Embedding an unknown word in an input sequence
An information learning apparatus includes a memory and a processor configured to perform generating, for each of processing units constituting an input sequence included in training data, a third embedded vector based on a first embedded vector for the processing unit and a second embedded vector corresponding to an unknown word; executing a process based on a learning target parameter, with the third embedded vector generated for each of the processing units as an input; and learning, for a processing result by the executing, the parameter based on an error of an output corresponding to the input sequence in the training data.
1 . An information learning apparatus comprising:
a memory and a processor configured to:
generate, for each of processing units constituting an input sequence included in training data, a third embedded vector by adding a second embedded vector corresponding to an unknown word to a first embedded vector of each processing unit regardless of whether said each processing unit represents the unknown word or not;
execute, using training data, a process based on a learning target parameter of a sequence-to-sequence model to generate an inference result, with the third embedded vector generated for said each processing unit as an input; and
learn the learning target parameter of the sequence-to-sequence model, wherein the learning target parameter is based on an error between the inference result of the execution and a ground truth output corresponding to the input sequence in the training data, wherein a learnt neural network with the learnt learning target parameter converts an input statement into one or more output words, and the input statement comprises the unknown word.
2 . A non-transitory computer-readable recording medium having computer-readable instructions stored thereon, which when executed, cause a computer including a memory and a processor to execute respective operations in the information processing apparatus according to claim 1 .
3 . An information processing apparatus comprising:
a memory and a processor configured to perform
generating, for each of processing units constituting an input sequence, a third embedded vector by adding a second embedded vector corresponding to an unknown word to a first embedded vector for each processing unit regardless of whether said each processing unit represents the unknown word or not; and
executing, using training data, a process based on a learned parameter of a sequence-to-sequence model to generate an inference result, with the third embedded vector generated for said each processing unit as an input, wherein the learned parameter is based on an error between the inference result of a previous execution of the process and a ground truth output corresponding to the input sequence in training data, a learnt neural network with the learnt learning target parameter converts an input statement into one or more output words as the inference result, and the input statement comprises the unknown word.
4 . A non-transitory computer-readable recording medium having computer-readable instructions stored thereon, when executed, cause a computer including a memory and a processor to execute respective operations in the information processing apparatus according to claim 3 .
5 . An information learning method executed by a computer including a memory and a processor the method comprising:
generating, for each of processing units constituting an input sequence included in training data, a third embedded vector by adding a second embedded vector corresponding to an unknown word to a first embedded vector of each processing unit regardless of whether said each processing unit represents the unknown word or not;
executing, using training data, a process based on a learning target parameter of a sequence-to-sequence model to generate an inference result, with the third embedded vector generated for said each processing unit as an input; and
learning the learning target parameter of the sequence-to-sequence model, wherein the learning target parameter is based on an error between the inference result of the execution and a ground truth output corresponding to the input sequence in the training data, wherein a learnt neural network with the learnt learning target parameter converts an input statement into one or more output words, and the input statement comprises the unknown word.