Abstract
Distant supervision can automatically generate labeled data between a large-scale corpus and a knowledge base without utilizing human efforts. Therefore, many studies have used the distant supervision approach in relation extraction tasks. However, existing studies have a disadvantage in that they do not reflect the homograph in the word embedding used as an input of the relation extraction model. Thus, it can be seen that the relation extraction model learns without grasping the meaning of the word accurately. In this paper, we propose a relation extraction model with multi-sense word embedding. We learn multi-sense word embedding using a word sense disambiguation module. In addition, we use convolutional neural network and piecewise max pooling convolutional neural network relation extraction models that efficiently grasp key features in sentences. To evaluate the performance of the proposed model, two additional methods of word embedding were learned and compared. Accordingly, our method showed the highest performance among them.- Anthology ID:
- 2018.gwc-1.27
- Volume:
- Proceedings of the 9th Global Wordnet Conference
- Month:
- January
- Year:
- 2018
- Address:
- Nanyang Technological University (NTU), Singapore
- Editors:
- Francis Bond, Piek Vossen, Christiane Fellbaum
- Venue:
- GWC
- SIG:
- SIGLEX
- Publisher:
- Global Wordnet Association
- Note:
- Pages:
- 239–244
- Language:
- URL:
- https://aclanthology.org/2018.gwc-1.27
- DOI:
- Cite (ACL):
- Sangha Nam, Kijong Han, Eun-Kyung Kim, and Key-Sun Choi. 2018. Distant Supervision for Relation Extraction with Multi-sense Word Embedding. In Proceedings of the 9th Global Wordnet Conference, pages 239–244, Nanyang Technological University (NTU), Singapore. Global Wordnet Association.
- Cite (Informal):
- Distant Supervision for Relation Extraction with Multi-sense Word Embedding (Nam et al., GWC 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2018.gwc-1.27.pdf