Shumin Wu
University of Colorado Boulder
7 Papers
198 Citations
Shumin Wu is an academic researcher from University of Colorado Boulder. The author has contributed to research in topics: Semantic role labeling & PropBank. The author has an hindex of 4, co-authored 7 publications. Previous affiliations of Shumin Wu include Brandeis University.
Chat about Author
Papers
•Book
Semantic Role Labeling
Martha Palmer,Ivan Titov,Shumin Wu +2 more
- 15 Jan 2010
TL;DR: This book is aimed at providing an overview of several aspects of semantic role labeling, including the use of joint inference to take advantage of context sensitivities, and attempts to improve performance by closer integration of the syntactic parsing task with semantic roles labeling.
•Proceedings Article
Detecting Cross-lingual Semantic Similarity Using Parallel PropBanks.
Shumin Wu,Jinho D. Choi,Martha Palmer +2 more
- 01 Jan 2010
TL;DR: This paper begins by improving word alignments for verb predicates generated by GIZA++ by using information available in parallel PropBanks to measure predicate-argument matching and improved verb predicate alignments by an F-score of 12.6%.
8
Can Selectional Preferences Help Automatic Semantic Role Labeling
Shumin Wu,Martha Palmer +1 more
- 01 Jun 2015
TL;DR: A topic model based approach for selectional preference using the topic features generated by an LDA model on the extracted predicate-arguments over the Chinese Gigaword corpus, which shows improvement to the state-of-the-art Chinese SRL system.
•Proceedings Article
Focusing Annotation for Semantic Role Labeling
Daniel W. Peterson,Martha Palmer,Shumin Wu +2 more
- 01 May 2014
TL;DR: It is shown that language models may be used to select sentences that are more useful to annotate, and the least probable sentences provide dramatic improved system performance over the baseline, especially when only a small portion of the data is annotated.
Leveraging Semantic Similarity in Parallel Corpora for Natural Language Processing
Shumin Wu
- 01 Jan 2015
TL;DR: Meaning Representation graph structure semantic representation of the whole sentence (including PropBank style arguments, coreference, named entity recognition, etc) Prague Workshop preliminary parsing results.