Using WordNet to Extend FrameNet Coverage
(2007) Building Frame Semantics Resources for Scandinavian and Baltic Languages p.27-30- Abstract
- We present two methods to address the problem of sparsity in the FrameNet lexical database. The first method is based on the idea that a word that belongs to a frame is ``similar'' to the other words in that frame. We measure the similarity using a WordNet-based variant of the Lesk metric. The second method uses the sequence of synsets in WordNet hypernym trees as feature vectors that can be used to train a classifier to determine whether a word belongs to a frame or not. The extended dictionary produced by the second method was used in a system for FrameNet-based
semantic analysis and gave an improvement in recall.
We believe that the methods are useful for bootstrapping FrameNets for new languages.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/630189
- author
- Johansson, Richard LU and Nugues, Pierre LU
- organization
- publishing date
- 2007
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Frame semantics, natural language processing, WordNet, FrameNet
- host publication
- LU-CS-TR: 2007-240
- editor
- Nugues, Pierre and Johansson, Richard
- pages
- 4 pages
- publisher
- Department of Computer Science, Lund University
- conference name
- Building Frame Semantics Resources for Scandinavian and Baltic Languages
- conference location
- Tartu, Estonia
- conference dates
- 2007-05-24
- ISBN
- 978-91-976939-0-5
- language
- English
- LU publication?
- yes
- id
- 8fba37ed-1c65-4f5d-8311-2cec266dd392 (old id 630189)
- date added to LUP
- 2016-04-04 10:58:45
- date last changed
- 2021-05-06 17:17:01
@inproceedings{8fba37ed-1c65-4f5d-8311-2cec266dd392, abstract = {{We present two methods to address the problem of sparsity in the FrameNet lexical database. The first method is based on the idea that a word that belongs to a frame is ``similar'' to the other words in that frame. We measure the similarity using a WordNet-based variant of the Lesk metric. The second method uses the sequence of synsets in WordNet hypernym trees as feature vectors that can be used to train a classifier to determine whether a word belongs to a frame or not. The extended dictionary produced by the second method was used in a system for FrameNet-based<br/><br> semantic analysis and gave an improvement in recall.<br/><br> We believe that the methods are useful for bootstrapping FrameNets for new languages.}}, author = {{Johansson, Richard and Nugues, Pierre}}, booktitle = {{LU-CS-TR: 2007-240}}, editor = {{Nugues, Pierre and Johansson, Richard}}, isbn = {{978-91-976939-0-5}}, keywords = {{Frame semantics; natural language processing; WordNet; FrameNet}}, language = {{eng}}, pages = {{27--30}}, publisher = {{Department of Computer Science, Lund University}}, title = {{Using WordNet to Extend FrameNet Coverage}}, url = {{https://lup.lub.lu.se/search/files/5665827/630202.pdf}}, year = {{2007}}, }