Abstract

We introduce the task of cross-lingual decompositional semantic parsing: mapping content provided in a source language into a decompositional semantic analysis based on a target language. We present: (1) a form of decompositional semantic analysis designed to allow systems to target varying levels of structural complexity (shallow to deep analysis), (2) an evaluation metric to measure the similarity between system output and reference semantic analysis, (3) an end-to-end model with a novel annotating mechanism that supports intra-sentential coreference, and (4) an evaluation dataset on which our model outperforms strong baselines by at least 1.75 F1 score.

Keywords:
Coreference Computer science Parsing Natural language processing Artificial intelligence Task (project management) Semantic similarity Metric (unit) Similarity (geometry) Semantic role labeling Resolution (logic) Image (mathematics) Sentence

Metrics

21
Cited By
3.77
FWCI (Field Weighted Citation Impact)
71
Refs
0.93
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Natural Language Processing Techniques
Physical Sciences →  Computer Science →  Artificial Intelligence
Topic Modeling
Physical Sciences →  Computer Science →  Artificial Intelligence
Text Readability and Simplification
Physical Sciences →  Computer Science →  Artificial Intelligence

Related Documents

JOURNAL ARTICLE

Zero-Shot Cross-lingual Semantic Parsing

Tom SherborneMirella Lapata

Journal:   Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Year: 2022 Pages: 4134-4153
JOURNAL ARTICLE

Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing

Tom SherborneTom HoskingMirella Lapata

Journal:   Transactions of the Association for Computational Linguistics Year: 2023 Vol: 11 Pages: 1432-1450
JOURNAL ARTICLE

Meta-Learning a Cross-lingual Manifold for Semantic Parsing

Tom SherborneMirella Lapata

Journal:   Transactions of the Association for Computational Linguistics Year: 2023 Vol: 11 Pages: 49-67
© 2026 ScienceGate Book Chapters — All rights reserved.