A Cross-Domain Transferable Neural Coherence Model

doi:doi:10.57702/0sq8lnv8

A Cross-Domain Transferable Neural Coherence Model

Coherence is an important aspect of text quality and is crucial for ensuring its readability. The proposed coherence model is simple in structure, yet it significantly outperforms previous state-of-art methods on a standard benchmark dataset on the Wall Street Journal corpus, as well as in multiple new challenging settings of transfer to unseen categories of discourse on Wikipedia articles.

BibTex:

@dataset{Peng_Xu_and_Hamidreza_Saghir_and_Jin_Sung_Kang_and_Teng_Long_and_Avishek_Joey_Bose_and_Yanshuai_Cao_and_Jackie_Chi_Kit_Cheung_2025,
    abstract = {Coherence is an important aspect of text quality and is crucial for ensuring its readability. The proposed coherence model is simple in structure, yet it significantly outperforms previous state-of-art methods on a standard benchmark dataset on the Wall Street Journal corpus, as well as in multiple new challenging settings of transfer to unseen categories of discourse on Wikipedia articles.},
    author = {Peng Xu and Hamidreza Saghir and Jin Sung Kang and Teng Long and Avishek Joey Bose and Yanshuai Cao and Jackie Chi Kit Cheung},
    doi = {10.57702/0sq8lnv8},
    institution = {No Organization},
    keyword = {'coherence', 'natural language processing', 'text quality', 'transfer learning'},
    month = {jan},
    publisher = {TIB},
    title = {A Cross-Domain Transferable Neural Coherence Model},
    url = {https://service.tib.eu/ldmservice/dataset/a-cross-domain-transferable-neural-coherence-model},
    year = {2025}
}