Learning Cross-lingual Distributed Logical Representations for Semantic Parsing
This work addresses a specific, incremental improvement for multilingual semantic parsing, potentially benefiting NLP researchers and practitioners in cross-lingual applications.
The paper tackles the problem of improving monolingual semantic parsers by leveraging data from multiple languages, showing that cross-lingual distributed logical representations can enhance performance on the GeoQuery dataset.
With the development of several multilingual datasets used for semantic parsing, recent research efforts have looked into the problem of learning semantic parsers in a multilingual setup. However, how to improve the performance of a monolingual semantic parser for a specific language by leveraging data annotated in different languages remains a research question that is under-explored. In this work, we present a study to show how learning distributed representations of the logical forms from data annotated in different languages can be used for improving the performance of a monolingual semantic parser. We extend two existing monolingual semantic parsers to incorporate such cross-lingual distributed logical representations as features. Experiments show that our proposed approach is able to yield improved semantic parsing results on the standard multilingual GeoQuery dataset.