التفاصيل البيبلوغرافية
| العنوان: |
Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation |
| المؤلفون: |
Jialin Yu, Alexandra I. Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Tahir Aduragba, Lei Shi, Noura Al Moubayed |
| المصدر: |
AI Open, Vol 4, Iss , Pp 19-32 (2023) |
| بيانات النشر: |
KeAi Communications Co. Ltd., 2023. |
| سنة النشر: |
2023 |
| المجموعة: |
LCC:Electronic computers. Computer science |
| مصطلحات موضوعية: |
Deep latent variable models, Paraphrase generation, Semi-supervised learning, Natural language processing, Deep learning, Electronic computers. Computer science, QA75.5-76.95 |
| الوصف: |
This paper explores deep latent variable models for semi-supervised paraphrase generation, where the missing target pair for unlabelled data is modelled as a latent paraphrase sequence. We present a novel unsupervised model named variational sequence auto-encoding reconstruction (VSAR), which performs latent sequence inference given an observed text. To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model. Combining VSAR with DDL (DDL+VSAR) enables us to conduct semi-supervised learning. Still, the combined model suffers from a cold-start problem. To further combat this issue, we propose an improved weight initialisation solution, leading to a novel two-stage training scheme we call knowledge-reinforced-learning (KRL). Our empirical evaluations suggest that the combined model yields competitive performance against the state-of-the-art supervised baselines on complete data. Furthermore, in scenarios where only a fraction of the labelled pairs are available, our combined model consistently outperforms the strong supervised model baseline (DDL) by a significant margin (p |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2666-6510 |
| Relation: |
http://www.sciencedirect.com/science/article/pii/S2666651023000025; https://doaj.org/toc/2666-6510 |
| DOI: |
10.1016/j.aiopen.2023.05.001 |
| URL الوصول: |
https://doaj.org/article/7405011d2af64562ae5861bfc0674a5f |
| رقم الانضمام: |
edsdoj.7405011d2af64562ae5861bfc0674a5f |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder