Character-position arithmetic for analogy questions between word forms

Research output: Contribution to journalConference article

Abstract

We show how to answer analogy questions A:B::C:D of unknown D between word forms, by essentially relying on the basic arithmetic equality D[ib - ia + ic] = B[ib] - A[ia] + C[ic] on characters and positions at the same time. We decompose the problem into two steps: specification and decoding. We examine several techniques to implement each of these two steps. We perform experiments on a set of positive and negative examples and assess the accuracy of combinations of techniques. We then evaluate the performance of the best combination of techniques on a large set of more than 40 million analogy questions from the training data of a shared task in morphology. We obtain the correct answer in 94 % of the cases.

Original languageEnglish
Pages (from-to)23-32
Number of pages10
JournalCEUR Workshop Proceedings
Volume2028
Publication statusPublished - 2017 Jan 1
Event2017 ICCBR Workshops on Computational Analogy and Case-Based Reasoning, CAW 2017, Case-Based Reasoning and Deep Learning, CBRDL 2017 and Process-Oriented Case-Based Reasoning, POCBR 2017, Doctoral Consortium, and Competitions, ICCBR-WS 2017 - Trondheim, Norway
Duration: 2017 Jun 262017 Jun 28

Fingerprint

Decoding
Specifications
Experiments

Keywords

  • Analogy questions
  • Character-position arithmetic
  • Formal analogy

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Character-position arithmetic for analogy questions between word forms. / Lepage, Yves.

In: CEUR Workshop Proceedings, Vol. 2028, 01.01.2017, p. 23-32.

Research output: Contribution to journalConference article

@article{1321ea3ac5774901862a25ae57b746fa,
title = "Character-position arithmetic for analogy questions between word forms",
abstract = "We show how to answer analogy questions A:B::C:D of unknown D between word forms, by essentially relying on the basic arithmetic equality D[ib - ia + ic] = B[ib] - A[ia] + C[ic] on characters and positions at the same time. We decompose the problem into two steps: specification and decoding. We examine several techniques to implement each of these two steps. We perform experiments on a set of positive and negative examples and assess the accuracy of combinations of techniques. We then evaluate the performance of the best combination of techniques on a large set of more than 40 million analogy questions from the training data of a shared task in morphology. We obtain the correct answer in 94 {\%} of the cases.",
keywords = "Analogy questions, Character-position arithmetic, Formal analogy",
author = "Yves Lepage",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "2028",
pages = "23--32",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",

}

TY - JOUR

T1 - Character-position arithmetic for analogy questions between word forms

AU - Lepage, Yves

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We show how to answer analogy questions A:B::C:D of unknown D between word forms, by essentially relying on the basic arithmetic equality D[ib - ia + ic] = B[ib] - A[ia] + C[ic] on characters and positions at the same time. We decompose the problem into two steps: specification and decoding. We examine several techniques to implement each of these two steps. We perform experiments on a set of positive and negative examples and assess the accuracy of combinations of techniques. We then evaluate the performance of the best combination of techniques on a large set of more than 40 million analogy questions from the training data of a shared task in morphology. We obtain the correct answer in 94 % of the cases.

AB - We show how to answer analogy questions A:B::C:D of unknown D between word forms, by essentially relying on the basic arithmetic equality D[ib - ia + ic] = B[ib] - A[ia] + C[ic] on characters and positions at the same time. We decompose the problem into two steps: specification and decoding. We examine several techniques to implement each of these two steps. We perform experiments on a set of positive and negative examples and assess the accuracy of combinations of techniques. We then evaluate the performance of the best combination of techniques on a large set of more than 40 million analogy questions from the training data of a shared task in morphology. We obtain the correct answer in 94 % of the cases.

KW - Analogy questions

KW - Character-position arithmetic

KW - Formal analogy

UR - http://www.scopus.com/inward/record.url?scp=85040354099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040354099&partnerID=8YFLogxK

M3 - Conference article

VL - 2028

SP - 23

EP - 32

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -