File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IALP.2011.36
- Scopus: eid_2-s2.0-84856052315
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Improving Chinese dependency parsing with self-disambiguating patterns
Title | Improving Chinese dependency parsing with self-disambiguating patterns |
---|---|
Authors | |
Keywords | Dependency parsing raw corpus self-disambiguating pattern |
Issue Date | 2011 |
Citation | 2011 International Conference on Asian Language Processing (IALP 2011), Penang, Malaysia, 15-17 November 2011. In 2011 International Conference on Asian Language Processing, 2011, p. 7-10 How to Cite? |
Abstract | To solve the data sparseness problem in dependency parsing, most previous studies used features constructed from large-scale auto-parsed data. Unlike previous work, we propose a new approach to improve dependency parsing with context-free dependency triples (CDT) extracted by using self-disambiguating patterns (SDP). The use of SDP makes it possible to avoid the dependency on a baseline parser and explore the influence of different types of substructures one by one. Additionally, taking the available CDTs as seeds, a label propagation process is used to tag a large number of unlabeled word pairs as CDTs. Experiments show that, when CDT features are integrated into a maximum spanning tree (MST) dependency parser, the new parser improves significantly over the baseline MST parser. Comparative results also show that CDTs with dependency relation labels perform much better than CDT without dependency relation label. © 2011 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/296263 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Qiu, Likun | - |
dc.contributor.author | Wu, Lei | - |
dc.contributor.author | Zhao, Kai | - |
dc.contributor.author | Hu, Changjian | - |
dc.contributor.author | Kong, Lingpeng | - |
dc.date.accessioned | 2021-02-11T04:53:11Z | - |
dc.date.available | 2021-02-11T04:53:11Z | - |
dc.date.issued | 2011 | - |
dc.identifier.citation | 2011 International Conference on Asian Language Processing (IALP 2011), Penang, Malaysia, 15-17 November 2011. In 2011 International Conference on Asian Language Processing, 2011, p. 7-10 | - |
dc.identifier.uri | http://hdl.handle.net/10722/296263 | - |
dc.description.abstract | To solve the data sparseness problem in dependency parsing, most previous studies used features constructed from large-scale auto-parsed data. Unlike previous work, we propose a new approach to improve dependency parsing with context-free dependency triples (CDT) extracted by using self-disambiguating patterns (SDP). The use of SDP makes it possible to avoid the dependency on a baseline parser and explore the influence of different types of substructures one by one. Additionally, taking the available CDTs as seeds, a label propagation process is used to tag a large number of unlabeled word pairs as CDTs. Experiments show that, when CDT features are integrated into a maximum spanning tree (MST) dependency parser, the new parser improves significantly over the baseline MST parser. Comparative results also show that CDTs with dependency relation labels perform much better than CDT without dependency relation label. © 2011 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | 2011 International Conference on Asian Language Processing | - |
dc.subject | Dependency parsing | - |
dc.subject | raw corpus | - |
dc.subject | self-disambiguating pattern | - |
dc.title | Improving Chinese dependency parsing with self-disambiguating patterns | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/IALP.2011.36 | - |
dc.identifier.scopus | eid_2-s2.0-84856052315 | - |
dc.identifier.spage | 7 | - |
dc.identifier.epage | 10 | - |