Method and apparatus for constructing binary feature dictionary

1. A method for constructing a binary feature dictionary, comprising:

extracting binary features from a corpus;

calculating a preset statistic of each of the binary features; and

selecting a preset number of the binary features in sequence according to the preset statistic to constitute the binary feature dictionary;

extracting the selected binary features included in the binary feature dictionary from word segments of a semantic similarity model as training data of the semantic similarity model; and

performing a neural network training according to the training data to generate the semantic similarity model.

2. The method according to claim 1 , wherein extracting the binary features from the corpus comprises:

determining two adjacent terms in the corpus as a binary feature.

3. The method according to claim 1 , wherein the preset statistic is T-statistic.

4. An apparatus for constructing a binary feature dictionary, comprising:

one or more processors;

a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:

extract binary features from a corpus;

calculate a preset statistic of each of the binary features;

select a preset number of the binary features in sequence according to the preset statistic to constitute the binary feature dictionary;

extract the selected binary features included in the binary feature dictionary from word segments of a semantic similarity model as training data of the semantic similarity model; and

perform a neural network training according to the training data to generate the semantic similarity model.

5. The apparatus according to claim 4 , wherein the one or more processors extract binary features from the corpus by performing act of:

determining two adjacent terms in the corpus as a binary feature.

6. The apparatus according to claim 4 , wherein the preset statistic calculated by the one or more processors is T-statistic.

7. A non-transitory computer readable storage medium, wherein when instructions in the storage medium are executed by a processor of a terminal, the terminal is caused to perform a method, the method comprises:

extracting binary features from a corpus;

calculating a preset statistic of each of the binary features;

selecting a preset number of the binary features in sequence according to the preset statistic to constitute a binary feature dictionary;

extracting the selected binary features included in the binary feature dictionary from word segments of a semantic similarity model as training data of the semantic similarity model; and

performing a neural network training according to the training data to generate the semantic similarity model.

8. The method according to claim 2 , wherein the preset statistic is T-statistic.

9. The apparatus according to claim 5 , wherein the preset statistic calculated by the one or more processors is T-statistic.