Orthogonality regularizer for question answering - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

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.
Fichier principal
Vignette du fichier
orthogonality.pdf (157.13 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01623819 , version 1 (25-10-2017)

Identifiers

Cite

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⟩
406 View
80 Download

Altmetric

Share

Gmail Facebook X LinkedIn More