Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems
This addresses the data scarcity issue for spoken dialog systems, offering a scalable solution for researchers and developers in conversational AI, though it is incremental as it builds on existing web log mining techniques.
The paper tackles the problem of training statistical dialog models by leveraging billions of web search and browse sessions to mine behavioral patterns, which are translated into spoken dialog models, resulting in state-of-the-art performance for entity extraction in spoken dialog systems and improved performance for entity and relation extraction on web queries.
Training statistical dialog models in spoken dialog systems (SDS) requires large amounts of annotated data. The lack of scalable methods for data mining and annotation poses a significant hurdle for state-of-the-art statistical dialog managers. This paper presents an approach that directly leverage billions of web search and browse sessions to overcome this hurdle. The key insight is that task completion through web search and browse sessions is (a) predictable and (b) generalizes to spoken dialog task completion. The new method automatically mines behavioral search and browse patterns from web logs and translates them into spoken dialog models. We experiment with naturally occurring spoken dialogs and large scale web logs. Our session-based models outperform the state-of-the-art method for entity extraction task in SDS. We also achieve better performance for both entity and relation extraction on web search queries when compared with nontrivial baselines.