Contextual Slot Carryover for Disparate Schemas

TL;DR

This paper introduces a neural network approach for slot carryover in multi-domain conversational systems, effectively handling large slot sets and schema diversity, with competitive performance demonstrated across multiple domains.

Contribution

The paper proposes a novel neural architecture that reformulates slot carryover as a decision process and introduces a data-driven method for schema transformation, addressing scalability and heterogeneity.

Findings

Scales effectively to multiple domains

Achieves competitive accuracy over strong baselines

Handles large, unbounded slot sets and diverse schemas

Abstract

In the slot-filling paradigm, where a user can refer back to slots in the context during a conversation, the goal of the contextual understanding system is to resolve the referring expressions to the appropriate slots in the context. In large-scale multi-domain systems, this presents two challenges - scaling to a very large and potentially unbounded set of slot values, and dealing with diverse schemas. We present a neural network architecture that addresses the slot value scalability challenge by reformulating the contextual interpretation as a decision to carryover a slot from a set of possible candidates. To deal with heterogenous schemas, we introduce a simple data-driven method for trans- forming the candidate slots. Our experiments show that our approach can scale to multiple domains and provides competitive results over a strong baseline.