A Pointwise Approach to Training Dependency Parsers from Partially Annotated Corpora
-
- Flannery Daniel
- Graduate School of Informatics, Kyoto University
-
- Miyao Yusuke
- National Institute of Informatics
-
- Neubig Graham
- Graduate School of Informatics, Kyoto University Now affiliated with the Nara Institute of Science and Technology
-
- Mori Shinsuke
- Academic Center for Computing and Media Studies, Kyoto University
この論文をさがす
抄録
We introduce a word-based dependency parser for Japanese that can be trained from partially annotated corpora, allowing for effective use of available linguistic resources and reduction of the costs of preparing new training data. This is especially important for domain adaptation in a real-world situation. We use a pointwise approach where each edge in the dependency tree for a sentence is estimated independently. Experiments on Japanese dependency parsing show that this approach allows for rapid training and achieves accuracy comparable to state-of-the-art dependency parsers trained on fully annotated data.
収録刊行物
-
- 自然言語処理
-
自然言語処理 19 (3), 167-191, 2012
一般社団法人 言語処理学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282679453097600
-
- NII論文ID
- 130004566428
- 10031117752
-
- NII書誌ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- NDL書誌ID
- 024020144
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可