Learning Interpretable Latent Dialogue Actions With Less Supervision
Hudeček, Vojtěch, Dušek, Ondřej
–arXiv.org Artificial Intelligence
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets, and we propose a way to measure dialogue success without the need for expert annotation. Finally, we propose a novel way to explain semantics of the latent variables with respect to system actions.
arXiv.org Artificial Intelligence
Oct-12-2022
- Country:
- Oceania > Australia
- Victoria > Melbourne (0.04)
- New South Wales > Sydney (0.04)
- North America
- Dominican Republic (0.04)
- United States
- Pennsylvania (0.04)
- Maryland > Baltimore (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.28)
- California
- San Francisco County > San Francisco (0.14)
- San Diego County > San Diego (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Canada > Alberta
- Europe
- Czechia > Prague (0.04)
- Italy (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Germany
- Saarland > Saarbrücken (0.04)
- Berlin (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Asia > Myanmar
- Tanintharyi Region > Dawei (0.04)
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.46)
- Technology: