Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing

Autor:	Rubino, Melanie, Mesnards, Nicolas Guenon des, Shah, Uday, Jiang, Nanjiang, Sun, Weiqi, Arkoudas, Konstantine
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted for publication at NAACL 2022 workshop DeepLo, "Deep Learning for Low-Resource NLP"
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2206.05352 Zobrazit plný text záznamu View this record from Arxiv