Structured text processing learning apparatus, structured text processing apparatus, structured text processing learning method, structured text processing method and program
View Patent ↗A structured text processing learning apparatus includes a memory, and a processor configured to: analyze a structure of structured text, extract, from the structured text, information related to a predetermined structure to be extracted based on the structure, generate a converted document including text data in which each string indicating a structure of the extracted information has been converted, in accordance with the structure related to the extracted information, and train a neural network for executing predetermined processing for the converted document, using, as input, the generated converted document and correct answer information for performing the predetermined processing. Thus, application of a neural network to structured text is facilitated.
1. A structured text processing learning apparatus comprising:
a memory, and
a processor configured to:
extract, from the structured text, context strings that contribute to a hierarchical structure among a plurality of meta strings representing the hierarchical structure of the structured text and context strings delimited by the meta strings,
combine the extracted context strings,
generate a converted document from a result of combining the extracted context strings by converting the plurality of meta strings included in the result into a common string, and
train a neural network for executing predetermined processing for the converted document, using, as input, the generated converted document and correct answer information for performing the predetermined processing.
2. The structured text processing learning apparatus according to claim 1 ,
wherein the processor is further configured to convert each string that is included in the information related to the structure and indicate the structure to a common string representing that the string has been present.
3. The structured text processing learning apparatus according to claim 1 ,
wherein the processor is further configured to perform multi-task learning of information retrieval and machine reading comprehension for the neural network.
4. A structured text processing apparatus comprising:
a memory, and
a processor configured to:
cause the neural network trained by the structured text processing learning apparatus according to claim 1 to execute the predetermined processing related to structured text.
5. A non-transitory computer-readable recording medium having stored therein a program causing a computer to function as the structured text processing apparatus according to claim 4 .
6. A computer-implemented structured text processing method comprising:
causing the neural network trained by the structured text processing learning apparatus according to claim 1 to execute the predetermined processing related to structured text.
7. A non-transitory computer-readable recording medium having stored therein a program causing a computer to function as the structured text processing learning apparatus according to claim 1 .
8. A computer-implemented structured text processing learning method comprising:
extracting, from the structured text, context strings that contribute to a hierarchical structure among a plurality of meta strings representing the hierarchical structure of the structured text and context strings delimited by the meta strings,
combine the extracted context strings;
generating a converted document from a result of combining the extracted context strings by converting the plurality of meta strings included in the result into a common string including text data in which each string indicating a structure of the extracted information has been converted, in accordance with the structure related to the extracted information; and
training a neural network for executing predetermined processing for the converted document, using, as input, the converted document generated in the conversion step and correct answer information for performing the predetermined processing.