Results 1 to 10 of about 255,417 (217)
CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction [PDF]
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023 Accepted as an EMNLP 2023 main ...
Jingheng Ye +6 more
+6 more sources
Executive functions predict time reference processing in French-speaking people with Alzheimer’s disease [PDF]
Scientific ReportsThe ability to express time through language, known as time reference, is impaired in people with Alzheimer’s disease. While cognitive impairments have been documented in this population, particularly in executive functions, few studies have examined how
Evodie Schaffner +4 more
doaj +2 more sources
Frontiers in Psychology, 2022 Evidence suggests that English speakers use pronouns when referring to the grammatical subject and predictable thematic role. We tested how grammatical role and thematic role predictability affect different types of referential forms, namely, overt ...
Heeju Hwang +3 more
doaj +2 more sources
A Grammatical Reference Analysis of Bobby Mook's "FOMO" TED Talk
HUELE: Journal of Applied Linguistics, Literature and Culture, 2022 This study examines the strategic use of grammatical reference devices, including personal, demonstrative, and comparative references, in Bobby Mook's "FOMO" TED Talk. The analysis aims to elucidate how these linguistic mechanisms contribute to the overall communicative impact and persuasiveness of influential public discourse.
Yuneth Johanna Pane +2 more
openalex +3 more sources
Reference-less Measure of Faithfulness for Grammatical Error Correction [PDF]
Proceedings of the 2018 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language
Technologies, Volume 2 (Short Papers), 2018 Final version for NAACL ...
Leshem Choshen, Omri Abend
openalex +4 more sources
Reliability Crisis of Reference-free Metrics for Grammatical Error Correction [PDF]
Findings of the Association for Computational Linguistics: EMNLP 2025Reference-free evaluation metrics for grammatical error correction (GEC) have achieved high correlation with human judgments. However, these metrics are not designed to evaluate adversarial systems that aim to obtain unjustifiably high scores. The existence of such systems undermines the reliability of automatic evaluation, as it can mislead users in ...
Takumi Goto, Yusuke Sakai, Taro Watanabe
+5 more sources
Inherent Biases in Reference-based Evaluation for Grammatical Error Correction [PDF]
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018 The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality (henceforth, low coverage bias or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range ...
Leshem Choshen, Omri Abend
openalex +2 more sources
Processing grammatical evidentiality and time reference in Turkish heritage and monolingual speakers [PDF]
Bilingualism: Language and Cognition, 2015 In the current study, we examined how adult heritage and monolingual speakers of Turkish process evidentiality (the linguistic expression of information source) through finite verb inflections and time reference, expressed on non-finite participles. A sentence-verification task was used to measure participants’ sensitivity to evidentiality and time ...
Seçkin Arslan +2 more
openalex +4 more sources
There's No Comparison: Reference-less Evaluation Metrics in Grammatical\n Error Correction [PDF]
Proceedings of the 2016 Conference on Empirical Methods in Natural
Language Processing, 2016 to appear in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Courtney Napoles +2 more
openalex +4 more sources
The Reference of Grammatical Cohesion in the Recess Therapy Youtube Channel
ENGLISH JOURNAL OF INDRAGIRIThe objective of this research was to identify distinct types of reference grammatical cohesion generated by children between the ages of two and nine in New York City based on the theory of Halliday & Hasan (1976). The data source of this research was the Recess Therapy YouTube channel. This research applied the qualitative research method defined
Imeldayanti Nehe, Ambalegin Ambalegin
openalex +3 more sources