Translation quality quantifying apparatus and method
AssigneeMultiling Corporation
InventorsMichael V. Sneddon, Brian R Chandler
Life of this patent
Estimating the term…
Abstract
A system for automating the quality evaluation of a translation. The system may include a computer having a processor and memory device operably connected to one another. A source text in a first language may be stored within the memory device. A target text comprising a translation of the source text into a second language may also be stored within the memory device. Additionally, a plurality of executables may be stored on the memory device and be configured to, when executed by the processor, independently identify a test sample comprising one or more blocks, each comprising a matched set having a source portion selected from the source text and a corresponding target portion selected from the target text.
Claims20
A computer system for sampling a translation to determine an overall quality thereof, the computer system comprising a processor and memory, wherein:
- the memory stores
- a source document corresponding to a first language,
- a target document comprising a translation of the source document in a second language, distinct from the first language, and
- executables comprising a metric module, an error reporting module, and an output module;
- the computer system is programmed to, by executing the metric module, identify a sample comprising substantially less than an entirety of the translation, a source portion selected from the source document, and a corresponding target portion selected from the target document;
- the computer system is programmed to, by executing the error reporting module, present to a human reviewer a list of preset error categories when the sample is being evaluated by the human reviewer;
- and
- the computer system is programmed to, by executing the output module, generalize error data associated with the sample into an overall quality characterization of the entirety of the translation.
A system for facilitating a translation and sampling the translation to determine an overall quality thereof, the system comprising:
- a first computer and a second computer operably connected to a database;
- the first computer comprising a first processor and first memory device operably connected to one another to operate as a translator workstation;
- the first computer, wherein the first processor is programmed to execute a translation assisting software module that assists a human translator by retrieving, from the database, a source document and storing, to the database, a target document that is a translation of the source document;
- the second computer comprising a second processor and second memory device operably connected to one another to operate as a reviewer work station;
- the second computer, wherein the second processor is programmed to execute a quality quantifying software module that operates to assist a human reviewer by
- retrieving a sample from the database, the sample comprising substantially less than an entirety of the translation, a subset of the target document, and a corresponding subset of the source document,
- providing a list of preset error categories,
- receiving selections from a reviewer as selected from the preset error categories, and
- generalizing the selections associated with the sample into an overall quality characterization of the entirety of the translation.
A method for facilitating a translation and sampling the translation to determine an overall quality thereof, the method comprising:
- executing, by a first processor, a translation assisting software module to assist a human translator by:
- retrieving a source document from a database and
- storing, to the database, a target document that is a translation of the source document;
- and
- executing, by a second processor, a quality quantifying software module to assist a human reviewer by:
- retrieving a sample from the database, the sample comprising substantially less than an entirety of the translation, a subset of the source document, and a corresponding subset of the target document,
- providing a list of preset error categories,
- receiving selections from a reviewer as selected from the preset error categories, and
- generalizing the selections associated with the sample into an overall quality characterization of the entirety of the translation.
Dependencies are inferred from the claim text.