Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks
Abstrak
Recently, post-processing networks (PPNs), which modify the outputs of arbitrary modules including non-differentiable ones in task-oriented dialogue systems, have been proposed. PPNs have successfully improved the dialogue performance by post-processing nat-ural language understanding (NLU), dialogue state tracking (DST), and dialogue policy (Policy) modules with a classification-based approach. However, they cannot be applied to natural language generation (NLG) modules because the post-processing of utterances output by NLG modules requires a generative approach. In this study, we propose a new post-processing component for NLG, generative post-processing networks (GenPPNs). For optimizing GenPPNs via reinforcement learning, the reward function incorporates dialogue act contribution, a new measure to evaluate the contribution of GenPPN-generated utterances with regard to task completion in dialogue. Through simulation and human evaluation experiments based on the MultiWOZ dataset, we confirmed that GenPPNs improve the task completion performance of task-oriented dialogue systems 1 .
Topik & Kata Kunci
Penulis (2)
Atsumoto Ohashi
Ryuichiro Higashinaka
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2023
- Bahasa
- en
- Total Sitasi
- 3×
- Sumber Database
- Semantic Scholar
- DOI
- 10.18653/v1/2023.emnlp-main.231
- Akses
- Open Access ✓