Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder

Ryo Takahashi, Ran Tian, Kentaro Inui


Abstract
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices – for one reason, composition of two relations M1, M2 may match a third M3 (e.g. composition of relations currency_of_country and country_of_film usually matches currency_of_film_budget), which imposes compositional constraints to be satisfied by the parameters (i.e. M1*M2=M3). In this paper we investigate a dimension reduction technique by training relations jointly with an autoencoder, which is expected to better capture compositional constraints. We achieve state-of-the-art on Knowledge Base Completion tasks with strongly improved Mean Rank, and show that joint training with an autoencoder leads to interpretable sparse codings of relations, helps discovering compositional constraints and benefits from compositional training. Our source code is released at github.com/tianran/glimvec.
Anthology ID:
P18-1200
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2148–2159
Language:
URL:
https://aclanthology.org/P18-1200
DOI:
10.18653/v1/P18-1200
Bibkey:
Cite (ACL):
Ryo Takahashi, Ran Tian, and Kentaro Inui. 2018. Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2148–2159, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder (Takahashi et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1200.pdf
Presentation:
 P18-1200.Presentation.pdf
Video:
 https://vimeo.com/285805371
Code
 tianran/glimvec
Data
FB15k-237