Automatic diagnosis and evaluation method for machine translation
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of automatic diagnosis and machine translation, applied in instruments, special data processing applications, electrical digital data processing, etc., can solve the problem that the processing capacity cannot obtain the translation system, etc.
Inactive Publication Date: 2009-09-02
HARBIN INST OF TECH
View PDF0 Cites 22 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0013] In order to solve the problem that existing translation system diagnosis methods can only examine the translation system’s ability to deal with specific monolingual phenomena and cannot obtain the defects of the translation system, this application proposes an automatic diagnosis and evaluation method for machine translation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0026] Specific implementation mode one: the machine translation automatic diagnosis and evaluation method described in this implementation mode is:
[0027] Step 1: Match the reference translation with the system translation at the vocabulary level;
[0028] Step 2: For each target language vocabulary, use translation knowledge to find possible source language vocabulary.
[0029] Step 3: Misrecognition, for each unmatched target language vocabulary is identified as a wrongly translated target language part; for a partial match, it is identified as a wrongly sorted target language part;
[0030] The fourth step: For each error, use the relationship between the source language and the target language to determine its bilingual type, and then use the relationship between bilingual features and translation knowledge to determine the cause of the error.
[0031] In the first step, the reference translation and the system translation are matched at the lexical level using a unigr...
specific Embodiment approach 2
[0109] Embodiment 2: This embodiment is an example of the machine translation automatic diagnosis and evaluation method described in Embodiment 1.
[0110] Here we give an example of misidentification.
[0111] Figure 5 A set of corresponding matching relationships between source language sentences and target sentences are given, the matching relationships are obtained according to translation rules, the target refers to the system translation, and the sentence refers to the system translation.
[0112] For the matching relationship between the target and the sentence, see Figure 6 As shown in , the translation system that generates the system translation uses the following translation rules:
[0114] Based on the above information, 3 translation errors can be identified as:
[0115] Incorrect translation due to translation model:
[0116] [desk, table, desk, Mis-Translatio...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention relates to an automatic diagnosis and evaluation method for machine translation, belonging to a machine translation evaluation technology and solving the problems that an evaluation method of the prior translation system can only test the processing capability of the translation system to a special monolingual phenomenon and can not obtain the defects of the translation system. The method comprises the following steps: firstly, matching words of a reference translation text and a systemic translation text and finding possible source language words for each object language word by utilizing translation knowledge; then, identifying errors and adopting the relation between source language and object language to judge a bilingual type of each error; and further utilizing the relation between the bilingual characteristics and the translation knowledge to judge the reasons of the errors. The automatic diagnosis and evaluation method for machine translation represents the bilingual errors by relative words in source language sentences, the reference translation text and the systemic translation text, induces the linguistics characteristics of the words in the diagnosis process and can more directly help developers to find and solve the inherent defects of the translation system.
Description
technical field [0001] The invention belongs to the diagnosis technology of machine translation, and in particular relates to an evaluation method of machine translation. Background technique [0002] Evaluating translation results is an important issue in the development of Statistical Machine Translation (SMT). Since manual evaluation is time-consuming and laborious, people have been working on developing automatic evaluation methods that can quickly evaluate the quality of translations. The current automatic evaluation method is through the translation of the system and human reference. Some of these methods have been widely used as standards for system comparison, such as BLEU (Papieni et al., 2002), NIST (Doddington, 2002), TER (Snover et al., 2006), GTM (Melamed et al., 2003) , Rouge (Lin and Och, 2004) and METEOR (Banerj ee and Lavie, 2005). [0003] However, the architecture of SMT is becoming more and more complex, often involving debugging of various modules and...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more