Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment
| Autor: | Yinpei Dai, Hangyu Li, Jian Sun, Chengguang Tang, Xiaodan Zhu, Yongbin Li |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
System deployment
Goal orientation Computer science Low resource business.industry 02 engineering and technology Machine learning computer.software_genre 03 medical and health sciences 0302 clinical medicine End-to-end principle 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Dialog box business computer |
| Zdroj: | ACL |
| DOI: | 10.18653/v1/2020.acl-main.57 |
| Popis: | Existing end-to-end dialog systems perform less effectively when data is scarce. To obtain an acceptable success in real-life online services with only a handful of training examples, both fast adaptability and reliable performance are highly desirable for dialog systems. In this paper, we propose the Meta-Dialog System (MDS), which combines the advantages of both meta-learning approaches and human-machine collaboration. We evaluate our methods on a new extended-bAbI dataset and a transformed MultiWOZ dataset for low-resource goal-oriented dialog learning. Experimental results show that MDS significantly outperforms non-meta-learning baselines and can achieve more than 90% per-turn accuracies with only 10 dialogs on the extended-bAbI dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|