MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging

TL;DR

This paper presents a recursive neural sequence tagging approach for cross-lingual UCCA semantic parsing, effectively handling the French language with limited training data by iteratively building semantic graphs.

Contribution

The paper introduces a recursive parsing method using masked sequence tagging for cross-lingual semantic parsing, emphasizing robustness with minimal training data.

Findings

Effective recursive parsing strategy for UCCA graphs

Successful cross-lingual transfer to French with few samples

Improved semantic graph accuracy over baseline methods

Abstract

This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the decisions made in previous steps. Process continues until the terminal nodes are reached. We choose a standard neural tagger and we focused on our recursive parsing strategy and on the cross lingual transfer problem to develop a robust model for the French language, using only few training samples.