Parsing Universal Dependencies without training

2017/01/11 by Héctor Martínez Alonso, Alonso, Héctor Martínez, Żeljko Agić +5
Computer Science · Neuroscience · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Neurobiology of Language and Bilingualism #Speech and dialogue systems

paper · pdf · doi:10.48550/arxiv.1701.03163

openalex publication_date 2017/01/11 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It 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, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.

Cited by

• Cross-Lingual Syntactic Transfer with Limited Resources

Related

• 75 Languages, 1 Model: Parsing Universal Dependencies Universally
• Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations
• Learning to Search for Dependencies
• UDapter: Language Adaptation for Truly Universal Dependency Parsing
• Universal Dependency Parsing with a General Transition-Based DAG Parser