Extracting representative arguments from dictionaries for resolving zero pronouns
We propose a method to alleviate the problem of referential granularity for Japanese zero pronoun resolution. We use dictionary definition sentences to extract ‘representative’ arguments of predicative definition words; e.g. ‘arrest’ is likely to take police as the subject and criminal as its object...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/79571 http://hdl.handle.net/10220/6809 |
| _version_ | 1826124089151979520 |
|---|---|
| author | Nichols, Eric Bond, Francis Tanaka, Takaaki Nakaiwa, Hiromi Nariyama, Shigeko |
| author2 | School of Humanities and Social Sciences |
| author_facet | School of Humanities and Social Sciences Nichols, Eric Bond, Francis Tanaka, Takaaki Nakaiwa, Hiromi Nariyama, Shigeko |
| author_sort | Nichols, Eric |
| collection | NTU |
| description | We propose a method to alleviate the problem of referential granularity for Japanese zero pronoun resolution. We use dictionary definition sentences to extract ‘representative’ arguments of predicative definition words; e.g. ‘arrest’ is likely to take police as the subject and criminal as its object. These representative
arguments are far more informative than ‘person’ that is provided by other valency dictionaries. They are auto-extracted using both Shallow parsing and Deep parsing for greater quality and quantity. Initial results are highly promising, obtaining more specific
information about selectional preferences. An architecture of zero pronoun resolution using
these representative arguments is described. |
| first_indexed | 2024-10-01T06:14:57Z |
| format | Conference Paper |
| id | ntu-10356/79571 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:14:57Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/795712019-12-06T13:28:29Z Extracting representative arguments from dictionaries for resolving zero pronouns Nichols, Eric Bond, Francis Tanaka, Takaaki Nakaiwa, Hiromi Nariyama, Shigeko School of Humanities and Social Sciences Machine Translation Summit (10th : 2005) DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics DRNTU::Humanities::Language::Japanese We propose a method to alleviate the problem of referential granularity for Japanese zero pronoun resolution. We use dictionary definition sentences to extract ‘representative’ arguments of predicative definition words; e.g. ‘arrest’ is likely to take police as the subject and criminal as its object. These representative arguments are far more informative than ‘person’ that is provided by other valency dictionaries. They are auto-extracted using both Shallow parsing and Deep parsing for greater quality and quantity. Initial results are highly promising, obtaining more specific information about selectional preferences. An architecture of zero pronoun resolution using these representative arguments is described. Accepted version 2011-06-09T04:15:10Z 2019-12-06T13:28:29Z 2011-06-09T04:15:10Z 2019-12-06T13:28:29Z 2005 2005 Conference Paper Nariyama, S., Nichols, E., Bond, F., Tanaka, T., & Nakaiwa, H. (2005). Extracting representative arguments from dictionaries for resolving zero pronouns. Proceedings of Machine Translation Summit X, 3-10. https://hdl.handle.net/10356/79571 http://hdl.handle.net/10220/6809 155526 en Machine Translation Summit X © 2005 AAMT. This is the author created version of a work that has been peer reviewed and accepted for publication by Proceedings of Machine Translation Summit X, Asia-Pacific Association for Machine Translation. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://www.mt-archive.info/MTS-2005-Nariyama.pdf]. 8 p. application/pdf |
| spellingShingle | DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics DRNTU::Humanities::Language::Japanese Nichols, Eric Bond, Francis Tanaka, Takaaki Nakaiwa, Hiromi Nariyama, Shigeko Extracting representative arguments from dictionaries for resolving zero pronouns |
| title | Extracting representative arguments from dictionaries for resolving zero pronouns |
| title_full | Extracting representative arguments from dictionaries for resolving zero pronouns |
| title_fullStr | Extracting representative arguments from dictionaries for resolving zero pronouns |
| title_full_unstemmed | Extracting representative arguments from dictionaries for resolving zero pronouns |
| title_short | Extracting representative arguments from dictionaries for resolving zero pronouns |
| title_sort | extracting representative arguments from dictionaries for resolving zero pronouns |
| topic | DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics DRNTU::Humanities::Language::Japanese |
| url | https://hdl.handle.net/10356/79571 http://hdl.handle.net/10220/6809 |
| work_keys_str_mv | AT nicholseric extractingrepresentativeargumentsfromdictionariesforresolvingzeropronouns AT bondfrancis extractingrepresentativeargumentsfromdictionariesforresolvingzeropronouns AT tanakatakaaki extractingrepresentativeargumentsfromdictionariesforresolvingzeropronouns AT nakaiwahiromi extractingrepresentativeargumentsfromdictionariesforresolvingzeropronouns AT nariyamashigeko extractingrepresentativeargumentsfromdictionariesforresolvingzeropronouns |