Pivot language translation method and device based on similarity matching
A technology of similarity matching and pivot language, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve problems such as loss of translation rules
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0029] Embodiment 1: In this embodiment, a pivot language translation method based on similarity matching is specifically carried out in accordance with the following steps:
[0030] Step 1. Establishing a source language-target language translation rule base, which specifically includes the following steps:
[0031] Step 11, establishing the source language-pivot language translation rule base, in the source language-pivot language translation rule base, the pivot language phrase is represented as a vector form;
[0032] Step 12, establish the pivot language-target language translation rule base, in the pivot language-target language translation rule base, express the pivot language phrase as a vector form;
[0033] Step 13, searching the vector representation of at least one first pivot phrase semantically matching the source language phrase in the source language-pivot language translation rule base;
[0034] Step 14. Search the vector representation of at least one second...
specific Embodiment approach 2
[0038] Embodiment 2: In this embodiment, a pivot language translation device based on similarity matching, the device includes:
[0039] 1. The pivot language phrase vector representation module 410 is used to represent the pivot language phrase as a vector in the source language-pivot language translation rule base and convert the pivot language phrase into a vector form in the pivot language-target language translation rule base. Expressed in vector form;
[0040] 2. The pivot language phrase search module 420, whose function is to: search the vector representation of at least one first pivot language phrase that matches the semantics of the first source language phrase in the source language-pivot language translation rule base;
[0041] 3. The vector similarity calculation module 430 is used to calculate the semantic similarity between the pivot phrase in the pivot language-target language translation rule base and the first pivot phrase;
[0042] Four, the target languag...
Embodiment 1
[0049] Human language, also called natural language, exists in the form of words. In order to calculate the similarity of the language itself, it is necessary to represent the human language in the form of vectors. There are many ways to implement the process of representing human language using vectors. This example uses the word vector representation based on deep learning and extends it to phrase representation. In this embodiment, the establishment process of a Chinese "beginning" to Spanish "iniciar" translation rule with English as the pivotal language is taken as an example to specifically illustrate the technical solution of the present invention, which specifically includes the following steps (such as figure 1 shown):
[0050] Step 1: Establish the source language-pivot language translation rule base, and express the pivot language phrases in vector form in the source language-pivot language translation rule base.
[0051] Step 2, in the pivot language-target langu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com