Machine learning techniques for determining predicted similarity scores for input sequences

1. A computer-implemented method comprising:

generating, by one or more processors, a token-level similarity probability score for a pair of input sequences based at least in part on a first cross-token image representation for a first input sequence of the pair of input sequences and a second cross-token image representation for a second input sequence of the pair of input sequences, wherein the token-level similarity probability score is based at least in part on a comparison between a first dimensionally-reduced image representation for the first cross-token image representation and a second dimensionally-reduced image representation for the second cross-token image representation;

generating, by the one or more processors and a machine learning model, a predicted similarity score for the pair of input sequences based at least in part on the token-level similarity probability score; and

initiating, by the one or more processors, the performance of one or more prediction-based actions based at least in part on the predicted similarity score.

2. The computer-implemented method of claim 1 , wherein the first cross-token image representation comprises a two-dimensional representation of a plurality of token-level embedded representations for the first input sequence and each token-level embedded representation for a particular token of the first input sequence is determined based at least in part on a Word2Vec representation of the particular token.

3. The computer-implemented method of claim 1 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a target region match indication for the pair of input sequences; and

generating the predicted similarity score based at least in part on the target region match indication and the token-level similarity probability score.

4. The computer-implemented method of claim 1 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a fuzzy match score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the fuzzy match score and the token-level similarity probability score.

5. The computer-implemented method of claim 1 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a character-level match score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the character-level match score and the token-level similarity probability score.

6. The computer-implemented method of claim 1 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a harmonic mean score of a fuzzy match score for the pair of input sequences and the token-level similarity probability score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the harmonic mean score and the token-level similarity probability score.

7. The computer-implemented method of claim 1 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining one or more similarity ratio occurrence indicators for the pair of input sequences; and

generating the predicted similarity score based at least in part on the one or more similarity ratio occurrence indicators and the token-level similarity probability score.

8. The computer-implemented method of claim 1 , wherein the first cross-token image representation is based at least in part on a padded input sequence for the first input sequence, and

the padded input sequence is generated based at least in part on a token count threshold.

9. A computing system for dynamically generating a predicted similarity score for a pair of input sequences, the computing system comprising one or more processors and memory including program code, the memory and the program code configured to, with the one or more processors, cause the computing system to at least:

generate a token-level similarity probability score for a pair of input sequences based at least in part on a first cross-token image representation for a first input sequence of the pair of input sequences and a second cross-token image representation for a second input sequence of the pair of input sequences, wherein the token-level similarity probability score is based at least in part on a comparison between a first dimensionally-reduced image representation for the first cross-token image representation and a second dimensionally-reduced image representation for the second cross-token image representation;

generate, using a machine learning model, a predicted similarity score for the pair of input sequences based at least in part on the token-level similarity probability score; and

initiate the performance of one or more prediction-based actions based at least in part on the predicted similarity score.

10. The computing system of claim 9 , wherein the first cross-token image representation comprises a two-dimensional representation of a plurality of token-level embedded representations for the first input sequence and each token-level embedded representation for a particular token of the first input sequence is determined based at least in part on a Word2Vec representation of the particular token.

11. The computing system of claim 9 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a target region match indication for the pair of input sequences; and

generating the predicted similarity score based at least in part on the target region match indication and the token-level similarity probability score.

12. The computing system of claim 9 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a fuzzy match score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the fuzzy match score and the token-level similarity probability score.

13. The computing system of claim 9 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a character-level match score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the character-level match score and the token-level similarity probability score.

14. The computing system of claim 9 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining a harmonic mean score of a fuzzy match score for the pair of input sequences and the token-level similarity probability score for the pair of input sequences; and

generating the predicted similarity score based at least in part on the harmonic mean score and the token-level similarity probability score.

15. The computing system of claim 9 , wherein generating the predicted similarity score for the pair of input sequences comprises:

determining one or more similarity ratio occurrence indicators for the pair of input sequences; and

generating the predicted similarity score based at least in part on the one or more similarity ratio occurrence indicators and the token-level similarity probability score.

16. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to:

generate a token-level similarity probability score for a pair of input sequences based at least in part on a first cross-token image representation for a first input sequence of the pair of input sequences and a second cross-token image representation for a second input sequence of the pair of input sequences, wherein the token-level similarity probability score is based at least in part on a comparison between a first dimensionally-reduced image representation for the first cross-token image representation and a second dimensionally-reduced image representation for the second cross-token image representation;

generate, using a machine learning model, a predicted similarity score for the pair of input sequences based at least in part on the token-level similarity probability score; and

initiate the performance of one or more prediction-based actions based at least in part on the predicted similarity score.