Method, apparatus, and computer program product for classification and tagging of textual data
Provided herein are systems, methods and computer readable media for classification and tagging of textual data. An example method may include accessing a corpus comprising a plurality of documents, each document having one or more labels indicative of services offered by a merchant, generating a query based on extracted features and the documents, generating a precision score for at least a portion of the generated query and selecting a subset of the generated queries based on an assigned precision score satisfying a precision score threshold, the selected subset of the generated queries configured to provide an indication of one or more labels to be applied to machine readable text. A second example method, utilized for tagging machine readable text with unknown labels, may include assigning a label to textual portions of the machine readable text based on results of the application of the queries.
1. A method for identifying one or more services based on machine readable text comprising:
accessing a corpus comprising a plurality of documents, each of one or more documents of the corpus having one or more labels indicative of one or more services offered by a merchant;
generating, using a processor, at least one query based on one or more extracted features and the one or more documents;
generating a recall score for at least a portion of the generated at least one query, wherein the recall score is calculated based on a number of true positives returned by the query divided by a total number of elements that belong to a positive class; and
selecting a subset of the generated at least one query based on an assigned recall score satisfying a recall score threshold, wherein the selected subset of the generated at least one query are configured to provide an indication of one or more labels to be applied to machine readable text.
2. The method according to claim 1 , wherein generating the query further comprises:
generating an array of feature index pairs, the array of feature index pairs comprising one or more features and a position of the one or more features in a sentence;
generating the at least one query as a function of one or more combinations of feature index pairs based on the array; and
outputting the at least one query.
3. The method according to claim 1 , wherein generating the query further comprises:
calculating a distance between a first feature in a query and a second feature in the query; and
generating a distance measure for the query.
4. The method according to claim 1 , further comprising:
receiving the corpus;
causing a first subset of words to be ignored in the corpus, the subset of words comprising at least one of rare words or stop words;
scoring a second subset of words based on the relationship between a word of the second subset of keywords and a label; and
extracting features, the features comprising one or more words from the second subset of keywords that satisfy a predetermined threshold.
5. The method according to claim 1 , further comprising:
calculating a normalization factor based on the recall score.
6. The method according to claim 1 , further comprising:
accessing machine readable text;
applying the subset of the generated at least one query;
generating a score for the machine readable text, the score is a function of the recall score of a query of the subset of the generated at least one query divided by a normalization factor; and
generating at least one label for the machine readable text.
7. The method according to claim 6 , wherein the at least one label is a sub-dominant level in a hierarchical structure of service categories.
8. An apparatus for identifying one or more services based on machine readable text, the apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:
access a corpus comprising a plurality of documents, each of one or more documents of the corpus having one or more labels indicative of one or more services offered by a merchant;
generate, using the processor, at least one query based on one or more extracted features and the one or more documents;
generate a recall score for at least a portion of the generated at least one query, wherein the recall score is calculated based on a number of true positives returned by the query divided by a total number of elements that belong to a positive class; and
select a subset of the generated at least one query based on an assigned recall score satisfying a recall score threshold, wherein the selected subset of the generated at least one query are configured to provide an indication of one or more labels to be applied to machine readable text.
9. The apparatus according to claim 8 , wherein generating the query further comprises:
generating an array of feature index pairs, the array of feature index pairs comprising one or more features and a position of the one or more features in a sentence;
generating the at least one query as a function of one or more combinations of feature index pairs based on the array; and
outputting the at least one query.
10. The apparatus according to claim 8 , wherein generating the query further comprises:
calculating a distance between a first feature in a query and a second feature in the query; and
generating a distance measure for the query.
11. The apparatus according to claim 8 , wherein the at least one memory and the computer program code are further configured to, with the processor, cause the apparatus to:
receive the corpus;
cause a first subset of words to be ignored in the corpus, the subset of words comprising at least one of rare words or stop words;
score a second subset of words based on the relationship between a word of the second subset of keywords and a label; and
extract features, the features comprising one or more words from the second subset of keywords that satisfy a predetermined threshold.
12. The apparatus according to claim 8 , wherein the at least one memory and the computer program code are further configured to, with the processor, cause the apparatus to:
calculate a normalization factor based on the recall score.
13. The apparatus according to claim 8 , wherein the at least one memory and the computer program code are further configured to, with the processor, cause the apparatus to:
access machine readable text;
apply the subset of the generated at least one query;
generate a score for the machine readable text, the score is a function of the recall score of a query of the subset of the generated at least one query divided by a normalization factor; and
generate at least one label for the machine readable text.
14. The apparatus according to claim 13 , wherein the at least one label is a sub-dominant level in a hierarchical structure of service categories.
15. A computer program product for identifying one or more services based on machine readable text, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions for:
accessing a corpus comprising a plurality of documents, each of one or more documents of the corpus having one or more labels indicative of one or more services offered by a merchant;
generating, using a processor, at least one query based on one or more extracted features and the one or more documents;
generating a recall score for at least a portion of the generated at least one query, wherein the recall score is calculated based on a number of true positives returned by the query divided by a total number of elements that belong to a positive class; and
selecting a subset of the generated at least one query based on an assigned recall score satisfying a recall score threshold, wherein the selected subset of the generated at least one query are configured to provide an indication of one or more labels to be applied to machine readable text.
16. The computer program product according to claim 15 , wherein generating the query further comprises:
generating an array of feature index pairs, the array of feature index pairs comprising one or more features and a position of the one or more features in a sentence;
generating the at least one query as a function of one or more combinations of feature index pairs based on the array; and
outputting the at least one query.
17. The computer program product according to claim 15 , wherein generating the query further comprises:
calculating a distance between a first feature in a query and a second feature in the query; and
generating a distance measure for the query.
18. The computer program product according to claim 15 , wherein the computer-executable program code portions further comprise program code instructions for:
receiving the corpus;
causing a first subset of words to be ignored in the corpus, the subset of words comprising at least one of rare words or stop words;
scoring a second subset of words based on the relationship between a word of the second subset of keywords and a label; and
extracting features, the features comprising one or more words from the second subset of keywords that satisfy a predetermined threshold.
19. The computer program product according to claim 15 , wherein the computer-executable program code portions further comprise program code instructions for:
calculating a normalization factor based on the recall score.
20. The computer program product according to claim 15 , wherein the computer-executable program code portions further comprise program code instructions for:
accessing machine readable text;
applying the subset of the generated at least one query;
generating a score for the machine readable text, the score is a function of the recall score of a query of the subset of the generated at least one query divided by a normalization factor; and
generating at least one label for the machine readable text.
21. The computer program product according to claim 15 , wherein the at least one label is a sub-dominant level in a hierarchical structure of service categories.