A comprehensive transfer news headline generation method based on semantic prototype transduction
Most current deep learning-based news headline generation models only target domain-specific news data. When a new news domain appears, it is usually costly to obtain a large amount of data with reference truth on the new domain for model training, so text generation models trained by traditional su...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-01-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023055?viewType=HTML |
| _version_ | 1811231854254096384 |
|---|---|
| author | Ting-Huai Ma Xin Yu Huan Rong |
| author_facet | Ting-Huai Ma Xin Yu Huan Rong |
| author_sort | Ting-Huai Ma |
| collection | DOAJ |
| description | Most current deep learning-based news headline generation models only target domain-specific news data. When a new news domain appears, it is usually costly to obtain a large amount of data with reference truth on the new domain for model training, so text generation models trained by traditional supervised approaches often do not generalize well on the new domain—inspired by the idea of transfer learning, this paper designs a cross-domain transfer text generation method based on domain data distribution alignment, intermediate domain redistribution, and zero-shot learning semantic prototype transduction, focusing on the data problem with no reference truth in the target domain. Eventually, the model can be guided by the most relevant source domain data to generate headlines from the target domain news text through the semantic correlation between source and target domain data during the training process of generating headlines for the target domain news, even without any reference truth of the news headlines in the target domain, which improves the usability of the text generation model in real scenarios. The experimental results show that the proposed transfer text generation method has a good domain transfer effect and outperforms other existing transfer text generation methods in various text generation evaluation indexes, proving the proposed method's effectiveness in this paper. |
| first_indexed | 2024-04-12T10:53:20Z |
| format | Article |
| id | doaj.art-62195c114ea1456d9547b74d55f3640e |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-12T10:53:20Z |
| publishDate | 2023-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-62195c114ea1456d9547b74d55f3640e2022-12-22T03:36:10ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-012011195122810.3934/mbe.2023055A comprehensive transfer news headline generation method based on semantic prototype transductionTing-Huai Ma0Xin Yu1Huan Rong21. School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, China1. School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, China2. School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science & Technology, Nanjing 210044, ChinaMost current deep learning-based news headline generation models only target domain-specific news data. When a new news domain appears, it is usually costly to obtain a large amount of data with reference truth on the new domain for model training, so text generation models trained by traditional supervised approaches often do not generalize well on the new domain—inspired by the idea of transfer learning, this paper designs a cross-domain transfer text generation method based on domain data distribution alignment, intermediate domain redistribution, and zero-shot learning semantic prototype transduction, focusing on the data problem with no reference truth in the target domain. Eventually, the model can be guided by the most relevant source domain data to generate headlines from the target domain news text through the semantic correlation between source and target domain data during the training process of generating headlines for the target domain news, even without any reference truth of the news headlines in the target domain, which improves the usability of the text generation model in real scenarios. The experimental results show that the proposed transfer text generation method has a good domain transfer effect and outperforms other existing transfer text generation methods in various text generation evaluation indexes, proving the proposed method's effectiveness in this paper.https://www.aimspress.com/article/doi/10.3934/mbe.2023055?viewType=HTMLtransfer learningzero-shot learningdata distribution alignmentsemantic prototype transductiontext generation model |
| spellingShingle | Ting-Huai Ma Xin Yu Huan Rong A comprehensive transfer news headline generation method based on semantic prototype transduction Mathematical Biosciences and Engineering transfer learning zero-shot learning data distribution alignment semantic prototype transduction text generation model |
| title | A comprehensive transfer news headline generation method based on semantic prototype transduction |
| title_full | A comprehensive transfer news headline generation method based on semantic prototype transduction |
| title_fullStr | A comprehensive transfer news headline generation method based on semantic prototype transduction |
| title_full_unstemmed | A comprehensive transfer news headline generation method based on semantic prototype transduction |
| title_short | A comprehensive transfer news headline generation method based on semantic prototype transduction |
| title_sort | comprehensive transfer news headline generation method based on semantic prototype transduction |
| topic | transfer learning zero-shot learning data distribution alignment semantic prototype transduction text generation model |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023055?viewType=HTML |
| work_keys_str_mv | AT tinghuaima acomprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction AT xinyu acomprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction AT huanrong acomprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction AT tinghuaima comprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction AT xinyu comprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction AT huanrong comprehensivetransfernewsheadlinegenerationmethodbasedonsemanticprototypetransduction |