A survey of cross-lingual features for zero-shot cross-lingual semantic parsing

TL;DR

This paper surveys cross-lingual features for zero-shot semantic parsing, demonstrating how universal dependency features can enhance parser transfer across languages, with empirical results on multilingual datasets.

Contribution

It provides a comprehensive review of cross-lingual features and evaluates their effectiveness in zero-shot semantic parsing across multiple languages.

Findings

Universal Dependency features improve zero-shot parsing performance.

Direct modeling of UD structure does not significantly boost results.

Cross-lingual embeddings combined with UD features enhance transferability.

Abstract

The availability of corpora to train semantic parsers in English has lead to significant advances in the field. Unfortunately, for languages other than English, annotation is scarce and so are developed parsers. We then ask: could a parser trained in English be applied to language that it hasn't been trained on? To answer this question we explore zero-shot cross-lingual semantic parsing where we train an available coarse-to-fine semantic parser (Liu et al., 2018) using cross-lingual word embeddings and universal dependencies in English and test it on Italian, German and Dutch. Results on the Parallel Meaning Bank - a multilingual semantic graphbank, show that Universal Dependency features significantly boost performance when used in conjunction with other lexical features but modelling the UD structure directly when encoding the input does not.