Dynamic Ensemble of Heterogeneous Encoding Models in Knowledge Extraction of Diverse Event Expressions
-
- Ishikawa Kai
- Data Science Research Laboratories, NEC Corporation
-
- Takamura Hiroya
- Laboratory for Future Interdisciplinary Research of Science and Technology, Institute of Innovative Research, Tokyo Institute of Technology Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology
-
- Okumura Manabu
- Laboratory for Future Interdisciplinary Research of Science and Technology, Institute of Innovative Research, Tokyo Institute of Technology
Bibliographic Information
- Other Title
-
- 多様なイベント表現を対象とした知識抽出における異なるエンコーディングモデル群の動的アンサンブル
- タヨウ ナ イベント ヒョウゲン オ タイショウ ト シタ チシキ チュウシュツ ニ オケル コトナル エンコーディングモデルグン ノ ドウテキ アンサンブル
Search this article
Abstract
<p>In this paper, we propose a novel ensemble approach for event nugget detection that consists of heterogeneous encoding models to handle diversifying linguistic expressions of events in text and a dynamic ensemble method to obtain an ensemble of reliable models for each input token dynamically. From a set of comparative evaluations in subtasks, we show that our proposed method exceeds each encoding model and soft voting in F1-score. Moreover, we prove the effectiveness of our proposal by comparing our evaluation system with the results of NIST TAC KBP2016 and KBP2017 participants in F1-scores. Lastly, we consider the usefulness of our proposed method in event nugget detection through a series of discussions on applying proposed method to recent neural network models.</p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 27 (2), 329-359, 2020-06-15
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390848647549735168
-
- NII Article ID
- 130007904624
-
- NII Book ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- NDL BIB ID
- 030502882
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed