A Transition-Based Directed Acyclic Graph Parser for UCCA

Abstract

We present the first parser for UCCA, a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. To our knowledge, the conjunction of these formal properties is not supported by any existing parser. Our transition-based parser, which uses a novel transition set and features based on bidirectional LSTMs, has value not just for UCCA parsing: its ability to handle more general graph structures can inform the development of parsers for other semantic DAG structures, and in languages that frequently use discontinuous structures.

16 pages; Accepted as long paper at ACL2017

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• DyNet: The Dynamic Neural Network Toolkit

Cited by in corpus (20)

• Does injecting linguistic structure into language models lead to better alignment with brain recordings?
• Semantics-aware Attention Improves Neural Machine Translation
• Scene Graph Parsing as Dependency Parsing
• Broad-Coverage Semantic Parsing as Transduction
• Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing
• A Survey on Text Simplification
• Reference-less Measure of Faithfulness for Grammatical Error Correction
• Incorporate Semantic Structures into Machine Translation Evaluation via UCCA
• Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing
• Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies
• Universal Dependency Parsing with a General Transition-Based DAG Parser
• SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA
• HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing
• Simple and Effective Text Simplification Using Semantic and Neural Methods
• Semantic Structural Evaluation for Text Simplification
• A Transition-based Parser for Unscoped Episodic Logical Forms
• MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging
• A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers
• Content Differences in Syntactic and Semantic Representations
• Deep Contextualized Self-training for Low Resource Dependency Parsing