Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment
This addresses a key limitation in dialogue systems for building policies in new domains with limited data, though it appears incremental as it extends prior transfer methods to more challenging scenarios.
The paper tackles the problem of transferring dialogue policies across domains with different speech-acts and disjoint slots, which existing methods cannot handle, and demonstrates that the proposed PROMISE model effectively achieves this transfer in experiments on real-world and simulated data.
Dialogue policy transfer enables us to build dialogue policies in a target domain with little data by leveraging knowledge from a source domain with plenty of data. Dialogue sentences are usually represented by speech-acts and domain slots, and the dialogue policy transfer is usually achieved by assigning a slot mapping matrix based on human heuristics. However, existing dialogue policy transfer methods cannot transfer across dialogue domains with different speech-acts, for example, between systems built by different companies. Also, they depend on either common slots or slot entropy, which are not available when the source and target slots are totally disjoint and no database is available to calculate the slot entropy. To solve this problem, we propose a Policy tRansfer across dOMaIns and SpEech-acts (PROMISE) model, which is able to transfer dialogue policies across domains with different speech-acts and disjoint slots. The PROMISE model can learn to align different speech-acts and slots simultaneously, and it does not require common slots or the calculation of the slot entropy. Experiments on both real-world dialogue data and simulations demonstrate that PROMISE model can effectively transfer dialogue policies across domains with different speech-acts and disjoint slots.