Compositional Generalization in Multilingual Semantic Parsing over Wikidata
This addresses the lack of multilingual resources for semantic parsing, enabling more realistic and diverse research, though it is incremental as it builds on existing benchmarks and methods.
The authors tackled the problem of compositional generalization in multilingual semantic parsing by creating a new dataset (MCWQ) grounded in Wikidata and testing it across Hebrew, Kannada, Chinese, and English, finding that cross-lingual compositional generalization fails even with state-of-the-art models.
Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on English resources, such as CFQ (Keysers et al., 2020), the current standard benchmark based on English data generated from grammar rules and oriented towards Freebase, an outdated knowledge base. We propose a method for creating a multilingual, parallel dataset of question-query pairs, grounded in Wikidata. We introduce such a dataset, which we call Multilingual Compositional Wikidata Questions (MCWQ), and use it to analyze the compositional generalization of semantic parsers in Hebrew, Kannada, Chinese and English. While within-language generalization is comparable across languages, experiments on zero-shot cross-lingual transfer demonstrate that cross-lingual compositional generalization fails, even with state-of-the-art pretrained multilingual encoders. Furthermore, our methodology, dataset and results will facilitate future research on SP in more realistic and diverse settings than has been possible with existing resources.