Context encoder for analogies on strings

Tianjing Zhao, Yves Lepage

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

We propose a model based on context encoder to solve formal analogies on strings likeaaabbbccc : aaaabbbbcccc :: abc : x )x = aabbcc or ubid : tubid :: ofjid : x) x = tofjid. As a context encodermodel, it consists of a generator and a discriminator. The generator attempts at generating the result of an analogical equation, whilethe discriminator attempts at discriminatingsolutions coming out of the generator againstthe real solution of the analogical equation.We conduct experiments on publicly availabledata sets to compare the performance of ourmodel with a previously published method designed for the same task. Our results showslight increases in accuracy, in comparison toa fully connected neural network architecture.

Original languageEnglish
Pages832-840
Number of pages9
Publication statusPublished - 2018
Event32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018 - Hong Kong, Hong Kong
Duration: 2018 Dec 12018 Dec 3

Conference

Conference32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018
CountryHong Kong
CityHong Kong
Period18/12/118/12/3

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)

Fingerprint Dive into the research topics of 'Context encoder for analogies on strings'. Together they form a unique fingerprint.

Cite this