Character-position arithmetic for analogy questions between word forms

Yves Lepage

Character-position arithmetic for analogy questions between word forms

Yves Lepage^*

^*Corresponding author for this work

Graduate School of Information, Production and Systems

Research output: Contribution to journal › Conference article › peer-review

4 Citations (Scopus)

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[i_b - i_a + i_c] = B[i_b] - A[i_a] + C[i_c] 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 language	English
Pages (from-to)	23-32
Number of pages	10
Journal	CEUR Workshop Proceedings
Volume	2028
Publication status	Published - 2017
Event	2017 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 26 → 2017 Jun 28

Keywords

Analogy questions
Character-position arithmetic
Formal analogy

ASJC Scopus subject areas

Computer Science(all)

Cite this

@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",

note = "Funding Information: ★ This work was supported by a JSPS Grant, Number 15K00317 (Kakenhi C), entitled Language productivity: efficient extraction of productive analogical clusters and their evaluation using statistical machine translation. Publisher Copyright: Copyright {\textcopyright} 2017 for this paper by its authors.; 2017 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 ; Conference date: 26-06-2017 Through 28-06-2017",

year = "2017",

language = "English",

volume = "2028",

pages = "23--32",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

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

AU - Lepage, Yves

N1 - Funding Information: ★ This work was supported by a JSPS Grant, Number 15K00317 (Kakenhi C), entitled Language productivity: efficient extraction of productive analogical clusters and their evaluation using statistical machine translation. Publisher Copyright: Copyright © 2017 for this paper by its authors.

PY - 2017

Y1 - 2017

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

AN - SCOPUS:85040354099

SN - 1613-0073

VL - 2028

SP - 23

EP - 32

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 2017 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

Y2 - 26 June 2017 through 28 June 2017

ER -

Character-position arithmetic for analogy questions between word forms

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this