_inverted_index.human | 12 |
| abstract_inverted_index.model | 118, 129, 181 |
| abstract_inverted_index.other | 151 |
| abstract_inverted_index.place | 139, 246 |
| abstract_inverted_index.sense | 232 |
| abstract_inverted_index.solve | 40 |
| abstract_inverted_index.which | 16 |
| abstract_inverted_index.word, | 191 |
| abstract_inverted_index.works | 145 |
| abstract_inverted_index.Change | 42 |
| abstract_inverted_index.choose | 185 |
| abstract_inverted_index.embeds | 65 |
| abstract_inverted_index.has.We | 21 |
| abstract_inverted_index.impact | 165 |
| abstract_inverted_index.likely | 144 |
| abstract_inverted_index.model, | 218 |
| abstract_inverted_index.output | 224 |
| abstract_inverted_index.proper | 30, 187 |
| abstract_inverted_index.scores | 230 |
| abstract_inverted_index.second | 138 |
| abstract_inverted_index.select | 28 |
| abstract_inverted_index.senses | 17 |
| abstract_inverted_index.simple | 216 |
| abstract_inverted_index.space, | 77 |
| abstract_inverted_index.system | 25, 63, 95, 135 |
| abstract_inverted_index.though | 157 |
| abstract_inverted_index.vector | 74 |
| abstract_inverted_index.verify | 46 |
| abstract_inverted_index.English | 100 |
| abstract_inverted_index.Russian | 108, 132, 212 |
| abstract_inverted_index.achieve | 243 |
| abstract_inverted_index.between | 223, 234 |
| abstract_inverted_index.changes | 204 |
| abstract_inverted_index.crucial | 176 |
| abstract_inverted_index.encoder | 128 |
| abstract_inverted_index.further | 238 |
| abstract_inverted_index.hundred | 150 |
| abstract_inverted_index.improve | 239 |
| abstract_inverted_index.labeled | 209 |
| abstract_inverted_index.largest | 87 |
| abstract_inverted_index.measure | 163 |
| abstract_inverted_index.product | 89 |
| abstract_inverted_index.propose | 193 |
| abstract_inverted_index.results | 241 |
| abstract_inverted_index.task.To | 45 |
| abstract_inverted_index.through | 205 |
| abstract_inverted_index.time.By | 206 |
| abstract_inverted_index.trained | 61, 97, 183 |
| abstract_inverted_index.vary.We | 161 |
| abstract_inverted_index.Semantic | 41 |
| abstract_inverted_index.achieves | 136 |
| abstract_inverted_index.approach | 52 |
| abstract_inverted_index.converts | 220 |
| abstract_inverted_index.familiar | 8 |
| abstract_inverted_index.followed | 50 |
| abstract_inverted_index.language | 117 |
| abstract_inverted_index.proposed | 54 |
| abstract_inverted_index.replaced | 111 |
| abstract_inverted_index.semantic | 203 |
| abstract_inverted_index.space.In | 75 |
| abstract_inverted_index.training | 214 |
| abstract_inverted_index.zeroshot | 122 |
| abstract_inverted_index.Detection | 43 |
| abstract_inverted_index.algorithm | 195 |
| abstract_inverted_index.corpus.To | 102 |
| abstract_inverted_index.distances | 222 |
| abstract_inverted_index.embedding | 79 |
| abstract_inverted_index.employing | 207 |
| abstract_inverted_index.exploited | 120 |
| abstract_inverted_index.humanlike | 229 |
| abstract_inverted_index.language, | 109 |
| abstract_inverted_index.languages | 152 |
| abstract_inverted_index.naturally | 39 |
| abstract_inverted_index.procedure | 174 |
| abstract_inverted_index.Consulting | 0 |
| abstract_inverted_index.additional | 208 |
| abstract_inverted_index.definition | 31, 84, 188 |
| abstract_inverted_index.dictionary | 5 |
| abstract_inverted_index.embeddings | 226 |
| abstract_inverted_index.finetuning | 126 |
| abstract_inverted_index.occurrence | 36 |
| abstract_inverted_index.particular | 19, 34 |
| abstract_inverted_index.pretrained | 155 |
| abstract_inverted_index.previously | 53 |
| abstract_inverted_index.regression | 217 |
| abstract_inverted_index.similarity | 233 |
| abstract_inverted_index.appropriate | 83 |
| abstract_inverted_index.definitions | 2, 67 |
| abstract_inverted_index.hypothesis, | 48 |
| abstract_inverted_index.hypothesize | 22 |
| abstract_inverted_index.occurrences | 70 |
| abstract_inverted_index.performance | 159 |
| abstract_inverted_index.pretraining | 169 |
| abstract_inverted_index.competition, | 142 |
| abstract_inverted_index.competition. | 249 |
| abstract_inverted_index.crosslingual | 123 |
| abstract_inverted_index.multilingual | 115 |
| abstract_inverted_index.occurrences, | 236 |
| abstract_inverted_index.embedding.The | 94 |
| abstract_inverted_index.results.Since | 179 |
| abstract_inverted_index.visualization | 200 |
| abstract_inverted_index.Disambiguation | 58 |
| abstract_inverted_index.contextualized | 92, 225 |
| abstract_inverted_index.interpretation | 198 |
| abstract_inverted_index.transferability.Despite | 124 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.4699999988079071 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.76936231 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |