DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble Approach Article Swipe
Engin Demir
,
Metin Bilgin
,
Engin Demir
,
Metin Bilgin
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/app152312480
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/app152312480
In the current information age, with the exponential growth of data volume and language-based applications, the accurate resolution of intra-contextual relationships in texts has become indispensable for both academic research and industrial Natural Language Processing (NLP) systems. This study focuses on the detection of pronominal anaphora in Turkish sentences. For the detection of pronominal anaphora, a specific dataset comprising 2000 sentences and 72,239 tokens was created, and this dataset was labeled using a BIO tagging method developed with a custom approach for this study. In this work, fine-tuning was performed on Transformer-based language models pre-trained on Turkish data, such as BERT and RoBERTa. Additionally, Large Language Models (LLMs) trained on Turkish data, including Turkcell-LLM-7b-v1 and ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1, as well as multilingual models like Microsoft’s Phi-3 Mini-4K-Instruct and OpenAI’s GPT-4o-mini, were also fine-tuned with the created dataset to detect pronominal anaphora in sentences. Following the training of the language models, the resulting performance was evaluated using pronoun accuracy, antecedent accuracy, exact match, and F1-score metrics. According to the results obtained in the pronominal anaphora detection phase of the study, a novel hybrid ensemble approach combining multiple Transformer models with linguistic rules achieved the highest performance. This hybrid system attained scores of 0.987 for pronoun accuracy, 0.977 for antecedent accuracy, 0.505 for exact match, and 0.960 for F1-score, surpassing all individual models, including GPT-4o-mini. These findings reveal the superiority of ensemble methods combined with Turkish-specific linguistic rules over standalone models in Turkish anaphora resolution. This study is considered novel, as it is the first work to apply hybrid ensemble methods with linguistic rule integration to this domain for the Turkish language.
Related Topics
Concepts
Anaphora (linguistics)
Computer science
Natural language processing
Turkish
Artificial intelligence
Pronoun
Antecedent (behavioral psychology)
Question answering
Linguistics
Coreference
Bootstrapping (finance)
Resolution (logic)
Transformer
Computational linguistics
Language model
Classifier (UML)
Demonstrative
Ensemble learning
Natural language
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.3390/app152312480
- https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353
- OA Status
- gold
- References
- 7
- OpenAlex ID
- https://openalex.org/W7106510517
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W7106510517Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3390/app152312480Digital Object Identifier
- Title
-
DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble ApproachWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-25Full publication date if available
- Authors
-
Engin Demir, Metin Bilgin, Engin Demir, Metin BilginList of authors in order
- Landing page
-
https://doi.org/10.3390/app152312480Publisher landing page
- PDF URL
-
https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353Direct OA link when available
- Concepts
-
Anaphora (linguistics), Computer science, Natural language processing, Turkish, Artificial intelligence, Pronoun, Antecedent (behavioral psychology), Question answering, Linguistics, Coreference, Bootstrapping (finance), Resolution (logic), Transformer, Computational linguistics, Language model, Classifier (UML), Demonstrative, Ensemble learning, Natural languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
7Number of works referenced by this work
Full payload
| id | https://openalex.org/W7106510517 |
|---|---|
| doi | https://doi.org/10.3390/app152312480 |
| ids.doi | https://doi.org/10.3390/app152312480 |
| ids.openalex | https://openalex.org/W7106510517 |
| fwci | 0.0 |
| type | article |
| title | DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble Approach |
| biblio.issue | 23 |
| biblio.volume | 15 |
| biblio.last_page | 12480 |
| biblio.first_page | 12480 |
| is_xpac | False |
| apc_list.value | 2300 |
| apc_list.currency | CHF |
| apc_list.value_usd | 2490 |
| apc_paid.value | 2300 |
| apc_paid.currency | CHF |
| apc_paid.value_usd | 2490 |
| concepts[0].id | https://openalex.org/C2781449363 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8953151106834412 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q156751 |
| concepts[0].display_name | Anaphora (linguistics) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.80222487449646 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.7132531404495239 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C2781121862 |
| concepts[3].level | 2 |
| concepts[3].score | 0.7035332918167114 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q256 |
| concepts[3].display_name | Turkish |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.6931584477424622 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2778551981 |
| concepts[5].level | 2 |
| concepts[5].score | 0.6569877862930298 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q36224 |
| concepts[5].display_name | Pronoun |
| concepts[6].id | https://openalex.org/C2781256819 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5397278666496277 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q16828835 |
| concepts[6].display_name | Antecedent (behavioral psychology) |
| concepts[7].id | https://openalex.org/C44291984 |
| concepts[7].level | 2 |
| concepts[7].score | 0.3831633925437927 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1074173 |
| concepts[7].display_name | Question answering |
| concepts[8].id | https://openalex.org/C41895202 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3669130206108093 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[8].display_name | Linguistics |
| concepts[9].id | https://openalex.org/C28076734 |
| concepts[9].level | 3 |
| concepts[9].score | 0.36454951763153076 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q63087 |
| concepts[9].display_name | Coreference |
| concepts[10].id | https://openalex.org/C207609745 |
| concepts[10].level | 2 |
| concepts[10].score | 0.3548296391963959 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q4944086 |
| concepts[10].display_name | Bootstrapping (finance) |
| concepts[11].id | https://openalex.org/C138268822 |
| concepts[11].level | 2 |
| concepts[11].score | 0.3528071343898773 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1051925 |
| concepts[11].display_name | Resolution (logic) |
| concepts[12].id | https://openalex.org/C66322947 |
| concepts[12].level | 3 |
| concepts[12].score | 0.35115647315979004 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[12].display_name | Transformer |
| concepts[13].id | https://openalex.org/C155092808 |
| concepts[13].level | 2 |
| concepts[13].score | 0.35062772035598755 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q182557 |
| concepts[13].display_name | Computational linguistics |
| concepts[14].id | https://openalex.org/C137293760 |
| concepts[14].level | 2 |
| concepts[14].score | 0.3345789611339569 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[14].display_name | Language model |
| concepts[15].id | https://openalex.org/C95623464 |
| concepts[15].level | 2 |
| concepts[15].score | 0.3037387728691101 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[15].display_name | Classifier (UML) |
| concepts[16].id | https://openalex.org/C2780277889 |
| concepts[16].level | 2 |
| concepts[16].score | 0.29490113258361816 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q282301 |
| concepts[16].display_name | Demonstrative |
| concepts[17].id | https://openalex.org/C45942800 |
| concepts[17].level | 2 |
| concepts[17].score | 0.2822266221046448 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q245652 |
| concepts[17].display_name | Ensemble learning |
| concepts[18].id | https://openalex.org/C195324797 |
| concepts[18].level | 2 |
| concepts[18].score | 0.276389479637146 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[18].display_name | Natural language |
| keywords[0].id | https://openalex.org/keywords/anaphora |
| keywords[0].score | 0.8953151106834412 |
| keywords[0].display_name | Anaphora (linguistics) |
| keywords[1].id | https://openalex.org/keywords/turkish |
| keywords[1].score | 0.7035332918167114 |
| keywords[1].display_name | Turkish |
| keywords[2].id | https://openalex.org/keywords/pronoun |
| keywords[2].score | 0.6569877862930298 |
| keywords[2].display_name | Pronoun |
| keywords[3].id | https://openalex.org/keywords/antecedent |
| keywords[3].score | 0.5397278666496277 |
| keywords[3].display_name | Antecedent (behavioral psychology) |
| keywords[4].id | https://openalex.org/keywords/question-answering |
| keywords[4].score | 0.3831633925437927 |
| keywords[4].display_name | Question answering |
| keywords[5].id | https://openalex.org/keywords/coreference |
| keywords[5].score | 0.36454951763153076 |
| keywords[5].display_name | Coreference |
| keywords[6].id | https://openalex.org/keywords/bootstrapping |
| keywords[6].score | 0.3548296391963959 |
| keywords[6].display_name | Bootstrapping (finance) |
| language | en |
| locations[0].id | doi:10.3390/app152312480 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210205812 |
| locations[0].source.issn | 2076-3417 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2076-3417 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Applied Sciences |
| locations[0].source.host_organization | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Applied Sciences |
| locations[0].landing_page_url | https://doi.org/10.3390/app152312480 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A2123210131 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6263-5915 |
| authorships[0].author.display_name | Engin Demir |
| authorships[0].countries | PK, TR |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I131835042 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I4210098942, https://openalex.org/I79305253 |
| authorships[0].affiliations[1].raw_affiliation_string | Department of Information Technology, National Defence University, Istanbul 34353, Turkey |
| authorships[0].institutions[0].id | https://openalex.org/I79305253 |
| authorships[0].institutions[0].ror | https://ror.org/https://ror.org/045vxh980 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I79305253 |
| authorships[0].institutions[0].country_code | PK |
| authorships[0].institutions[0].display_name | National Defence University |
| authorships[0].institutions[1].id | https://openalex.org/I4210098942 |
| authorships[0].institutions[1].ror | https://ror.org/https://ror.org/010t24d82 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I4210098942 |
| authorships[0].institutions[1].country_code | TR |
| authorships[0].institutions[1].display_name | Milli Savunma Üniversitesi |
| authorships[0].institutions[2].id | https://openalex.org/I131835042 |
| authorships[0].institutions[2].ror | https://ror.org/https://ror.org/03tg3eb07 |
| authorships[0].institutions[2].type | education |
| authorships[0].institutions[2].lineage | https://openalex.org/I131835042 |
| authorships[0].institutions[2].country_code | TR |
| authorships[0].institutions[2].display_name | Bursa Uludağ Üni̇versi̇tesi̇ |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Engin Demir |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey, Department of Information Technology, National Defence University, Istanbul 34353, Turkey |
| authorships[1].author.id | https://openalex.org/A2103568523 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Metin Bilgin |
| authorships[1].countries | TR |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I131835042 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| authorships[1].institutions[0].id | https://openalex.org/I131835042 |
| authorships[1].institutions[0].ror | https://ror.org/https://ror.org/03tg3eb07 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I131835042 |
| authorships[1].institutions[0].country_code | TR |
| authorships[1].institutions[0].display_name | Bursa Uludağ Üni̇versi̇tesi̇ |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Metin Bilgin |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| authorships[2].author.id | https://openalex.org/A2123210131 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6263-5915 |
| authorships[2].author.display_name | Engin Demir |
| authorships[2].countries | PK, TR |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I131835042 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| authorships[2].affiliations[1].institution_ids | https://openalex.org/I79305253, https://openalex.org/I4210098942 |
| authorships[2].affiliations[1].raw_affiliation_string | Department of Information Technology, National Defence University, Istanbul 34353, Turkey |
| authorships[2].institutions[0].id | https://openalex.org/I131835042 |
| authorships[2].institutions[0].ror | https://ror.org/https://ror.org/03tg3eb07 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I131835042 |
| authorships[2].institutions[0].country_code | TR |
| authorships[2].institutions[0].display_name | Bursa Uludağ Üni̇versi̇tesi̇ |
| authorships[2].institutions[1].id | https://openalex.org/I4210098942 |
| authorships[2].institutions[1].ror | https://ror.org/https://ror.org/010t24d82 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I4210098942 |
| authorships[2].institutions[1].country_code | TR |
| authorships[2].institutions[1].display_name | Milli Savunma Üniversitesi |
| authorships[2].institutions[2].id | https://openalex.org/I79305253 |
| authorships[2].institutions[2].ror | https://ror.org/https://ror.org/045vxh980 |
| authorships[2].institutions[2].type | education |
| authorships[2].institutions[2].lineage | https://openalex.org/I79305253 |
| authorships[2].institutions[2].country_code | PK |
| authorships[2].institutions[2].display_name | National Defence University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Engin Demir |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey, Department of Information Technology, National Defence University, Istanbul 34353, Turkey |
| authorships[3].author.id | https://openalex.org/A2103568523 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Metin Bilgin |
| authorships[3].countries | TR |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I131835042 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| authorships[3].institutions[0].id | https://openalex.org/I131835042 |
| authorships[3].institutions[0].ror | https://ror.org/https://ror.org/03tg3eb07 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I131835042 |
| authorships[3].institutions[0].country_code | TR |
| authorships[3].institutions[0].display_name | Bursa Uludağ Üni̇versi̇tesi̇ |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Metin Bilgin |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Computer Engineering, Bursa Uludag University, Bursa 16059, Turkey |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-25T00:00:00 |
| display_name | DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble Approach |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-27T01:12:40.094763 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.3390/app152312480 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210205812 |
| best_oa_location.source.issn | 2076-3417 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2076-3417 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Applied Sciences |
| best_oa_location.source.host_organization | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Applied Sciences |
| best_oa_location.landing_page_url | https://doi.org/10.3390/app152312480 |
| primary_location.id | doi:10.3390/app152312480 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210205812 |
| primary_location.source.issn | 2076-3417 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2076-3417 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Applied Sciences |
| primary_location.source.host_organization | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.mdpi.com/2076-3417/15/23/12480/pdf?version=1764065353 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Applied Sciences |
| primary_location.landing_page_url | https://doi.org/10.3390/app152312480 |
| publication_date | 2025-11-25 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W2964222246, https://openalex.org/W1652618140, https://openalex.org/W2114439521, https://openalex.org/W2103710036, https://openalex.org/W3091729174, https://openalex.org/W4405073919, https://openalex.org/W2250668331 |
| referenced_works_count | 7 |
| abstract_inverted_index.a | 55, 72, 78, 177 |
| abstract_inverted_index.In | 0, 84 |
| abstract_inverted_index.as | 99, 116, 118, 246 |
| abstract_inverted_index.in | 21, 46, 139, 168, 237 |
| abstract_inverted_index.is | 243, 248 |
| abstract_inverted_index.it | 247 |
| abstract_inverted_index.of | 9, 18, 43, 52, 144, 174, 198, 226 |
| abstract_inverted_index.on | 40, 90, 95, 109 |
| abstract_inverted_index.to | 135, 164, 252, 261 |
| abstract_inverted_index.BIO | 73 |
| abstract_inverted_index.For | 49 |
| abstract_inverted_index.all | 216 |
| abstract_inverted_index.and | 12, 30, 61, 66, 101, 114, 125, 160, 211 |
| abstract_inverted_index.for | 26, 81, 200, 204, 208, 213, 264 |
| abstract_inverted_index.has | 23 |
| abstract_inverted_index.the | 1, 6, 15, 41, 50, 132, 142, 145, 148, 165, 169, 175, 190, 224, 249, 265 |
| abstract_inverted_index.was | 64, 69, 88, 151 |
| abstract_inverted_index.2000 | 59 |
| abstract_inverted_index.BERT | 100 |
| abstract_inverted_index.This | 37, 193, 241 |
| abstract_inverted_index.age, | 4 |
| abstract_inverted_index.also | 129 |
| abstract_inverted_index.both | 27 |
| abstract_inverted_index.data | 10 |
| abstract_inverted_index.like | 121 |
| abstract_inverted_index.over | 234 |
| abstract_inverted_index.rule | 259 |
| abstract_inverted_index.such | 98 |
| abstract_inverted_index.this | 67, 82, 85, 262 |
| abstract_inverted_index.well | 117 |
| abstract_inverted_index.were | 128 |
| abstract_inverted_index.with | 5, 77, 131, 186, 230, 257 |
| abstract_inverted_index.work | 251 |
| abstract_inverted_index.(NLP) | 35 |
| abstract_inverted_index.0.505 | 207 |
| abstract_inverted_index.0.960 | 212 |
| abstract_inverted_index.0.977 | 203 |
| abstract_inverted_index.0.987 | 199 |
| abstract_inverted_index.Large | 104 |
| abstract_inverted_index.Phi-3 | 123 |
| abstract_inverted_index.These | 221 |
| abstract_inverted_index.apply | 253 |
| abstract_inverted_index.data, | 97, 111 |
| abstract_inverted_index.exact | 158, 209 |
| abstract_inverted_index.first | 250 |
| abstract_inverted_index.novel | 178 |
| abstract_inverted_index.phase | 173 |
| abstract_inverted_index.rules | 188, 233 |
| abstract_inverted_index.study | 38, 242 |
| abstract_inverted_index.texts | 22 |
| abstract_inverted_index.using | 71, 153 |
| abstract_inverted_index.work, | 86 |
| abstract_inverted_index.(LLMs) | 107 |
| abstract_inverted_index.72,239 | 62 |
| abstract_inverted_index.Models | 106 |
| abstract_inverted_index.become | 24 |
| abstract_inverted_index.custom | 79 |
| abstract_inverted_index.detect | 136 |
| abstract_inverted_index.domain | 263 |
| abstract_inverted_index.growth | 8 |
| abstract_inverted_index.hybrid | 179, 194, 254 |
| abstract_inverted_index.match, | 159, 210 |
| abstract_inverted_index.method | 75 |
| abstract_inverted_index.models | 93, 120, 185, 236 |
| abstract_inverted_index.novel, | 245 |
| abstract_inverted_index.reveal | 223 |
| abstract_inverted_index.scores | 197 |
| abstract_inverted_index.study, | 176 |
| abstract_inverted_index.study. | 83 |
| abstract_inverted_index.system | 195 |
| abstract_inverted_index.tokens | 63 |
| abstract_inverted_index.volume | 11 |
| abstract_inverted_index.Natural | 32 |
| abstract_inverted_index.Turkish | 47, 96, 110, 238, 266 |
| abstract_inverted_index.created | 133 |
| abstract_inverted_index.current | 2 |
| abstract_inverted_index.dataset | 57, 68, 134 |
| abstract_inverted_index.focuses | 39 |
| abstract_inverted_index.highest | 191 |
| abstract_inverted_index.labeled | 70 |
| abstract_inverted_index.methods | 228, 256 |
| abstract_inverted_index.models, | 147, 218 |
| abstract_inverted_index.pronoun | 154, 201 |
| abstract_inverted_index.results | 166 |
| abstract_inverted_index.tagging | 74 |
| abstract_inverted_index.trained | 108 |
| abstract_inverted_index.F1-score | 161 |
| abstract_inverted_index.Language | 33, 105 |
| abstract_inverted_index.RoBERTa. | 102 |
| abstract_inverted_index.academic | 28 |
| abstract_inverted_index.accurate | 16 |
| abstract_inverted_index.achieved | 189 |
| abstract_inverted_index.anaphora | 45, 138, 171, 239 |
| abstract_inverted_index.approach | 80, 181 |
| abstract_inverted_index.attained | 196 |
| abstract_inverted_index.combined | 229 |
| abstract_inverted_index.created, | 65 |
| abstract_inverted_index.ensemble | 180, 227, 255 |
| abstract_inverted_index.findings | 222 |
| abstract_inverted_index.language | 92, 146 |
| abstract_inverted_index.metrics. | 162 |
| abstract_inverted_index.multiple | 183 |
| abstract_inverted_index.obtained | 167 |
| abstract_inverted_index.research | 29 |
| abstract_inverted_index.specific | 56 |
| abstract_inverted_index.systems. | 36 |
| abstract_inverted_index.training | 143 |
| abstract_inverted_index.According | 163 |
| abstract_inverted_index.F1-score, | 214 |
| abstract_inverted_index.Following | 141 |
| abstract_inverted_index.accuracy, | 155, 157, 202, 206 |
| abstract_inverted_index.anaphora, | 54 |
| abstract_inverted_index.combining | 182 |
| abstract_inverted_index.detection | 42, 51, 172 |
| abstract_inverted_index.developed | 76 |
| abstract_inverted_index.evaluated | 152 |
| abstract_inverted_index.including | 112, 219 |
| abstract_inverted_index.language. | 267 |
| abstract_inverted_index.performed | 89 |
| abstract_inverted_index.resulting | 149 |
| abstract_inverted_index.sentences | 60 |
| abstract_inverted_index.OpenAI’s | 126 |
| abstract_inverted_index.Processing | 34 |
| abstract_inverted_index.antecedent | 156, 205 |
| abstract_inverted_index.comprising | 58 |
| abstract_inverted_index.considered | 244 |
| abstract_inverted_index.fine-tuned | 130 |
| abstract_inverted_index.individual | 217 |
| abstract_inverted_index.industrial | 31 |
| abstract_inverted_index.linguistic | 187, 232, 258 |
| abstract_inverted_index.pronominal | 44, 53, 137, 170 |
| abstract_inverted_index.resolution | 17 |
| abstract_inverted_index.sentences. | 48, 140 |
| abstract_inverted_index.standalone | 235 |
| abstract_inverted_index.surpassing | 215 |
| abstract_inverted_index.Transformer | 184 |
| abstract_inverted_index.exponential | 7 |
| abstract_inverted_index.fine-tuning | 87 |
| abstract_inverted_index.information | 3 |
| abstract_inverted_index.integration | 260 |
| abstract_inverted_index.performance | 150 |
| abstract_inverted_index.pre-trained | 94 |
| abstract_inverted_index.resolution. | 240 |
| abstract_inverted_index.superiority | 225 |
| abstract_inverted_index.GPT-4o-mini, | 127 |
| abstract_inverted_index.GPT-4o-mini. | 220 |
| abstract_inverted_index.multilingual | 119 |
| abstract_inverted_index.performance. | 192 |
| abstract_inverted_index.Additionally, | 103 |
| abstract_inverted_index.Microsoft’s | 122 |
| abstract_inverted_index.applications, | 14 |
| abstract_inverted_index.indispensable | 25 |
| abstract_inverted_index.relationships | 20 |
| abstract_inverted_index.language-based | 13 |
| abstract_inverted_index.Mini-4K-Instruct | 124 |
| abstract_inverted_index.Turkish-specific | 231 |
| abstract_inverted_index.intra-contextual | 19 |
| abstract_inverted_index.Transformer-based | 91 |
| abstract_inverted_index.Turkcell-LLM-7b-v1 | 113 |
| abstract_inverted_index.ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1, | 115 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |