Generalization of Semantic Roles in Automatic Semantic Role Labeling
-
- Matsubayashi Yuichiroh
- Department of Computer Science, University of Tokyo National Institute of Informatics, from this April
-
- Okazaki Naoaki
- Department of Computer Science, University of Tokyo
-
- Tsujii Jun’ichi
- Department of Computer Science, University of Tokyo School of Computer Science, University of Manchester National Centre for Text Mining, UK
Bibliographic Information
- Other Title
-
- 自動意味役割付与における意味役割の汎化
- ジドウ イミ ヤクワリ フヨ ニ オケル イミ ヤクワリ ノ ハンカ
Search this article
Description
A number of studies have applied machine-learning approaches to semantic role labeling with availability of corpora such as FrameNet and PropBank. These corpora define frame-specific semantic roles for each frame. It is crucial for the machine-learning approach because the corpus contain a number of infrequent roles which hinder an efficient learning. This paper focus on a generalization problem of semantic roles in a semantic role labeling task. We compare existing generalization criteria and our novel criteria, and clarify characteristics of each criterion. We also show that using multiple generalization criteria in a model improves the performance of a semantic role classification. In experiments on FrameNet, we achieved 19.16% error reduction in terms of total accuracy and 7.42% in macro F1 avarage. On PropBank, we reduced 24.07% of errors in total accuracy, and 26.39% of errors in the evaluation for unseen verbs.
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 17 (4), 59-89, 2010
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679453075200
-
- NII Article ID
- 10027016456
-
- NII Book ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- NDL BIB ID
- 10771976
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed