Automated translation of subject matter specific documents

Abstract

Documents in source natural languages are translated into target natural languages using a computer-implemented translation that is configured to operate within the domain of the subject matter of the documents that imposes specialized requirements for translation and readability. Subject matter specific documents typically include domain-specific terminology, are subject to various regulatory guidelines, and have different readability requirements depending on the intended reader. The computer-implemented translation applies machine-learning techniques that deconstruct elements of the subject matter specific document into a standard data structure and perform pre-processing steps to tokenize digitized document text to identify the correct sentence structure and syntax for the target natural language to optimize translation by, e.g., a neural machine translation engine. The text segments that are input into the neural machine translation engine are generated to be semantically meaningful in the target natural language to thereby enhance the understanding of the neural machine translation engine.

What is claimed: 
     
         1 . A computer-implemented method comprising:
 identifying a plurality of segments in a received clinical trial document;   for each of the identified segments, matching the identified segment to a portion of a translated clinical trial document stored in a database to translate the identified segment from a first language to a second language;   producing a representation for each set of sentences of the received clinical trial document that share a common meaning by applying at least one transformational technique to each of the identified segments of the received clinical trial document; and   providing an output of the clinical trial document in the second language by reconstructing the clinical trial document from the translated identified segments and the representations for each set of sentences that share a common meaning.   
     
     
         2 . The method of  claim 1 , further comprising:
 applying the at least one transformational technique to one or more of the identified segments of the clinical trial document by using sentence splitting to identify tokens that determine key sentence structures.   
     
     
         3 . The method of  claim 1 , further comprising:
 applying the at least one transformational technique to one or more of the identified segments of the clinical trial document by re-arranging a set of words within the clinical trial document to enable the set of words to share a common meaning.   
     
     
         4 . The method of  claim 1 , wherein one or more of the identified segments of the clinical trial document share a common meaning in the second language. 
     
     
         5 . The method of  claim 1 , wherein the database comprises a plurality of translated clinical trial documents translated from the first language to the second language. 
     
     
         6 . The method of  claim 1 , further comprising:
 matching one or more of the identified segments of the received clinical trial document to one or more sources of additional information within the database.   
     
     
         7 . The method of  claim 1 , wherein the step of matching the identified segment to the portion of the translated clinical trial document comprises applying a plurality of matching patterns to the identified segment of the clinical trial document. 
     
     
         8 . A computer program product comprising a non-transitory storage medium having processor-readable instructions stored thereon that, when executed by one or more processors, cause the computer program product to:
 identify a plurality of segments in a received clinical trial document;   for each of the identified segments, match the identified segment to a portion of a translated clinical trial document stored in a database to translate the identified segment from a first language to a second language;   produce a representation for each set of sentences of the received clinical trial document that share a common meaning by applying at least one transformational technique to each of the identified segments of the received clinical trial document; and   provide an output of the clinical trial document in the second language by reconstructing the clinical trial document from the translated identified segments and the representations for each set of sentences that share a common meaning.   
     
     
         9 . The computer program product of  claim 8 , wherein the at least one transformational technique is applied to one or more of the identified segments of the clinical trial document by using sentence splitting to identify tokens that determine key sentence structures. 
     
     
         10 . The computer program product of  claim 8 , wherein the at least one transformational technique is applied to one or more of the identified segments of the clinical trial document by re-arranging a set of words within the clinical trial document to enable the set of words to share a common meaning. 
     
     
         11 . The computer program product of  claim 8 , wherein one or more of the identified segments share a common meaning in the second language. 
     
     
         12 . The computer program product of  claim 8 , wherein the database comprises a plurality of translated clinical trial documents translated from the first language to the second language. 
     
     
         13 . The computer program product of  claim 8 , wherein one or more of the identified segments of the received clinical trial document are matched to one or more sources of additional information within the database. 
     
     
         14 . The computer program product of  claim 8 , wherein the step of matching the identified segment to the portion of the translated clinical trial document comprises applying a plurality of matching patterns to the identified segment of the clinical trial document. 
     
     
         15 . A computer system connected to a network, the system comprising:
 a memory configured to store instructions;   one or more processors configured to execute the instructions and configured to:   identify a plurality of segments in a received clinical trial document;   for each of the identified segments, match the identified segment to a portion of a translated clinical trial document stored in a database to translate the identified segment from a first language to a second language;   produce a representation for each set of sentences of the received clinical trial document that share a common meaning by applying at least one transformational technique to each of the identified segments of the received clinical trial document; and   provide an output of the clinical trial document in the second language by reconstructing the clinical trial document from the translated identified segments and the representations for each set of sentences that share a common meaning.   
     
     
         16 . The system of  claim 15 , wherein the at least one transformational technique is applied to one or more of the identified segments of the clinical trial document by using sentence splitting to identify tokens that determine key sentence structures. 
     
     
         17 . The system of  claim 15 , wherein the at least one transformational technique is applied to one or more of the identified segments of the clinical trial document by re-arranging a set of words within the clinical trial document to enable the set of words to share a common meaning. 
     
     
         18 . The system of  claim 15 , wherein one or more of the identified segments of the clinical trial document share a common meaning in the second language. 
     
     
         19 . The system of  claim 15 , wherein the database comprises a plurality of translated clinical trial documents translated from the first language to the second language. 
     
     
         20 . The system of  claim 15 , wherein one or more of the identified segments are matched to one or more sources of additional information within the database.