• Corpus ID: 36021421

Character-Position Arithmetic for Analogy Questions between Word Forms

  title={Character-Position Arithmetic for Analogy Questions between Word Forms},
  author={Y. Lepage},
  booktitle={International Conference on Case-Based Reasoning},
  • Y. Lepage
  • Published in
    International Conference on…
  • Computer Science
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… 

Figures and Tables from this paper

A Neural Approach for Detecting Morphological Analogies

This paper proposes a deep learning approach to detect morphological analogies, for instance, with reinflexion or conjugation, and presents empirical results that show that this framework is competitive with state of the art symbolic approaches.

Numerical Methods for Retrieval and Adaptation in Nagao’s EBMT model

  • Kun HeT. ZhaoY. Lepage
  • Computer Science
    2018 International Conference on Advanced Computer Science and Information Systems (ICACSIS)
  • 2018
We build an example-based machine translation system. It is an instance of case-based reasoning for machine translation. We introduce numerical methods instead of symbolic methods in two steps:

Context Encoder for Analogies on Strings

A model based on context encoder to solve formal analogies on strings like aaabbbccc and ubid to show slight increases in accuracy, in comparison to a fully connected neural network architecture.

Tackling Morphological Analogies Using Deep Learning - Extended Version

This paper proposes an approach using deep learning to detect and solve morphological analogies, which encodes structural properties of analogical proportions and relies on a specifically designed embedding model capturing morphological characteristics of words.

Solving Morphological Analogies Through Generation

This contribution is a first attempt at solving morphological analogies through generation, instead of relying on retrieval approaches. Our preliminary experiments show promising results for some

Réseaux de neurones pour la résolution d'analogies entre phrases en traduction automatique par l'exemple (Neural networks for the resolution of analogies between sentences in EBMT )

Un modele de reseau de neurones pour the resolution d’equations analogiques au niveau semantique et entre phrases dans le cadre de the traduction automatique par l’exemple are proposed.

Solving Analogies on Words based on Minimal Complexity Transformation

A rough estimation of complexity for word analogies and an algorithm to find the optimal transformations of minimal complexity is proposed and compared with state-of-the-art approaches to demonstrate the interest of using complexity to solve analogies on words.



Linguistic Regularities in Continuous Space Word Representations

The vector-space word representations that are implicitly learned by the input-layer weights are found to be surprisingly good at capturing syntactic and semantic regularities in language, and that each relationship is characterized by a relation-specific vector offset.

Proportional Analogy in Written Language Data

The purpose of this paper is to summarize some of the results obtained over many years of research in proportional analogy applied to natural language processing, some of which were obtained in structuring language data by the characters (bitmaps), words or short sentences in several languages like Chinese or English.

Translating Unknown Words by Analogical Learning

This study shows that analogical learning offers as well an elegant and effective solution to the problem of identifying potential translations of unknown words.

Language Production, Cognition, and the Lexicon

This book discusses language resources, reading and writing technologies, and how to improve a Language Quality of Requirements using the Lexical Ontology and Lexicon.

Algorithms for Approximate String Matching

Scaling up Analogical Learning

Different strategies for efficiently solving the identification of analogies in the input space are investigated and their scalability is studied.

The Hungarian method for the assignment problem

  • H. Kuhn
  • Economics
    50 Years of Integer Programming
  • 2010
This paper has been presented with the Best Paper Award. It will appear in print in Volume 52, No. 1, February 2005.

De l'analogie rendant compte de la commutation en linguistique

La grammaticalite, c'est-a-dire l'appartenance a un langage, est testee par egalite avec certaines chaines attestees apres reduction selon des modeles analogiques, eux aussi attestes.

Solving Analogies on Words: An Algorithm

The algorithm presented in this paper takes a path that is inverse to the historical development of the idea of analogy, which is necessary, because a certain incomprehension is faced when speaking about linguistic analogy.

Solution of the optimal assignment problem by diagonal scaling algorithms

It is shown that a solution of the optimal assignment problem can be obtained as the limit of the solution of an entropy maximization problem, as a deformation parameter tends to infinity, which allows the Sinkhorn algorithm to be used as a preprocessing to handle large dense optimal assignment problems.