Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling Article Swipe
Shuangyin Li
,
Rong Pan
,
Haoyu Luo
,
Xiao Liu
,
Gansen Zhao
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1016/j.knosys.2021.106827
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1016/j.knosys.2021.106827
Because of its efficiency, word embedding has been widely used in many natural language processing and text modeling tasks. It aims to represent each word by a vector so such that the geometry between these vectors can capture the semantic correlations between words. An ambiguous word can often have diverse meanings in different contexts, a quality which is called polysemy. The bulk of studies aimed to generate only one single embedding for each word, whereas a few studies have made a small number of embeddings to present different meanings of each word. However, it is hard to determine the exact number of senses for each word, as meanings depend on contexts. To address this problem, this paper proposes a novel adaptive cross-contextual word embedding (ACWE) method for capturing the word polysemy in different contexts based on topic modeling, in which the word polysemy is defined over a latent interpretable semantic space. The proposed ACWE consists of two main parts, in the first of which an unsupervised cross-contextual probabilistic word embedding model is designed to obtain the global word embeddings, and each word is represented by an embedding in the unified latent semantic space. Based on the global word embeddings, an adaptive cross-contextual word embedding process is then devised in the second part to learn the local embeddings for each polysemous word in different contexts. In fact, a word embedding is adaptively adjusted and updated with respect to different contexts to generate different word embeddings tailored to the corresponding contexts. The proposed ACWE is validated on two datasets collected from Wikipedia and IMDb on different tasks including word similarity, polysemy induction, semantic interpretability, and text classification. Experimental results indicate that ACWE does not only outperform the established word embedding methods, which consider word polysemy on six popular benchmark datasets, but it also yields competitive performance compared with state-of-the-art deep learning-based approaches without considering polysemy. Moreover, the proposed ACWE significantly improves the performances of text classification both in precision and F1, and the visualizations of the semantics of words demonstrate the feasibility and advantage of the proposed ACWE model on polysemy.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1016/j.knosys.2021.106827
- OA Status
- hybrid
- Cited By
- 35
- References
- 124
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3132982245
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3132982245Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1016/j.knosys.2021.106827Digital Object Identifier
- Title
-
Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modelingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-02-21Full publication date if available
- Authors
-
Shuangyin Li, Rong Pan, Haoyu Luo, Xiao Liu, Gansen ZhaoList of authors in order
- Landing page
-
https://doi.org/10.1016/j.knosys.2021.106827Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1016/j.knosys.2021.106827Direct OA link when available
- Concepts
-
Polysemy, Word (group theory), Natural language processing, Computer science, Word embedding, Artificial intelligence, Embedding, Latent semantic analysis, Context (archaeology), Linguistics, Paleontology, Philosophy, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
35Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 6, 2024: 6, 2023: 7, 2022: 10, 2021: 6Per-year citation counts (last 5 years)
- References (count)
-
124Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3132982245 |
|---|---|
| doi | https://doi.org/10.1016/j.knosys.2021.106827 |
| ids.doi | https://doi.org/10.1016/j.knosys.2021.106827 |
| ids.mag | 3132982245 |
| ids.openalex | https://openalex.org/W3132982245 |
| fwci | 4.09200368 |
| type | article |
| title | Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling |
| biblio.issue | |
| biblio.volume | 218 |
| biblio.last_page | 106827 |
| biblio.first_page | 106827 |
| topics[0].id | https://openalex.org/T10028 |
| 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 | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9979000091552734 |
| 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 | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T13083 |
| 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/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Advanced Text Analysis Techniques |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| is_xpac | False |
| apc_list.value | 3130 |
| apc_list.currency | USD |
| apc_list.value_usd | 3130 |
| apc_paid.value | 3130 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 3130 |
| concepts[0].id | https://openalex.org/C2780276568 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9431743621826172 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q191928 |
| concepts[0].display_name | Polysemy |
| concepts[1].id | https://openalex.org/C90805587 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8070300817489624 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q10944557 |
| concepts[1].display_name | Word (group theory) |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.7214157581329346 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6990522146224976 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C2777462759 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6759688854217529 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q18395344 |
| concepts[4].display_name | Word embedding |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.6176455020904541 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C41608201 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5100842118263245 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[6].display_name | Embedding |
| concepts[7].id | https://openalex.org/C170133592 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4322913587093353 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1806883 |
| concepts[7].display_name | Latent semantic analysis |
| concepts[8].id | https://openalex.org/C2779343474 |
| concepts[8].level | 2 |
| concepts[8].score | 0.41261520981788635 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[8].display_name | Context (archaeology) |
| concepts[9].id | https://openalex.org/C41895202 |
| concepts[9].level | 1 |
| concepts[9].score | 0.33874374628067017 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[9].display_name | Linguistics |
| concepts[10].id | https://openalex.org/C151730666 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[10].display_name | Paleontology |
| 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/C86803240 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[12].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/polysemy |
| keywords[0].score | 0.9431743621826172 |
| keywords[0].display_name | Polysemy |
| keywords[1].id | https://openalex.org/keywords/word |
| keywords[1].score | 0.8070300817489624 |
| keywords[1].display_name | Word (group theory) |
| keywords[2].id | https://openalex.org/keywords/natural-language-processing |
| keywords[2].score | 0.7214157581329346 |
| keywords[2].display_name | Natural language processing |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.6990522146224976 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/word-embedding |
| keywords[4].score | 0.6759688854217529 |
| keywords[4].display_name | Word embedding |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.6176455020904541 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/embedding |
| keywords[6].score | 0.5100842118263245 |
| keywords[6].display_name | Embedding |
| keywords[7].id | https://openalex.org/keywords/latent-semantic-analysis |
| keywords[7].score | 0.4322913587093353 |
| keywords[7].display_name | Latent semantic analysis |
| keywords[8].id | https://openalex.org/keywords/context |
| keywords[8].score | 0.41261520981788635 |
| keywords[8].display_name | Context (archaeology) |
| keywords[9].id | https://openalex.org/keywords/linguistics |
| keywords[9].score | 0.33874374628067017 |
| keywords[9].display_name | Linguistics |
| language | en |
| locations[0].id | doi:10.1016/j.knosys.2021.106827 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S10169007 |
| locations[0].source.issn | 0950-7051, 1872-7409 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0950-7051 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Knowledge-Based Systems |
| locations[0].source.host_organization | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_name | Elsevier BV |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_lineage_names | Elsevier BV |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Knowledge-Based Systems |
| locations[0].landing_page_url | https://doi.org/10.1016/j.knosys.2021.106827 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5079920323 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6404-3438 |
| authorships[0].author.display_name | Shuangyin Li |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I187400657 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| authorships[0].institutions[0].id | https://openalex.org/I187400657 |
| authorships[0].institutions[0].ror | https://ror.org/01kq0pv72 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I187400657 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | South China Normal University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shuangyin Li |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| authorships[1].author.id | https://openalex.org/A5075012459 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5171-8248 |
| authorships[1].author.display_name | Rong Pan |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I157773358 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Data and Computer Science, Sun Yat-sen University, Guangzhou, Guangdong, China |
| authorships[1].institutions[0].id | https://openalex.org/I157773358 |
| authorships[1].institutions[0].ror | https://ror.org/0064kty71 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I157773358 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Sun Yat-sen University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Rong Pan |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | School of Data and Computer Science, Sun Yat-sen University, Guangzhou, Guangdong, China |
| authorships[2].author.id | https://openalex.org/A5100641952 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3201-4963 |
| authorships[2].author.display_name | Haoyu Luo |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210098034 |
| authorships[2].affiliations[0].raw_affiliation_string | Key Lab on Cloud Security and Assessment technology of Guangzhou, Guangdong, China |
| authorships[2].affiliations[1].institution_ids | https://openalex.org/I187400657 |
| authorships[2].affiliations[1].raw_affiliation_string | School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| authorships[2].institutions[0].id | https://openalex.org/I4210098034 |
| authorships[2].institutions[0].ror | https://ror.org/00swtqp09 |
| authorships[2].institutions[0].type | facility |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210098034 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Key Laboratory of Guangdong Province |
| authorships[2].institutions[1].id | https://openalex.org/I187400657 |
| authorships[2].institutions[1].ror | https://ror.org/01kq0pv72 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I187400657 |
| authorships[2].institutions[1].country_code | CN |
| authorships[2].institutions[1].display_name | South China Normal University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Haoyu Luo |
| authorships[2].is_corresponding | True |
| authorships[2].raw_affiliation_strings | Key Lab on Cloud Security and Assessment technology of Guangzhou, Guangdong, China, School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| authorships[3].author.id | https://openalex.org/A5075936732 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8400-5754 |
| authorships[3].author.display_name | Xiao Liu |
| authorships[3].countries | AU |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I149704539 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Information Technology, Deakin University, Geelong, Australia |
| authorships[3].institutions[0].id | https://openalex.org/I149704539 |
| authorships[3].institutions[0].ror | https://ror.org/02czsnj07 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I149704539 |
| authorships[3].institutions[0].country_code | AU |
| authorships[3].institutions[0].display_name | Deakin University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xiao Liu |
| authorships[3].is_corresponding | True |
| authorships[3].raw_affiliation_strings | School of Information Technology, Deakin University, Geelong, Australia |
| authorships[4].author.id | https://openalex.org/A5101818721 |
| authorships[4].author.orcid | https://orcid.org/0009-0007-1526-5326 |
| authorships[4].author.display_name | Gansen Zhao |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I4210098034 |
| authorships[4].affiliations[0].raw_affiliation_string | Key Lab on Cloud Security and Assessment technology of Guangzhou, Guangdong, China |
| authorships[4].affiliations[1].institution_ids | https://openalex.org/I187400657 |
| authorships[4].affiliations[1].raw_affiliation_string | School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| authorships[4].institutions[0].id | https://openalex.org/I4210098034 |
| authorships[4].institutions[0].ror | https://ror.org/00swtqp09 |
| authorships[4].institutions[0].type | facility |
| authorships[4].institutions[0].lineage | https://openalex.org/I4210098034 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Key Laboratory of Guangdong Province |
| authorships[4].institutions[1].id | https://openalex.org/I187400657 |
| authorships[4].institutions[1].ror | https://ror.org/01kq0pv72 |
| authorships[4].institutions[1].type | education |
| authorships[4].institutions[1].lineage | https://openalex.org/I187400657 |
| authorships[4].institutions[1].country_code | CN |
| authorships[4].institutions[1].display_name | South China Normal University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Gansen Zhao |
| authorships[4].is_corresponding | True |
| authorships[4].raw_affiliation_strings | Key Lab on Cloud Security and Assessment technology of Guangzhou, Guangdong, China, School of Computer Science, South China Normal University, Guangzhou, Guangdong, China |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1016/j.knosys.2021.106827 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| 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 | Topic Modeling |
| related_works | https://openalex.org/W2600654830, https://openalex.org/W947140380, https://openalex.org/W4286432911, https://openalex.org/W4230884544, https://openalex.org/W4245453790, https://openalex.org/W3194985222, https://openalex.org/W3216571906, https://openalex.org/W4214830338, https://openalex.org/W2518587255, https://openalex.org/W4287599800 |
| cited_by_count | 35 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 6 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 6 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 7 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 10 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 6 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1016/j.knosys.2021.106827 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S10169007 |
| best_oa_location.source.issn | 0950-7051, 1872-7409 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0950-7051 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Knowledge-Based Systems |
| best_oa_location.source.host_organization | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_name | Elsevier BV |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_lineage_names | Elsevier BV |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Knowledge-Based Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1016/j.knosys.2021.106827 |
| primary_location.id | doi:10.1016/j.knosys.2021.106827 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S10169007 |
| primary_location.source.issn | 0950-7051, 1872-7409 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0950-7051 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Knowledge-Based Systems |
| primary_location.source.host_organization | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_name | Elsevier BV |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_lineage_names | Elsevier BV |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Knowledge-Based Systems |
| primary_location.landing_page_url | https://doi.org/10.1016/j.knosys.2021.106827 |
| publication_date | 2021-02-21 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W6682691769, https://openalex.org/W6691431627, https://openalex.org/W6622801540, https://openalex.org/W2962739339, https://openalex.org/W6739901393, https://openalex.org/W6684443387, https://openalex.org/W6684165356, https://openalex.org/W6683778255, https://openalex.org/W6691826361, https://openalex.org/W2963639656, https://openalex.org/W2889647547, https://openalex.org/W6680532216, https://openalex.org/W6731874461, https://openalex.org/W999446416, https://openalex.org/W6737123006, https://openalex.org/W6772245388, https://openalex.org/W6742080785, https://openalex.org/W2507974895, https://openalex.org/W1010415138, https://openalex.org/W6630877349, https://openalex.org/W2787984249, https://openalex.org/W2954731083, https://openalex.org/W2808282792, https://openalex.org/W6675387176, https://openalex.org/W6689951360, https://openalex.org/W2250753706, https://openalex.org/W6676358562, https://openalex.org/W6845343071, https://openalex.org/W6692924172, https://openalex.org/W6697291937, https://openalex.org/W2900979343, https://openalex.org/W6750366282, https://openalex.org/W6773573887, https://openalex.org/W6744121944, https://openalex.org/W6755950812, https://openalex.org/W6755245825, https://openalex.org/W6639619044, https://openalex.org/W6736084046, https://openalex.org/W6775259997, https://openalex.org/W6764253783, https://openalex.org/W2939795228, https://openalex.org/W6752546469, https://openalex.org/W3091499889, https://openalex.org/W2782863194, https://openalex.org/W6754567369, https://openalex.org/W6675806119, https://openalex.org/W6695690082, https://openalex.org/W6652520323, https://openalex.org/W6684578138, https://openalex.org/W6636440780, https://openalex.org/W6692011917, https://openalex.org/W6679482899, https://openalex.org/W6682044806, https://openalex.org/W6663947504, https://openalex.org/W6639014918, https://openalex.org/W6691746754, https://openalex.org/W2142625445, https://openalex.org/W2112184938, https://openalex.org/W2702896255, https://openalex.org/W2107743791, https://openalex.org/W1854884267, https://openalex.org/W2965373594, https://openalex.org/W4240892256, https://openalex.org/W2950386031, https://openalex.org/W2896304678, https://openalex.org/W4231510805, https://openalex.org/W3003352390, https://openalex.org/W1592076897, https://openalex.org/W2130339025, https://openalex.org/W2251012068, https://openalex.org/W2113651538, https://openalex.org/W4250650717, https://openalex.org/W2100062901, https://openalex.org/W2612690371, https://openalex.org/W2067438047, https://openalex.org/W2781528640, https://openalex.org/W2999905431, https://openalex.org/W2212194804, https://openalex.org/W2293834552, https://openalex.org/W2772124661, https://openalex.org/W1532325895, https://openalex.org/W2810694153, https://openalex.org/W4294562888, https://openalex.org/W2108061274, https://openalex.org/W2997292130, https://openalex.org/W2964121225, https://openalex.org/W2238728730, https://openalex.org/W4238600740, https://openalex.org/W2757106032, https://openalex.org/W2896457183, https://openalex.org/W4285719527, https://openalex.org/W3021256576, https://openalex.org/W2164973920, https://openalex.org/W2950813464, https://openalex.org/W2162456950, https://openalex.org/W2963563735, https://openalex.org/W1612003148, https://openalex.org/W2897987981, https://openalex.org/W2949679478, https://openalex.org/W2147946282, https://openalex.org/W2164019165, https://openalex.org/W2970597249, https://openalex.org/W2740711318, https://openalex.org/W2600756564, https://openalex.org/W2250539671, https://openalex.org/W2998704965, https://openalex.org/W2008225289, https://openalex.org/W2133564696, https://openalex.org/W1513718494, https://openalex.org/W2262907013, https://openalex.org/W2798760675, https://openalex.org/W810147176, https://openalex.org/W4213069590, https://openalex.org/W2251537235, https://openalex.org/W3012570180, https://openalex.org/W2626778328, https://openalex.org/W2140610559, https://openalex.org/W2281717416, https://openalex.org/W2251491951, https://openalex.org/W2604706042, https://openalex.org/W2166851633, https://openalex.org/W2955642149, https://openalex.org/W1880262756, https://openalex.org/W2950133940 |
| referenced_works_count | 124 |
| abstract_inverted_index.a | 26, 54, 75, 80, 118, 146, 226 |
| abstract_inverted_index.An | 43 |
| abstract_inverted_index.In | 224 |
| abstract_inverted_index.It | 19 |
| abstract_inverted_index.To | 111 |
| abstract_inverted_index.an | 164, 185, 199 |
| abstract_inverted_index.as | 106 |
| abstract_inverted_index.by | 25, 184 |
| abstract_inverted_index.in | 10, 51, 131, 138, 159, 187, 208, 221, 325 |
| abstract_inverted_index.is | 57, 94, 143, 171, 182, 205, 229, 252 |
| abstract_inverted_index.it | 93, 299 |
| abstract_inverted_index.of | 1, 62, 83, 89, 101, 155, 162, 321, 332, 335, 342 |
| abstract_inverted_index.on | 109, 135, 194, 254, 262, 293, 347 |
| abstract_inverted_index.so | 28 |
| abstract_inverted_index.to | 21, 65, 85, 96, 173, 212, 236, 239, 245 |
| abstract_inverted_index.F1, | 328 |
| abstract_inverted_index.The | 60, 151, 249 |
| abstract_inverted_index.and | 15, 179, 232, 260, 272, 327, 329, 340 |
| abstract_inverted_index.but | 298 |
| abstract_inverted_index.can | 36, 46 |
| abstract_inverted_index.few | 76 |
| abstract_inverted_index.for | 71, 103, 126, 217 |
| abstract_inverted_index.has | 6 |
| abstract_inverted_index.its | 2 |
| abstract_inverted_index.not | 281 |
| abstract_inverted_index.one | 68 |
| abstract_inverted_index.six | 294 |
| abstract_inverted_index.the | 31, 38, 98, 128, 140, 160, 175, 188, 195, 209, 214, 246, 284, 314, 319, 330, 333, 338, 343 |
| abstract_inverted_index.two | 156, 255 |
| abstract_inverted_index.ACWE | 153, 251, 279, 316, 345 |
| abstract_inverted_index.IMDb | 261 |
| abstract_inverted_index.aims | 20 |
| abstract_inverted_index.also | 300 |
| abstract_inverted_index.been | 7 |
| abstract_inverted_index.both | 324 |
| abstract_inverted_index.bulk | 61 |
| abstract_inverted_index.deep | 307 |
| abstract_inverted_index.does | 280 |
| abstract_inverted_index.each | 23, 72, 90, 104, 180, 218 |
| abstract_inverted_index.from | 258 |
| abstract_inverted_index.hard | 95 |
| abstract_inverted_index.have | 48, 78 |
| abstract_inverted_index.made | 79 |
| abstract_inverted_index.main | 157 |
| abstract_inverted_index.many | 11 |
| abstract_inverted_index.only | 67, 282 |
| abstract_inverted_index.over | 145 |
| abstract_inverted_index.part | 211 |
| abstract_inverted_index.such | 29 |
| abstract_inverted_index.text | 16, 273, 322 |
| abstract_inverted_index.that | 30, 278 |
| abstract_inverted_index.then | 206 |
| abstract_inverted_index.this | 113, 115 |
| abstract_inverted_index.used | 9 |
| abstract_inverted_index.with | 234, 305 |
| abstract_inverted_index.word | 4, 24, 45, 122, 129, 141, 168, 177, 181, 197, 202, 220, 227, 242, 266, 286, 291 |
| abstract_inverted_index.Based | 193 |
| abstract_inverted_index.aimed | 64 |
| abstract_inverted_index.based | 134 |
| abstract_inverted_index.exact | 99 |
| abstract_inverted_index.fact, | 225 |
| abstract_inverted_index.first | 161 |
| abstract_inverted_index.learn | 213 |
| abstract_inverted_index.local | 215 |
| abstract_inverted_index.model | 170, 346 |
| abstract_inverted_index.novel | 119 |
| abstract_inverted_index.often | 47 |
| abstract_inverted_index.paper | 116 |
| abstract_inverted_index.small | 81 |
| abstract_inverted_index.tasks | 264 |
| abstract_inverted_index.these | 34 |
| abstract_inverted_index.topic | 136 |
| abstract_inverted_index.which | 56, 139, 163, 289 |
| abstract_inverted_index.word, | 73, 105 |
| abstract_inverted_index.word. | 91 |
| abstract_inverted_index.words | 336 |
| abstract_inverted_index.(ACWE) | 124 |
| abstract_inverted_index.called | 58 |
| abstract_inverted_index.depend | 108 |
| abstract_inverted_index.global | 176, 196 |
| abstract_inverted_index.latent | 147, 190 |
| abstract_inverted_index.method | 125 |
| abstract_inverted_index.number | 82, 100 |
| abstract_inverted_index.obtain | 174 |
| abstract_inverted_index.parts, | 158 |
| abstract_inverted_index.second | 210 |
| abstract_inverted_index.senses | 102 |
| abstract_inverted_index.single | 69 |
| abstract_inverted_index.space. | 150, 192 |
| abstract_inverted_index.tasks. | 18 |
| abstract_inverted_index.vector | 27 |
| abstract_inverted_index.widely | 8 |
| abstract_inverted_index.words. | 42 |
| abstract_inverted_index.yields | 301 |
| abstract_inverted_index.Because | 0 |
| abstract_inverted_index.address | 112 |
| abstract_inverted_index.between | 33, 41 |
| abstract_inverted_index.capture | 37 |
| abstract_inverted_index.defined | 144 |
| abstract_inverted_index.devised | 207 |
| abstract_inverted_index.diverse | 49 |
| abstract_inverted_index.natural | 12 |
| abstract_inverted_index.popular | 295 |
| abstract_inverted_index.present | 86 |
| abstract_inverted_index.process | 204 |
| abstract_inverted_index.quality | 55 |
| abstract_inverted_index.respect | 235 |
| abstract_inverted_index.results | 276 |
| abstract_inverted_index.studies | 63, 77 |
| abstract_inverted_index.unified | 189 |
| abstract_inverted_index.updated | 233 |
| abstract_inverted_index.vectors | 35 |
| abstract_inverted_index.whereas | 74 |
| abstract_inverted_index.without | 310 |
| abstract_inverted_index.However, | 92 |
| abstract_inverted_index.adaptive | 120, 200 |
| abstract_inverted_index.adjusted | 231 |
| abstract_inverted_index.compared | 304 |
| abstract_inverted_index.consider | 290 |
| abstract_inverted_index.consists | 154 |
| abstract_inverted_index.contexts | 133, 238 |
| abstract_inverted_index.datasets | 256 |
| abstract_inverted_index.designed | 172 |
| abstract_inverted_index.generate | 66, 240 |
| abstract_inverted_index.geometry | 32 |
| abstract_inverted_index.improves | 318 |
| abstract_inverted_index.indicate | 277 |
| abstract_inverted_index.language | 13 |
| abstract_inverted_index.meanings | 50, 88, 107 |
| abstract_inverted_index.methods, | 288 |
| abstract_inverted_index.modeling | 17 |
| abstract_inverted_index.polysemy | 130, 142, 268, 292 |
| abstract_inverted_index.problem, | 114 |
| abstract_inverted_index.proposed | 152, 250, 315, 344 |
| abstract_inverted_index.proposes | 117 |
| abstract_inverted_index.semantic | 39, 149, 191, 270 |
| abstract_inverted_index.tailored | 244 |
| abstract_inverted_index.Moreover, | 313 |
| abstract_inverted_index.Wikipedia | 259 |
| abstract_inverted_index.advantage | 341 |
| abstract_inverted_index.ambiguous | 44 |
| abstract_inverted_index.benchmark | 296 |
| abstract_inverted_index.capturing | 127 |
| abstract_inverted_index.collected | 257 |
| abstract_inverted_index.contexts, | 53 |
| abstract_inverted_index.contexts. | 110, 223, 248 |
| abstract_inverted_index.datasets, | 297 |
| abstract_inverted_index.determine | 97 |
| abstract_inverted_index.different | 52, 87, 132, 222, 237, 241, 263 |
| abstract_inverted_index.embedding | 5, 70, 123, 169, 186, 203, 228, 287 |
| abstract_inverted_index.including | 265 |
| abstract_inverted_index.modeling, | 137 |
| abstract_inverted_index.polysemy. | 59, 312, 348 |
| abstract_inverted_index.precision | 326 |
| abstract_inverted_index.represent | 22 |
| abstract_inverted_index.semantics | 334 |
| abstract_inverted_index.validated | 253 |
| abstract_inverted_index.adaptively | 230 |
| abstract_inverted_index.approaches | 309 |
| abstract_inverted_index.embeddings | 84, 216, 243 |
| abstract_inverted_index.induction, | 269 |
| abstract_inverted_index.outperform | 283 |
| abstract_inverted_index.polysemous | 219 |
| abstract_inverted_index.processing | 14 |
| abstract_inverted_index.competitive | 302 |
| abstract_inverted_index.considering | 311 |
| abstract_inverted_index.demonstrate | 337 |
| abstract_inverted_index.efficiency, | 3 |
| abstract_inverted_index.embeddings, | 178, 198 |
| abstract_inverted_index.established | 285 |
| abstract_inverted_index.feasibility | 339 |
| abstract_inverted_index.performance | 303 |
| abstract_inverted_index.represented | 183 |
| abstract_inverted_index.similarity, | 267 |
| abstract_inverted_index.Experimental | 275 |
| abstract_inverted_index.correlations | 40 |
| abstract_inverted_index.performances | 320 |
| abstract_inverted_index.unsupervised | 165 |
| abstract_inverted_index.corresponding | 247 |
| abstract_inverted_index.interpretable | 148 |
| abstract_inverted_index.probabilistic | 167 |
| abstract_inverted_index.significantly | 317 |
| abstract_inverted_index.classification | 323 |
| abstract_inverted_index.learning-based | 308 |
| abstract_inverted_index.visualizations | 331 |
| abstract_inverted_index.classification. | 274 |
| abstract_inverted_index.cross-contextual | 121, 166, 201 |
| abstract_inverted_index.state-of-the-art | 306 |
| abstract_inverted_index.interpretability, | 271 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 98 |
| corresponding_author_ids | https://openalex.org/A5100641952, https://openalex.org/A5101818721, https://openalex.org/A5075012459, https://openalex.org/A5075936732, https://openalex.org/A5079920323 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| corresponding_institution_ids | https://openalex.org/I149704539, https://openalex.org/I157773358, https://openalex.org/I187400657, https://openalex.org/I4210098034 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6899999976158142 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.94801881 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |