X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
This work addresses the challenge of generalizing TCSP models to low-resource languages and domains, which is crucial for improving virtual assistants, though it appears incremental as it builds on existing parsing methods with novel adaptations.
The paper tackles the problem of task-oriented compositional semantic parsing (TCSP) by introducing X2Parser, a cross-lingual and cross-domain framework that predicts flattened intents and slots via sequence labeling and a fertility-based slot predictor, achieving significant performance improvements over baselines and reducing latency by up to 66% compared to generative models.
Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries and serves as an essential component of virtual assistants. Current TCSP models rely on numerous training data to achieve decent performance but fail to generalize to low-resource target languages or domains. In this paper, we present X2Parser, a transferable Cross-lingual and Cross-domain Parser for TCSP. Unlike previous models that learn to generate the hierarchical representations for nested intents and slots, we propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems. After that, we further propose a fertility-based slot predictor that first learns to dynamically detect the number of labels for each token, and then predicts the slot types. Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability on target languages of target domains. Furthermore, our model tackles the problem in an efficient non-autoregressive way that reduces the latency by up to 66% compared to the generative model.