Solving Analogies on Words: An Algorithm

نویسنده

  • Yves Lepage
چکیده

Un rappel de travaux pr4c4dents sur l'analogie en psychologie, en intelligence artificieUe et en traitement automatique des langues pr4cSde la pr4sentation d'un algorithme de r4solution, au niveau morphologique, d'analogies entre mots. Cet algorithme cr4e un quatri~me mot h partir de trois mots donn4s, quand c'est possible. Par exemple, 4rant donn4s fable, fabuleux et miracle, l'algorithme cr4e bien miraculeux. Des cas bien plus difficiles sont correctement r4solus par ralgorithme, en particulier, les cas d'infixation multiple, n4cessaires pour rendre compte de la morphologie des langues s4mitiques. Nous donnons les caract4ristiques de l'algorithme et mentionnons quelques applications possibles. S t r e s z c z e n i e

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Architects and Engineers Differences: A comparison between problem solving performances of architects and engineers in the ideation phase of an analogy-based design

This study examines how analogy affects problem-solving in ideation phase of design among architects and engineers. For this purpose, a design problem was given to master and Ph.D. students of engineering and architecture. They were given two optional analogy sources to choose and be inspired by one. From the analysis of design sessions, using different coding groups and the application of the ...

متن کامل

community2vec: Vector representations of online communities encode semantic relationships

Vector embeddings of words have been shown to encode meaningful semantic relationships that enable solving of complex analogies. This vector embedding concept has been extended successfully to many different domains and in this paper we both create and visualize vector representations of an unstructured collection of online communities based on user participation. Further, we quantitatively and...

متن کامل

Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen

Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as king:man :: woman:queen) are indicative of the quality of the embedding. We question this assumption by showing that the information not detected by linear offset may still be recoverable by a more sophisticated search method, and thus is actua...

متن کامل

Yard crane scheduling in port container terminals using genetic algorithm

Yard crane is an important resource in container terminals. Efficient utilization of the yard crane significantly improves the productivity and the profitability of the container terminal. This paper presents a mixed integer programming model for the yard crane scheduling problem with non- interference constraint that is NPHARD in nature. In other words, one of the most important constraints in...

متن کامل

Solving a New Multi-Period Mathematical Model of the Rail-Car Fleet Size and Car Utilization by Simulated Annealing

There is a significant interaction between sizing a fleet of rail cars and its utilization. This paper presents a new multi-period mathematical model and a solution procedure to optimize the rail-car fleet size and freight car allocation, wherein car demands, and travel times, are assumed to be deterministic, and unmet demands are backordered. This problem is considered NP-complete. In other wo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998