CANDLE: Decomposing Conditional and Conjunctive Queries for Task-Oriented Dialogue Systems
This addresses a bottleneck in task-oriented dialogue systems for users needing to express multi-action queries, but it is incremental as it focuses on dataset creation and baseline methods.
The paper tackles the problem of domain-specific dialogue systems struggling with complex queries containing conditional and sequential clauses by decomposing them into single-action subqueries, resulting in the release of the CANDLE dataset with 4282 manually tagged utterances and baseline taggers.
Domain-specific dialogue systems generally determine user intents by relying on sentence level classifiers that mainly focus on single action sentences. Such classifiers are not designed to effectively handle complex queries composed of conditional and sequential clauses that represent multiple actions. We attempt to decompose such queries into smaller single action subqueries that are reasonable for intent classifiers to understand in a dialogue pipeline. We release, CANDLE(Conditional & AND type Expressions), a dataset consisting of 4282 utterances manually tagged with conditional and sequential labels, and demonstrates this decomposition by training two baseline taggers.