Dependencies vs. Constituents for Tree-Based Alignment

Given a parallel parsed corpus, statistical treeto-tree alignment attempts to match nodes in the syntactic trees for a given sentence in two languages. We train a probabilistic tree transduction model on a large automatically parsed Chinese-English corpus, and evaluate results against human-annotated word level alignments. We find that a constituent-based model performs better than a similar probability model trained on the same trees converted to a dependency representation.

• Type: Conference
• Year: 2004
• Where: EMNLP
• Authors: Daniel Gildea
• Keywords: EMNLP 2004, EMNLP 2007, Parallel Parsed Corpus, Parsed Chinese-english Corpus, Tree Transduction Model