Year: 2007
Type: conference-paper
Abstract: Parallel treebanks, which comprise paired source-target parse trees aligned at sub-sentential level, could be useful\nfor many applications, particularly data-driven machine translation. In this paper, we focus on how translational\ndivergences are captured within a parallel treebank using a fully automatic statistical tree-to-tree aligner. We\nobserve that while the algorithm performs well at the phrase level, performance on lexical-level alignments\nis compromised by an inappropriate bias towards coverage rather than precision. This preference for high precision\nrather than broad coverage in terms of expressing translational divergences through tree-alignment stands in\ndirect opposition to the situation for SMT word-alignment models. We suggest that this has implications not only\nfor tree-alignment itself but also for the broader area of induction of syntaxaware models for SMT.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7519655