CN111177412B - Public logo bilingual parallel corpus system - Google Patents

Abstract

The invention relates to a bilingual parallel corpus system of public signs, comprising a corpus collection module, a classification and labeling module, a parallel corpus information sub-database, a corpus information sub-database, a category index table, and a query information extraction module, which collects collected information through the classification and labeling module The corpus information is stored in the parallel corpus information sub-database by category, and the corpus information sub-database uses the secondary classification to establish associations with other main classifications, so that the corresponding bilingual parallel corpus information can be quickly found within the required range when querying information . Aiming at the problem that public logos involve many fields, the present invention specially designs an interrelated multi-level labeling form to classify and label the stored public logo corpus information, and combine semantic labeling to make corpus with possible associations All can be quickly displayed in the query, and the query search of non-related corpus is effectively excluded, and the use efficiency of the bilingual parallel corpus of public signs is improved.

Description

Public logo bilingual parallel corpus system

technical field

The invention relates to a bilingual parallel corpus system of public signs.

Background technique

Public signs, also known as public signs, are mainly indicative voices provided in cities for the convenience of the public or tourists, including service facilities, agency names, billboards, public facilities, public transportation, tourist attractions, street signs , slogans, shop signs, etc., its role is to provide effective information to the public through concise language. With the development of economy and culture, especially the development of tourism, many cities have attracted a large number of foreign friends, so the translation of public signs is particularly important. important role in the development of the industry. Correct and appropriate translations of public signs can provide good and convenient help for tourists from all over the world and improve the overall image of the city. On the contrary, wrong and inappropriate public sign translations will bring obstacles or even misunderstandings to foreign tourists. Therefore, it is necessary to ensure the accuracy of the translation of public signs.

In the process of improving the translation accuracy of public signs, it is very important to establish a reasonable and accurate bilingual parallel corpus of public signs. Since public signs involve many fields, how to enable users to obtain the required public signs quickly and accurately? Bilingual corpus information of signs is urgently needed by those skilled in the art.

Contents of the invention

Aiming at the above technical problems, the present invention provides a bilingual parallel corpus system of public signs, which utilizes computer information processing technology to improve the acquisition efficiency of bilingual parallel corpora of public signs.

To achieve the above object, the technical scheme adopted in the present invention is as follows:

A bilingual parallel corpus system for public signs, including:

The corpus collection module is used to collect and obtain bilingual parallel corpus information of public signs from external information channels;

The classification and labeling module is used to label the bilingual parallel corpus information of public signs obtained by the corpus collection module according to the preset category, and output the corresponding category identifier. The preset category includes at least the corresponding public sign bilingual parallel corpus The first-level category of the main classification of information, and the second-level category of the secondary classification of bilingual parallel corpus information corresponding to the public logo. class identifier;

Parallel corpus information sub-database, the number of which matches the number of first-level categories of bilingual parallel corpus information of public signs, and is used to independently store the bilingual parallel corpus information of public signs according to main classifications;

The corpus information sub-database belongs to each parallel corpus information sub-database, and is used to store the second-type identifiers generated by the bilingual parallel corpus information of the current classification of public signs according to its secondary classification, and to make the second-type identifiers establish a relationship with other Associations between primary categories;

The category index table is used to record and store the category identifier, and configure a jump interface on the second category identifier associated with the first category;

The query information extraction module is used to label the input information semantically with the category identifiers it may involve, so that it can directly compare the category index table to perform traversal information query in the corresponding parallel corpus information sub-database.

Specifically, the second-class identifier establishes a relationship between other first-level categories that match it through the semantic context of the secondary classification.

Further, the public logo bilingual parallel corpus information stored in each of the parallel corpus information sub-databases is configured with a priority value, and the priority values are sorted according to their query frequency.

Further, the corpus information sub-base is configured with a degree of relevance value, which is used to indicate the semantic correlation between bilingual parallel corpus information of different common logos.

Compared with the prior art, the present invention has the following beneficial effects:

Aiming at the problem that public logos involve many fields, the present invention specially designs an interrelated multi-level labeling form to classify and label the stored public logo corpus information, and combine semantic labeling to make corpus with possible associations All can be quickly displayed in the query, and effectively exclude the query search of non-related corpora, improve the efficiency of the use of the bilingual parallel corpus of public signs, and play an important role in promoting the application of public signs.

Description of drawings

Fig. 1 is a functional block diagram of the present invention.

Detailed ways

The present invention will be further described below with reference to the accompanying drawings and embodiments, and the mode of the present invention includes but not limited to the following embodiments.

Example

As shown in Figure 1, the public logo bilingual parallel corpus system includes:

The corpus collection module is used to collect and obtain bilingual parallel corpus information of public signs from external information channels;

The classification and labeling module is used to label the bilingual parallel corpus information of public signs obtained by the corpus collection module according to the preset category, and output the corresponding category identifier. The preset category includes at least the corresponding public sign bilingual parallel corpus The first-level category of the main classification of information, and the second-level category of the secondary classification of bilingual parallel corpus information corresponding to the public logo. class identifier;

Parallel corpus information sub-database, the number of which matches the number of first-level categories of bilingual parallel corpus information of public signs, and is used to independently store the bilingual parallel corpus information of public signs according to main classifications;

The corpus information sub-database, which belongs to each parallel corpus information sub-database, is used to store the second-type identifiers generated by the secondary classification of the bilingual parallel corpus information of the current classification of public signs, and make the second-type identifiers pass through the secondary The semantic context of the classification establishes the association between other first-level categories that match it; wherein the corpus information sub-base is configured with an association degree value, which is used to indicate the semantic correlation between bilingual parallel corpus information of different public signs sex;

The category index table is used to record and store the category identifier, and configure a jump interface on the second category identifier associated with the first category;

The query information extraction module is used to label the input information semantically with the category identifiers it may involve, so that it can directly compare the category index table to perform traversal information query in the corresponding parallel corpus information sub-database.

In addition, the bilingual parallel corpus information of public logos stored in each parallel corpus information sub-database is configured with a priority value, and the priority values are sorted according to their frequency of being queried.

In practical applications, when a user queries a piece of public logo corpus, the query information extraction module first labels the category identifiers, and then the system first assigns the parallel corpus information associated with it to be queried according to the category identifiers. Sub-databases, and then query according to the actual keyword information in these sub-databases, so as to quickly and accurately obtain the required bilingual parallel corpus information.

The above-mentioned embodiment is only one of the preferred implementation modes of the present invention, and should not be used to limit the scope of protection of the present invention, but any modification or embellishment without substantive significance made on the main design concept and spirit of the present invention shall be solved by it. If the technical problems are still consistent with the present invention, all should be included in the protection scope of the present invention.

Claims (3)

1. A bilingual parallel corpus system of public signs, characterized in that it comprises: The corpus collection module is used to collect and obtain bilingual parallel corpus information of public signs from external information channels; The classification and labeling module is used to label the bilingual parallel corpus information of public signs obtained by the corpus collection module according to the preset category, and output the corresponding category identifier. The preset category includes at least the corresponding public sign bilingual parallel corpus The first-level category of the main classification of information, and the second-level category of the secondary classification of bilingual parallel corpus information corresponding to the public logo. class identifier; Parallel corpus information sub-database, the number of which matches the number of first-level categories of bilingual parallel corpus information of public signs, and is used to independently store the bilingual parallel corpus information of public signs according to main classifications; The corpus information sub-database belongs to each parallel corpus information sub-database, and is used to store the second-type identifiers generated by the bilingual parallel corpus information of the current classification of public signs according to its secondary classification, and to make the second-type identifiers establish a relationship with other The association between the first-level categories; wherein the second-class identifier establishes the association between other first-level categories matching it through the semantic context of the secondary classification; The category index table is used to record and store the category identifier, and configure a jump interface on the second category identifier associated with the first category; The query information extraction module is used to label the input information semantically with the category identifiers it may involve, so that it can directly compare the category index table to perform traversal information query in the corresponding parallel corpus information sub-database. 2. the bilingual parallel corpus system of public signs according to claim 1, is characterized in that, the bilingual parallel corpus information of public signs stored in each said parallel corpus information sub-bank is configured with a priority value, and the priority value Sort by how often they are queried. 3. The public sign bilingual parallel corpus system according to claim 2, wherein the corpus information sub-base is configured with a degree of relevance value for indicating the semantic correlation between different public sign bilingual parallel corpus information sex.

Images