2017
EACL
EACL 2017
Unsupervised AMR-Dependency Parse Alignment
Abstract
AbstractIn this paper, we introduce an Abstract Meaning Representation (AMR) to Dependency Parse aligner. Alignment is a preliminary step for AMR parsing, and our aligner improves current AMR parser performance. Our aligner involves several different features, including named entity tags and semantic role labels, and uses Expectation-Maximization training. Results show that our aligner reaches an 87.1% F-Score score with the experimental data, and enhances AMR parsing.
🌉
Interdisciplinary Bridge
— Interdisciplinary and Knowledge & Reasoning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— amr parsing
🐣
Hot Topic Early Bird
— semantic role labeling
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Learning Types > Unsupervised Learning
Natural Language Processing > Understanding > Parsing
Natural Language Processing > Understanding > Semantic Analysis
Natural Language Processing > Understanding > Syntax
Natural Language Processing > Resources & Methods > Text Representation
Knowledge & Reasoning > Representation > Knowledge Representation
Interdisciplinary > Linguistics > Computational Linguistics