AUTOMATICALLY APPLYING CORRECTION SUGGESTIONS IN TEXT CHECKING

1 . A computer-implemented method executed at a first computer and comprising:

receiving, at the first computer, a digital electronic object that includes a source text that has been composed at a second computer;

sending, to the second computer, instructions for presenting one or more filters via a user interface, the one or more filters being programmed to generate one or more first suggestions concerning the source text when the filters are selected and executed, each of the filters being configured to generate a different type of the one or more first suggestions, each of the one or more first suggestions including a change to a character, word, phrase, or sentence of the source text;

receiving, from the second computer, a first input specifying a selection of a first filter of the one or more filters;

in response to detecting the first input specifying the selection of the first filter, generating an output set of two or more second suggestions for different portions of the source text based on executing the first filter over the source text and an explanation for the two or more second suggestions, wherein generating the output set of two or more second suggestions includes:

identifying one or more first source text units of a first class corresponding to the first filter from a plurality of source text units associated with the source text; and

transforming the one or more first source text units to the output set of two or more second suggestions;

transmitting the output set of two or more second suggestions for the different portions of the source text and the explanation for the two or more second suggestions to the second computer; and

receiving, from the second computer, a second input specifying to apply the two or more second suggestions, and in response to the second input, automatically applying the two or more second suggestions to the different portions of the source text and transmitting, to the second computer, updated presentation instructions, execution of which by the second computer causes displaying of an updated text with the two or more second suggestions having been applied to the different portions of the source text.

2 . The computer-implemented method of claim 1 , each of the filters being programmed to execute a different type of spelling or grammar adjustment of the source text.

3 . The computer-implemented method of claim 1 , each of the filters being programmed to execute a different type of clarity adjustment of the source text.

4 . The computer-implemented method of claim 1 , each of the filters being programmed to execute a different type of tone adjustment of the source text.

5 . The computer-implemented method of claim 1 , each of the filters being programmed to execute a different type of transparency adjustment of the source text.

6 . The computer-implemented method of claim 1 , each of the filters being programmed to execute a different type of applause adjustment of the source text.

7 . The computer-implemented method of claim 1 , further comprising, before the transmitting, ranking the output set of two or more second suggestions based on a ranking criterion.

8 . The computer-implemented method of claim 1 , further comprising:

parsing the source text into a the plurality of source text units; and

evaluating each particular source text unit among the plurality of source text units using a trained machine-learning model, and receiving a classification output from the trained machine-learning model that classifies each particular source text unit into a particular class among a plurality of possible classes corresponding to the one or more filters.

9 . The computer-implemented method of claim 1 , further comprising generating the output set of suggestions by:

identifying the first class corresponding to the first filter from the one or more classes;

identifying one or more first source text units of the first class from the plurality of source text units; and

transforming the one or more first source text units to the output set of suggestions.

10 . The computer-implemented method of claim 1 , further comprising transforming the first source text units to the output set of two or more second suggestions by any one of:

mapping the one or more first source text units to a plurality of candidate text-unit suggestions in a digital database, to yield an initial set of matching text-unit suggestions, and filtering the initial set of matching text-unit suggestions to yield the output set of two or more second suggestions; or

mapping the one or more first source text units to a plurality of candidate text-unit suggestions in a digital database, to yield an initial set of matching text-unit suggestions, scoring the plurality of candidate text-unit suggestions, and selecting top N candidate text-unit suggestions to yield the output set of two or more second suggestions.

11 . One or more non-transitory computer-readable media storing one or more sequences of instructions, execution of which in a first computer causes the first computer to perform:

programmatically receiving a digital electronic object, the digital electronic object including a source text that has been composed at a second computer;

sending, to the second computer, instructions for presenting one or more filters via a user interface, the one or more filters being programmed to generate one or more first suggestions concerning the source text when the filters are selected and executed, each of the filters being programmed to generate a different type of the one or more first suggestions, each of the one or more first suggestions including a change to a character, word, phrase, or sentence of the source text;

receiving, from the second computer, a first input specifying a selection of a first filter of the one or more filters;

in response to detecting the first input specifying the selection of the first filter, generating an output set of two or more second suggestions for different portions of the source text based on executing the first filter over the source text and an explanation for the two or more second suggestions, wherein generating the output set of two or more second suggestions includes:

identifying one or more first source text units of a first class corresponding to the first filter from a plurality of source text units associated with the source text; and

transforming the one or more first source text units to the output set of two or more second suggestions;

transmitting the output set of two or more second suggestions for the different portions of the source text and the explanation for the two or more second suggestions to the second computer; and

receiving, from the second computer, a second input specifying to apply the two or more second suggestions, and in response to the second input, automatically applying the two or more second suggestions to the different portions of the source text and transmitting, to the second computer, updated presentation instructions, execution of which by the second computer causes displaying of an updated text with the two or more second suggestions having been applied to the different portions of the source text.

12 . The one or more non-transitory computer-readable media of claim 11 , each of the filters being programmed to execute a different type of spelling or grammar adjustment of the source text.

13 . The one or more non-transitory computer-readable media of claim 11 , each of the filters being programmed to execute a different type of clarity adjustment of the source text.

14 . The one or more non-transitory computer-readable media of claim 11 , further comprising:

parsing the source text into a the plurality of source text units; and

evaluating each particular source text unit among the plurality of source text units using a trained machine-learning model, and receiving a classification output from the trained machine-learning model that classifies each particular source text unit into a particular class among a plurality of possible classes corresponding to the one or more filters.

15 . A computer system comprising:

one or more processing units;

one or more network interfaces configured to communicatively couple the one or more processing units to a data communication network;

digital memory storing sequences of program instructions that, when executed by the computer system, cause performance of executable checks for checking a digitally stored source text that has been received via the data communication network from a computing device that is executing a text processing extension, a text-unit check being one of the executable checks, the text-unit check including multi-class text classifier instructions operatively coupled to text-unit suggestion instructions, the text-unit suggestion instructions being operatively coupled to a digital text-unit store; and

wherein execution of the sequences of program instructions causes:

reading the source text;

sending, to the computing device via the data communication network, instructions for presenting one or more filters via a user interface, the one or more filters being configured to generate one or more first suggestions concerning the source text when the filters are selected and executed, each of the filters being configured to generate a different type of the one or more first suggestions, each of the one or more first suggestions including a change to a character, word, phrase, or sentence of the source text;

receiving, from the computing device via the data communication network, a first input specifying a selection of a first filter of the one or more filters;

in response to detecting the first input specifying the selection of the first filter, generating an output set of two or more second suggestions for different portions of the source text based on executing the first filter over the source text and an explanation for the two or more second suggestions, wherein generating the output set of two or more second suggestions includes:

identifying one or more first source text units of a first class corresponding to the first filter from a plurality of source text units associated with the source text; and

transforming the one or more first source text units to the output set of two or more second suggestions;

transmitting the output set of two or more second suggestions for the different portions of the source text and the explanation for the two or more second suggestions to a second computer; and

receiving, from the second computer, a second input specifying to apply the two or more second suggestions, and in response to the second input, automatically applying the two or more second suggestions to the different portions of the source text and transmitting, to the second computer, updated presentation instructions, execution of which by the second computer causes displaying of an updated text with the two or more second suggestions having been applied to the different portions of the source text.

16 . The computer system of claim 15 , each of the filters being programmed to execute a different type of spelling or grammar adjustment of the source text.

17 . The computer system of claim 15 , each of the filters being programmed to execute a different type of clarity adjustment of the source text.

18 . The computer system of claim 15 , each of the filters being programmed to execute a different type of tone adjustment of the source text.

19 . The computer system of claim 15 , each of the filters being programmed to execute a different type of transparency adjustment of the source text.

20 . The computer system of claim 15 , wherein execution of the sequences of program instructions further causes:

parsing the source text into a the plurality of source text units; and

evaluating each particular source text unit among the plurality of source text units using a trained machine-learning model, and receiving a classification output from the trained machine-learning model that classifies each particular source text unit into a particular class among a plurality of possible classes corresponding to the one or more filters.