← Back to papers
2017 EACL EACL 2017

Parsing Universal Dependencies without training

Abstract

AbstractWe present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD. The parser has very few parameters and distinctly robust to domain change across languages.

🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
📈 Trend Setter — Self-Supervised Learning
🧭 Keyword Pioneer — head rule
🐝 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, Security & Privacy, Speech & Audio

Authors

Héctor Martínez Alonso , Željko Agić , Barbara Plank , Anders Søgaard

Topics

Machine Learning > Learning Types > Unsupervised Learning Natural Language Processing > Understanding > Parsing Machine Learning > Learning Paradigms > Self-Supervised Learning

Keywords

universal dependencies dependency parsing unsupervised parsing pagerank algorithm head rule training-free parser
Download PDF

Related papers

Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages 2017
Learning and Knowledge Transfer with Memory Networks for Machine Comprehension 2017
Is this a Child, a Girl or a Car? Exploring the Contribution of Distributional Similarity to Learning Referential Word Meanings 2017
Building Web-Interfaces for Vector Semantic Models with the WebVectors Toolkit 2017
Assessing Convincingness of Arguments in Online Debates with Limited Number of Features 2017