System and method of automatic example sentence search based on weighted editing distance

Abstract

A method and computer-readable medium are provided that retrieve example sentences from a collection of sentences. An input query sentence is received, and candidate example sentences for the input query sentence are selected from the collection of sentences using a term frequency-inverse document frequency (TF-IDF) algorithm. The selected candidate example sentences are then re-ranked based upon weighted editing distances between the selected candidate example sentences and the input query sentence. A system which implements the method is also provided.

Description

technical field [0001] The present invention relates to a machine-aided writing system and method, in particular to a system and method for automatic example sentence retrieval to assist writing or translation processing. Background technique [0002] Automatic example sentence retrieval is necessary or useful in various applications. For example, in example-based machine translation, it is necessary to retrieve sentences that are grammatically similar to the sentence being translated. Then get translated by activating or selecting a retrieved sentence. [0003] In machine-assisted translation systems, such as a translation memory system, a retrieval method is required to obtain associated sentences. However many retrieval algorithms suffer from different types of shortcomings, some of which are ineffective. For example, the retrieved sentences often have little relationship to the input sentences. Other problems with many retrieval algorithms include the fact that some ...

AI Technical Summary

Problems solved by technology

Unfortunately, for some societies with entirely different cultures and writing styles, the ability to write in a non-native language is a perpetual barrier

Images