Abstract | ||
---|---|---|
We propose a relaxed correspondence assumption for cross-lingual projection of constituent syntax, which allows a supposed constituent of the target sentence to correspond to an unrestricted treelet in the source parse. Such a relaxed assumption fundamentally tolerates the syntactic non-isomorphism between languages, and enables us to learn the target-language-specific syntactic idiosyncrasy rather than a strained grammar directly projected from the source language syntax. Based on this assumption, a novel constituency projection method is also proposed in order to induce a projected constituent tree-bank from the source-parsed bilingual corpus. Experiments show that, the parser trained on the projected treebank dramatically outperforms previous projected and unsupervised parsers. |
Year | DOI | Venue |
---|---|---|
2011 | null | EMNLP |
Keywords | DocType | Volume |
cross-lingual projection,projected constituent tree-bank,constituent syntax,syntactic non-isomorphism,projected treebank,supposed constituent,source language syntax,source parse,novel constituency projection method,correspondence assumption | Conference | null |
Issue | ISSN | Citations |
null | null | 7 |
PageRank | References | Authors |
0.44 | 33 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenbin Jiang | 1 | 355 | 36.55 |
Qun Liu | 2 | 2149 | 203.11 |
Yajuan Lü | 3 | 276 | 20.00 |