Real-time assessment of text consistency

1. A method of generating text change suggestions, comprising:

receiving a document comprising portions, wherein each of the portions includes at least two words;

generating portion scores corresponding to the portions;

generating a global assessment score for the document;

determining, for the portion scores, variations from the global assessment score;

determining that the variations include at least two variations below a threshold variation and a variation above the threshold variation;

selecting consistent portions from the portions based on the variations, wherein the consistent portions correspond to portion scores with variations from the at least two variations below the threshold variation;

generating a language model for the document based on the consistent portions;

selecting an inconsistent portion from the portions based on the variations, wherein the inconsistent portion corresponds to a portion score with the variation above the threshold variation; and

generating, based on the language model, at least one text change suggestion for the inconsistent portion.

2. The method of claim 1 , wherein the global assessment score and the portion scores are based on semantic artifacts.

3. The method of claim 2 , wherein the semantic artifacts include at least one semantic artifact selected from the group consisting of bias-based semantic artifacts, correctness-based semantic artifacts, and coherence-based semantic artifacts.

4. The method of claim 1 , wherein the global assessment score and the portion scores are based on semantic artifacts and contributor scores.

5. The method of claim 1 , wherein the at least one text change suggestion is generated using style-based transformers.

6. The method of claim 1 , further comprising:

identifying at least one leader from at least two contributors to the document; and

generating the global assessment score based on portion scores for portions of the document contributed by the at least one leader.

7. The method of claim 1 , wherein the at least one text change suggestion indicates that the inconsistent portion contains information that contradicts information in the consistent portions.

8. A system, comprising:

at least one processing component;

at least one memory component;

a display screen configured to display a document;

a dictionary; and

an editing module, comprising:

an assessment module configured to:

receive a document comprising portions, wherein each of the portions includes at least two words;

generate portion scores corresponding to the portions;

generate a global assessment score for the document;

determine, for the portion scores, variations from the global assessment score;

determine that the variations include at least two variations below a threshold variation and a variation above the threshold variation;

select consistent portions from the portions based on the variations, wherein the consistent portions correspond to portion scores with variations from the at least two variations below the threshold variation; and

select an inconsistent portion from the portions based on the variations, wherein the inconsistent portion corresponds to a portion score with the variation above the threshold variation; and

a suggestion module configured to:

generate a language model for the document based on the consistent portions; and

generate, based on the language model, at least one text change suggestion for the inconsistent portion.

9. The system of claim 8 , wherein the global assessment scores and the portion scores are based on semantic artifacts.

10. The system of claim 9 , wherein the semantic artifacts include at least one semantic artifact selected from the group consisting of bias-based semantic artifacts, correctness-based semantic artifacts, and coherence-based semantic artifacts.

11. The system of claim 8 , global assessment score and the portion scores are based on semantic artifacts and contributor scores.

12. The system of claim 8 , wherein the assessment module is further configured to:

identify at least one leader from at least two contributors to the document; and

generate the global assessment score based on portion scores for portions of the document contributed by the at least one leader.

13. The system of claim 8 , wherein the at least one text change suggestion indicates that the inconsistent portion contains information that contradicts information in the consistent portions.

14. The system of claim 8 , further comprising a set of contributor profiles.

15. A computer program product for generating text change suggestions, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the device to perform a method, the method comprising:

receiving a document comprising portions, wherein each of the portions includes at least two words;

generating portion scores corresponding to the portions;

generating a global assessment score for the document;

determining, for the portion scores, variations from the global assessment score;

determining that the variations include at least two variations below a threshold variation and a variation above the threshold variation;

selecting consistent portions from the portions based on the variations, wherein the consistent portions correspond to portion scores with variations from the at least two variations below the threshold variation;

generating a language model for the document based on the consistent portions;

selecting an inconsistent portion from the portions based on the variations, wherein the inconsistent portion corresponds to a portion score with the variation above the threshold variation; and

generating, based on the language model, at least one text change suggestion for the inconsistent portion.

16. The computer program product of claim 15 , wherein the global assessment score and the portion scores are based on semantic artifacts.

17. The computer program product of claim 16 , wherein the semantic artifacts include at least one semantic artifact selected from the group consisting of bias-based semantic artifacts, correctness-based semantic artifacts, and coherence-based semantic artifacts.

18. The computer program product of claim 15 , wherein the global assessment score and the portion scores are based on semantic artifacts and contributor scores.

19. The computer program product of claim 15 , wherein the at least one text change suggestion is generated using style-based transformers.

20. The computer program product of claim 15 , further comprising:

identifying at least one leader from at least two contributors to the document; and

generating the global assessment score based on portion scores for portions of the document contributed by the at least one leader.