A Dense Vector Representation for Relation Tuple Similarity

Ade Romadhony, Ayu Purwarianti, Dwi H. Widyantoro, Alfan Farizki Wicaksono

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Open Information Extraction (Open IE), which has been extensively studied as a new paradigm on unrestricted information extraction, produces relation tuples (results) which serve as intermediate structures in several natural language processing tasks, one of which is question answering system. In this paper, we investigate ways to learn the vector representation of Open IE relation tuples using various approaches, ranging from simple vector composition to more advanced methods, such as recursive autoencoder (RAE). The quality of vector representation was evaluated by conducting experiments on the relation tuple similarity task. While the results show that simple linear combination (i.e., averaging the vectors of the words participating in the tuple) outperforms any other methods, including RAE, RAE itself has its own advantage in dealing with a case, in which the similarity criterion is characterized by each element in the tuple, in cases where the simple linear combination is unable to identify them.

Original languageEnglish
Title of host publicationICAICTA 2018 - 5th International Conference on Advanced Informatics
Subtitle of host publicationConcepts Theory and Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages48-53
Number of pages6
ISBN (Electronic)9781538648049
DOIs
Publication statusPublished - 20 Nov 2018
Event5th International Conference on Advanced Informatics: Concepts Theory and Applications, ICAICTA 2018 - Krabi, Thailand
Duration: 14 Aug 201817 Aug 2018

Publication series

NameICAICTA 2018 - 5th International Conference on Advanced Informatics: Concepts Theory and Applications

Conference

Conference5th International Conference on Advanced Informatics: Concepts Theory and Applications, ICAICTA 2018
CountryThailand
CityKrabi
Period14/08/1817/08/18

Keywords

  • open-domain relation tuple
  • relation tuple similarity
  • vector representation

Fingerprint Dive into the research topics of 'A Dense Vector Representation for Relation Tuple Similarity'. Together they form a unique fingerprint.

Cite this