Method and system for attribute extraction from product titles using sequence labeling algorithms

1. A system comprising:

one or more computer processing modules; and

one or more non-transitory storage modules storing computing instructions configured to run on the one or more computer processing modules and perform acts of:

receiving, at the one or more computer processing modules and from a third-party electronic device, a title for a product;

dividing, at the one or more computer processing modules, the title into a sequence of tokens;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the sequence of tokens;

determining, at the one or more computer processing modules and using a sequence labeling model, a type of each token of the sequence of tokens;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the type of each token of the sequence of tokens;

encoding, at the one or more computer processing modules, each token of the sequence of tokens to indicate the type of each token of the sequence of tokens, wherein the type of each token of the sequence of tokens comprises a BIO encoding scheme, wherein:

a label B of the BIO encoding scheme indicates a first token of a brand name;

a label I of the BIO encoding scheme indicates a subsequent token of the brand name; and

a label O of the BIO encoding scheme indicates a token that is not part of the brand name;

determining, at the one or more computer processing modules, the brand name present in the title using each token of the sequence of tokens, as encoded;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the brand name present in the title;

normalizing, at the one or more computer processing modules, the brand name present in the title to create a standardized representation of the brand name;

writing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the standardized representation of the brand name present in the title to an empty database entry associated with the product; and

in response to a search request from a user, transmitting instructions to a user display to display a representation of the standardized representation of the brand name for each token of the sequence of tokens.

2. The system of claim 1 , wherein the sequence labeling model comprises at least one of:

a conditional random fields (CRF) algorithm;

a structured perception algorithm; or

a bidirectional long short term memory (LSTM) model.

3. The system of claim 2 , wherein the sequence labeling model comprises the CRF algorithm and the bidirectional LSTM model.

4. The system of claim 3 , wherein the bidirectional LSTM model is performed before the CRF algorithm.

5. The system of claim 1 , wherein the sequence labeling model comprises a bidirectional long short term memory (LSTM) model, which solves an attribute extraction function of:

E seq ( x t )= E seq (( x 1 , x 2 , . . . , x n ))=( x i , x i+1 , . . . , x k ) for 1≤ i≤k≤n, wherein:

E seq comprises the attribute extraction function; and

x t is a tokenization of the product title x.

6. The system of claim 5 , wherein at least one of (x 1 , x 2 , . . . , x n ) comprises a token having the label B of the BIO encoding scheme.

7. The system of claim 1 , wherein the sequence labeling model comprises a bidirectional long short term memory (LSTM) model comprising:

i t =σ( W xi x t +W hi h t−1 +W ci c t−1 +b i )

f t =σ( W xi x t +W hi h t−1 +W ci c t−1 +b i )

c t =f t ⊙c t−1 +i t ⊙tan h ( W xc x t +W hc h t−1 +b c )

o t =σ( W xo x t +W ho h t−1 +W co c t−1 +b c )

h t =o t ⊙tan h ( c t ), wherein:

σ comprises a logistic function;

⊙ comprises an element-wise product;

i comprises an input gate;

f comprises a forget gate;

c comprises a cell;

o comprises an output gate;

h comprises a hidden vector;

W comprises a weight matrix;

x comprises a product title;

b comprises a model coefficient; and

t comprises a time.

8. A method being implemented via execution of computing instructions configured to run at one or more computer processing modules and configured to be stored at one or more non-transitory storage modules, the method comprising:

receiving, at the one or more computer processing modules and from a third-party electronic device, a title for a product;

dividing, at the one or more computer processing modules, the title into a sequence of tokens;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the sequence of tokens;

determining, at the one or more computer processing modules and using a sequence labeling model, a type of each token of the sequence of tokens;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the type of each token of the sequence of tokens;

encoding, at the one or more computer processing modules, each token of the sequence of tokens to indicate the type of each token of the sequence of tokens, wherein the type of each token of the sequence of tokens comprises a BIO encoding scheme, wherein:

a label B of the BIO encoding scheme indicates a first token of a brand name;

a label I of the BIO encoding scheme indicates a subsequent token of the brand name; and

a label O of the BIO encoding scheme indicates a token that is not part of the brand name;

determining, at the one or more computer processing modules, the brand name present in the title using each token of the sequence of tokens, as encoded;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the brand name present in the title;

normalizing, at the one or more computer processing modules, the brand name present in the title to create a standardized representation of the brand name;

writing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the standardized representation of the brand name present in the title to an empty database entry associated with the product; and

in response to a search request from a user, transmitting instructions to a user display to display a representation of the standardized representation of the brand name for each token of the sequence of tokens.

9. The method of claim 8 , wherein the sequence labeling model comprises at least one of:

a conditional random fields (CRF) algorithm;

a structured perception algorithm; or

a bidirectional long short term memory (LSTM) model.

10. The method of claim 9 , wherein the sequence labeling model comprises the CRF algorithm and the bidirectional LSTM model.

11. The method of claim 10 , wherein the bidirectional LSTM model is performed before the CRF algorithm.

12. The method of claim 11 , wherein the sequence labeling model comprises a bidirectional long short term memory (LSTM) model, which solves an attribute extraction function of:

E seq ( x t )= E seq (( x 1 , x 2 , . . . , x n ))=( x i , x i+1 , . . . , x k ) for 1≤ i≤k≤n, wherein:

E seq comprises the attribute extraction function; and

x t is a tokenization of the product title x.

13. The method of claim 12 , wherein at least one of (x 1 , x 2 , . . . , x n ) comprises a token having the label B of the BIO encoding scheme.

14. The method of claim 8 , wherein the sequence labeling model comprises a bidirectional long short term memory (LSTM) model comprising:

i t =σ( W xi x t +W hi h t−1 +W ci c t−1 +b i )

f t =σ( W xi x t +W hi h t−1 +W ci c t−1 +b i )

c t =f t ⊙c t−1 +i t ⊙tan h ( W xc x t +W hc h t−1 +b c )

o t =σ( W xo x t +W ho h t−1 +W co c t−1 +b c )

h t =o t ⊙tan h ( c t ), wherein:

σ comprises a logistic function;

⊙ comprises an element-wise product;

i comprises an input gate;

f comprises a forget gate;

c comprises a cell;

o comprises an output gate;

h comprises a hidden vector;

W comprises a weight matrix;

x comprises a product title;

b comprises a model coefficient; and

t comprises a time.

15. A non-transitory computer-readable medium storing computing instructions configured to be executed by one or more processors, and, when executed, cause the one or more processors to perform acts of:

receiving, at one or more computer processing modules and from a third-party electronic device, a title for a product;

dividing, at the one or more computer processing modules, the title into a sequence of tokens;

storing, by the one or more computer processing modules onto one or more non-transitory storage modules, the sequence of tokens;

determining, at the one or more computer processing modules and using a sequence labeling model, a type of each token of the sequence of tokens;

storing, by the one or more computer processing modules onto one or more non-transitory storage modules, the type of each token of the sequence of tokens;

encoding, at the one or more computer processing modules, each token of the sequence of tokens to indicate the type of each token of the sequence of tokens, wherein the type of each token of the sequence of tokens comprises a BIO encoding scheme, wherein:

a label B of the BIO encoding scheme indicates a first token of a brand name;

a label I of the BIO encoding scheme indicates a subsequent token of the brand name; and

a label O of the BIO encoding scheme indicates a token that is not part of the brand name;

determining, at the one or more computer processing modules, the brand name present in the title using each token of the sequence of tokens, as encoded;

storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the brand name present in the title;

normalizing, at the one or more computer processing modules, the brand name present in the title to create a standardized representation of the brand name;

writing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the standardized representation of the brand name present in the title to an empty database entry associated with the product; and

in response to a search request from a user, transmitting instructions to a user display to display a representation of the standardized representation of the brand name for each token of the sequence of tokens.

16. The computer-readable medium of claim 15 , wherein the sequence labeling model comprises at least one of:

a conditional random fields (CRF) algorithm;

a structured perception algorithm; or

a bidirectional long short term memory (LSTM) model.

17. The computer-readable medium of claim 16 , wherein the sequence labeling model comprises the CRF algorithm and the bidirectional LSTM model.

18. The computer-readable medium of claim 17 , wherein the bidirectional LSTM model is performed before the CRF algorithm.

19. The computer-readable medium of claim 15 , wherein the sequence labeling model comprises a bidirectional long short term memory (LSTM) model, which solves an attribute extraction function of:

E seq ( x t )= E seq (( x 1 , x 2 , . . . , x n ))=( x i , x i+1 , . . . , x k ) for 1≤ i≤k≤n, wherein:

E seq comprises the attribute extraction function; and

x t is a tokenization of the product title x.

20. The method of claim 12 , wherein at least one of (x 1 , x 2 , . . . , x n ) comprises a token having the label B of the BIO encoding scheme.