Statistical Identification of Pleonastic Pronouns
(2012) The Fourth Swedish Language Technology Conference p.67-68- Abstract
- This paper describes an algorithm to identify pleonastic pronouns using statistical techniques. The training step uses a coreference
annotated corpus of English and focuses on a set of pronouns such as it. As far as we know, there is no corpus with a pleonastic
annotation. The main idea of the algorithm was then to recast the definition of pleonastic pronouns as pronouns that never occur
in a coreference chain. We integrated this algorithm in an existing coreference solver (Bj¨orkelund and Nugues, 2011) and we
measured the overall performance gains brought by the pleonastic it removal. We observed an improvement of 0.42 from 59.15
of the CoNLL score. The complete system (Stamborg et al., 2012)... (More) - This paper describes an algorithm to identify pleonastic pronouns using statistical techniques. The training step uses a coreference
annotated corpus of English and focuses on a set of pronouns such as it. As far as we know, there is no corpus with a pleonastic
annotation. The main idea of the algorithm was then to recast the definition of pleonastic pronouns as pronouns that never occur
in a coreference chain. We integrated this algorithm in an existing coreference solver (Bj¨orkelund and Nugues, 2011) and we
measured the overall performance gains brought by the pleonastic it removal. We observed an improvement of 0.42 from 59.15
of the CoNLL score. The complete system (Stamborg et al., 2012) participated in the CoNLL 2012 shared task (Pradhan et al.,
2012), where it obtained the 4th rank. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3191726
- author
- Stamborg, Marcus and Nugues, Pierre LU
- organization
- publishing date
- 2012
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- SLTC 2012 : The Fourth Swedish Language Technology Conference - The Fourth Swedish Language Technology Conference
- pages
- 67 - 68
- publisher
- SLTC
- conference name
- The Fourth Swedish Language Technology Conference
- conference location
- Lund, Sweden
- conference dates
- 2012-10-24 - 2012-10-26
- language
- English
- LU publication?
- yes
- id
- 72f4afad-dfa7-4209-b5ba-d9961fb27163 (old id 3191726)
- date added to LUP
- 2016-04-04 14:13:31
- date last changed
- 2021-05-06 16:07:57
@inproceedings{72f4afad-dfa7-4209-b5ba-d9961fb27163, abstract = {{This paper describes an algorithm to identify pleonastic pronouns using statistical techniques. The training step uses a coreference<br/><br> annotated corpus of English and focuses on a set of pronouns such as it. As far as we know, there is no corpus with a pleonastic<br/><br> annotation. The main idea of the algorithm was then to recast the definition of pleonastic pronouns as pronouns that never occur<br/><br> in a coreference chain. We integrated this algorithm in an existing coreference solver (Bj¨orkelund and Nugues, 2011) and we<br/><br> measured the overall performance gains brought by the pleonastic it removal. We observed an improvement of 0.42 from 59.15<br/><br> of the CoNLL score. The complete system (Stamborg et al., 2012) participated in the CoNLL 2012 shared task (Pradhan et al.,<br/><br> 2012), where it obtained the 4th rank.}}, author = {{Stamborg, Marcus and Nugues, Pierre}}, booktitle = {{SLTC 2012 : The Fourth Swedish Language Technology Conference}}, language = {{eng}}, pages = {{67--68}}, publisher = {{SLTC}}, title = {{Statistical Identification of Pleonastic Pronouns}}, url = {{https://lup.lub.lu.se/search/files/19769020/3191727.pdf}}, year = {{2012}}, }