## 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)