تقرير
Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation
| العنوان: | Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation |
|---|---|
| المؤلفون: | Inoue, Shumpei, Liu, Tsungwei, Son, Nguyen Hong, Nguyen, Minh-Tien |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| الوصف: | This paper introduces a model for incomplete utterance restoration (IUR) called JET (\textbf{J}oint learning token \textbf{E}xtraction and \textbf{T}ext generation). Different from prior studies that only work on extraction or abstraction datasets, we design a simple but effective model, working for both scenarios of IUR. Our design simulates the nature of IUR, where omitted tokens from the context contribute to restoration. From this, we construct a Picker that identifies the omitted tokens. To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens. The restoration is done by using a Generator with the help of the Picker on joint learning. Promising results on four benchmark datasets in extraction and abstraction scenarios show that our model is better than the pretrained T5 and non-generative language model methods in both rich and limited training data settings.\footnote{The code is available at \url{https://github.com/shumpei19/JET}} Comment: This paper was accepted by 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022). It includes 10 pages, 2 figures |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2204.03958 |
| رقم الأكسشن: | edsarx.2204.03958 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |