X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

Abstract

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.

arXiv commentAccepted in RepL4NLP 2021

References in corpus (7)

• Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection
• Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• CrossNER: Evaluating Cross-Domain Named Entity Recognition
• Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
• MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark
• Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing