Summary generation method and summary generation apparatus

A non-transitory computer-readable recording medium having stored therein a program that, when executed by a processor, causes the processor to be configured to:

• obtain input text;
• generate an initial lattice including a plurality of serially coupled nodes corresponding to words within the input text;
• generate a node of a section corresponding to a predetermined expression within the initial lattice;
• add the generated node to the initial lattice to provide an extended lattice corresponding to the input text;
• calculate a generation probability of each word within the input test using a dictionary and a machine learning model;
• calculate a generation probability for each node included in the extended lattice based on a hidden state output by a cell corresponding to the node among cells in an encoder of the machine learning model and a hidden state updated by a cell in a decoder of the machine learning model;
• and
• generate an element of a summary of the input text based on the generation probability of each word and the generation probability of each node of the extended lattice,
• wherein, when there is a named entity within the input text, the processor generates a node corresponding to the named entity, and adds the node corresponding to the named entity to the initial lattice to extend the initial lattice into the extended lattice.

A summary generation apparatus comprising:

• a memory;
• and
• a processor coupled to the memory and the processor configured to:
• obtain input text;
• generate an initial lattice including a plurality of serially coupled nodes corresponding to words within the input text;
• generate a node of a section corresponding to a predetermined expression within the initial lattice;
• add the generated node to the initial lattice to provide an extended lattice corresponding to the input text;
• calculate a generation probability of each word within the input test using a dictionary and a machine learning model;
• calculate a generation probability for each node included in the extended lattice based on a hidden state output by a cell corresponding to the node among cells in an encoder of the machine learning model and a hidden state updated by a cell in a decoder of the machine learning model;
• and
• generate an element of a summary of the input text based on the generation probability of each word and the generation probability of each node of the extended lattice,
• wherein, when there is a named entity within the input text, the processor generates a node corresponding to the named entity, and adds the node corresponding to the named entity to the initial lattice to extend the initial lattice into the extended lattice.