Method and system for suggesting revisions to an electronic document
A method for suggesting revisions to a document-under-analysis from a seed database, the seed database including a plurality of original texts each respectively associated with one of a plurality of final texts, the method for suggesting revisions including selecting a statement-under-analysis (“SUA”), selecting a first original text of the plurality of original texts, determining a first edit-type classification of the first original text with respect to its associated final text, generating a first similarity score for the first original text based on the first edit-type classification, the first similarity score representing a degree of similarity between the SUA and the first original text, selecting a second original text of the plurality of original texts, determining a second edit-type classification of the second original text with respect to its associated final text, generating a second similarity score for the second original text based on the second edit-type classification, the second similarity score representing a degree of similarity between the SUA and the second original text, selecting a candidate original text from one of the first original text and the second original text, and creating an edited SUA (“ESUA”) by modifying a copy of the first SUA consistent with a first candidate final text associated with the first candidate original text.
1. A method for suggesting revisions to text data, the method comprising:
obtaining a text-under-analysis (“TUA”);
obtaining an original text from a plurality of original texts;
identifying an edit operation of the original text with respect to a final text associated with the original text, the edit operation having an edit-type classification;
selecting a similarity scoring metric from a plurality of similarity scoring metrics based on the edit-type classification;
generating a similarity score for the original text using the selected similarity scoring metric, the similarity score representing a degree of similarity between the TUA and the original text; and
creating an edited TUA (“ETUA”) by modifying the TUA consistent with the final text associated with the original text.
2. The method of claim 1 , further comprising:
obtaining a second original text from the plurality of original texts;
identifying a second edit operation of the second original text with respect to a second final text associated with the second original text, the second edit operation having a second edit-type classification different than the first edit-type classification;
selecting a second similarity scoring metric from the plurality of similarity scoring metrics based on the second edit-type classification, wherein the second similarity scoring metric is different than the first similarity scoring metric; and
generating a second similarity score for the second original text using the selected second similarity scoring metric, the second similarity score representing a degree of similarity between the TUA and the second original text.
3. The method of claim 2 , further comprising:
selecting the first original text from at least the first original text and the second original text.
4. The method of claim 3 , further comprising:
determining that the first similarity score is higher than the second similarity score, and wherein the selecting the first original text is based on the determining.
5. The method of claim 3 , further comprising:
determining that the first similarity score exceeds a threshold, and wherein the selecting the first original text is based on the determining.
6. The method of claim 1 , wherein the plurality of similarity scoring metrics comprise two or more of: cosine distance, edit distance, word count, and word embeddings.
7. The method of claim 1 , wherein the edit-type classification comprises a point edit and the selected similarity scoring metric comprises a cosine distance.
8. The method of claim 1 , wherein the edit-type classification comprises a span edit and the selected similarity scoring metric comprises an edit distance.
9. The method of claim 1 , wherein the creating the ETUA comprises:
selecting an alignment method from a plurality of alignment methods based on the edit-type classification of the edit operation;
identifying a second edit operation based on the selected alignment method; and
creating the ETUA by applying to the TUA the second edit operation.
10. The method of claim 1 , further comprising:
obtaining an input indicating one of an accept, rejection, or revision of the ETUA.
11. A non-transitory computer readable medium storing instructions configured to cause a computer to perform the method of claim 1 .
12. A system for suggesting revisions to text data, the system comprising:
a processor;
a non-transitory computer readable memory coupled to the processor, wherein the processor is configured to:
obtain a text-under-analysis (“TUA”);
obtain an original text from a plurality of original texts;
identify an edit operation of the original text with respect to a final text associated with the original text, the edit operation having an edit-type classification;
select a similarity scoring metric from a plurality of similarity scoring metrics based on the edit-type classification;
generate a similarity score for the original text using the selected similarity scoring metric, the similarity score representing a degree of similarity between the TUA and the original text; and
create an edited TUA (“ETUA”) by modifying the TUA consistent with the final text associated with the original text.
13. The system of claim 12 , wherein the processor is further configured to:
obtain a second original text from the plurality of original texts;
identify a second edit operation of the second original text with respect to a second final text associated with the second original text, the second edit operation having a second edit-type classification different than the first edit-type classification;
select a second similarity scoring metric from the plurality of similarity scoring metrics based on the second edit-type classification, wherein the second similarity scoring metric is different than the first similarity scoring metric; and
generate a second similarity score for the second original text using the selected second similarity scoring metric, the second similarity score representing a degree of similarity between the TUA and the second original text.
14. The system of claim 13 , wherein the processor is further configured to:
select the first original text from at least the first original text and the second original text.
15. The system of claim 13 , wherein the processor is further configured to:
determine that the first similarity score is higher than the second similarity score, and wherein the select the first original text is based on the determination.
16. The system of claim 13 , wherein the processor is further configured to:
determine that the first similarity score exceeds a threshold, and wherein the select the first original text is based on the determination.
17. The system of claim 12 , wherein the plurality of similarity scoring metrics comprise two or more of: cosine distance, edit distance, word count, and word embeddings.
18. The system of claim 12 , wherein the edit-type classification comprises a point edit and the selected similarity scoring metric comprises a cosine distance.
19. The system of claim 12 , wherein the edit-type classification comprises a span edit and the selected similarity scoring metric comprises an edit distance.
20. The system of claim 12 , wherein the processor is further configured to:
select an alignment method from a plurality of alignment methods based on the edit-type classification of the edit operation;
identify a second edit operation based on the selected alignment method; and
create the ETUA by applying to the TUA the second edit operation.