Dual Constrained Question Embeddings with Relational Knowledge Bases for Simple Question Answering

Kaustubh Kulkarni, Riku Togashi, Hideyuki Maeda, Sumio Fujita


Abstract
Embedding based approaches are shown to be effective for solving simple Question Answering (QA) problems in recent works. The major drawback of current approaches is that they look only at the similarity (constraint) between a question and a head, relation pair. Due to the absence of tail (answer) in the questions, these models often require paraphrase datasets to obtain adequate embeddings. In this paper, we propose a dual constraint model which exploits the embeddings obtained by Trans* family of algorithms to solve the simple QA problem without using any additional resources such as paraphrase datasets. The results obtained prove that the embeddings learned using dual constraints are better than those with single constraint models having similar architecture.
Anthology ID:
I17-2037
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
217–221
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/I17-2037/
DOI:
Bibkey:
Cite (ACL):
Kaustubh Kulkarni, Riku Togashi, Hideyuki Maeda, and Sumio Fujita. 2017. Dual Constrained Question Embeddings with Relational Knowledge Bases for Simple Question Answering. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 217–221, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Dual Constrained Question Embeddings with Relational Knowledge Bases for Simple Question Answering (Kulkarni et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/I17-2037.pdf