Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing
This addresses the scalability challenge for businesses needing to support new tasks in domains like food-ordering or travel booking, though it is incremental as it builds on existing parsing methods.
The paper tackles the problem of requiring separate labeled training data for each task in task-oriented semantic parsing by introducing Cross-TOP, a zero-shot method that trains a single parser to handle multiple tasks within a vertical, achieving high accuracy on unseen tasks without additional data.
Deep learning methods have enabled task-oriented semantic parsing of increasingly complex utterances. However, a single model is still typically trained and deployed for each task separately, requiring labeled training data for each, which makes it challenging to support new tasks, even within a single business vertical (e.g., food-ordering or travel booking). In this paper we describe Cross-TOP (Cross-Schema Task-Oriented Parsing), a zero-shot method for complex semantic parsing in a given vertical. By leveraging the fact that user requests from the same vertical share lexical and semantic similarities, a single cross-schema parser is trained to service an arbitrary number of tasks, seen or unseen, within a vertical. We show that Cross-TOP can achieve high accuracy on a previously unseen task without requiring any additional training data, thereby providing a scalable way to bootstrap semantic parsers for new tasks. As part of this work we release the FoodOrdering dataset, a task-oriented parsing dataset in the food-ordering vertical, with utterances and annotations derived from five schemas, each from a different restaurant menu.