Universal dependency relation features, but not explicit dependency tree structure, improve zero-shot cross-lingual semantic parsing on the Parallel Meaning Bank.
Cross-lingual Semantic Parsing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce the task of cross-lingual semantic parsing: mapping content provided in a source language into a meaning representation based on a target language. We present: (1) a meaning representation 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 meaning representations, (3) an end-to-end model with a novel copy mechanism that supports intrasentential coreference, and (4) an evaluation dataset where experiments show our model outperforms strong baselines by at least 1.18 F1 score.
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A survey of cross-lingual features for zero-shot cross-lingual semantic parsing
Universal dependency relation features, but not explicit dependency tree structure, improve zero-shot cross-lingual semantic parsing on the Parallel Meaning Bank.