Orthogonality regularizer for question answering

Abstract : Learning embeddings of words and knowledge base elements is a promising approach for open domain question answering. Based on the remark that relations and entities are distinct object types lying in the same embedding space, we analyze the benefit of adding a regularizer favoring the embeddings of entities to be orthogonal to those of relations. The main motivation comes from the observation that modifying the embeddings using prior knowledge often helps performance. The experiments show that incorporating the regularizer yields better results on a challenging question answering benchmark.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01623819
Contributor : Claire Gardent <>
Submitted on : Wednesday, October 25, 2017 - 5:02:48 PM
Last modification on : Tuesday, February 12, 2019 - 10:30:06 AM
Long-term archiving on : Friday, January 26, 2018 - 2:30:32 PM

File

orthogonality.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Chunyang Xiao, Guillaume Bouchard, Marc Dymetman, Claire Gardent. Orthogonality regularizer for question answering. *SEM 2016,. The Fifth Joint Conference on Lexical and Computational Semantics, Aug 2016, Berlin, Germany. pp.142 - 147, ⟨10.18653/v1/S16-2019⟩. ⟨hal-01623819⟩

Share

Metrics

Record views

444

Files downloads

94