Method and apparatus for natural language document orchestrator

Patent metadata

Field	Value
Publication number	US-11727222-B2
Application number	US-202117185807-A
Country	US
Kind code	B2
Filing date	Feb 25, 2021
Priority date	Oct 31, 2016
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

Methods, apparatuses, and computer program products are described herein that are configured to be embodied as a natural language document orchestrator. In some example embodiments, a method is provided that comprises generating natural language text. The method of this embodiment may also include executing document orchestration requests from a scripted input language file.

First claim

That which is claimed:

1. An apparatus comprising at least one processor and at least one memory storing instructions that, with the at least one processor, configure the apparatus to:
parse one or more document orchestration requests of an input language file to identify one or more document orchestration module identifiers;
invoke one or more document orchestration modules respectively associated with the one or more document orchestration module identifiers of the one or more document orchestration requests;
generate natural language text based at least in part on a natural language output from the one or more document orchestration modules; and
provide the natural language text for display via a user interface.

2. The apparatus of claim 1 , wherein a document orchestration module comprises one or more of a morphology processor, an orthography processor, or a morphophonology processor.

3. The apparatus of claim 2 , wherein the least one memory stores instructions that, with the at least one processor, further configure the apparatus to:
invoke a morphology processor;
apply morphology rules an input of the input language file to generate natural language;
substitute a base word form in the input with an inflected word form of a lexicon by searching the lexicon for the base word form and determining which inflected form from the lexicon to substitute;
utilize a base word form for other realization operations, by determining other morphological changes to the input; and
output a natural language output comprising a morphological output.

4. The apparatus of claim 2 , wherein the least one memory stores instructions that, with the at least one processor, further configure the apparatus to:
invoke a morphophonology processor;
apply morphophonology rules to an input of the input language file to generate natural language; and
output a natural language output comprising a morphophonological output.

5. The apparatus of claim 2 , wherein the least one memory stores instructions that, with the at least one processor, further configure the apparatus to:
invoke a orthography processor;
apply orthography rules to an input of the input language file to generate natural language by one or more of capitalizing individual words, formatting numbers, performing punctuation operations, or placing white space characters between words; and
output a natural language output comprising an orthographical output.

6. The apparatus of claim 2 , wherein the input language file includes at least partially orchestrated natural language text.

7. The apparatus of claim 2 , wherein the natural language output of the invoked document orchestration module is processed by further document orchestration requests of the input language file or outputted directly to an output text processor or the user interface.

8. A computer program product comprising at least one computer-readable non-transitory memory medium having program code instructions stored thereon, the program code instructions, when executed by an apparatus, causing the apparatus to:
parse one or more document orchestration requests of an input language file to identify one or more document orchestration module identifiers;
invoke one or more document orchestration modules respectively associated with the one or more document orchestration module identifiers of the one or more document orchestration requests;
generate natural language text based at least in part on a natural language output from the one or more document orchestration modules; and
provide the natural language text for display via a user interface.

9. The computer program product of claim 8 , wherein a document orchestration module comprises one or more of a morphology processor, an orthography processor, or a morphophonology processor.

10. The computer program product of claim 9 , wherein the program code instructions, when executed by the apparatus, further cause the apparatus to:
invoke a morphology processor;
apply morphology rules an input of the input language file to generate natural language;
substitute a base word form in the input with an inflected word form of a lexicon by searching the lexicon for the base word form and determining which inflected form from the lexicon to substitute;
utilize a base word form for other realization operations, by determining other morphological changes to the input; and
output a natural language output comprising a morphological output.

11. The computer program product of claim 9 , wherein the program code instructions, when executed by the apparatus, further cause the apparatus to:
invoke a morphophonology processor;
apply morphophonology rules to an input of the input language file to generate natural language; and
output a natural language output comprising a morphophonological output.

12. The computer program product of claim 9 , wherein the program code instructions, when executed by the apparatus, further cause the apparatus to:
invoke a orthography processor;
apply orthography rules to an input of the input language file to generate natural language by one or more of capitalizing individual words, formatting numbers, performing punctuation operations, or placing white space characters between words; and
output a natural language output comprising an orthographical output.

13. The computer program product of claim 9 , wherein the input language file includes at least partially orchestrated natural language text.

14. The computer program product of claim 9 , wherein the natural language output of the invoked document orchestration module is processed by further document orchestration requests of the input language file or outputted directly to an output text processor or the user interface.

15. A computer implemented method for generating natural language, the method comprising:
parsing one or more document orchestration requests of an input language file to identify one or more document orchestration module identifiers;
invoking one or more document orchestration modules respectively associated with the one or more document orchestration module identifiers of the one or more document orchestration requests;
generating natural language text based at least in part on a natural language output from the one or more document orchestration modules; and
providing the natural language text for display via a user interface.

16. The method of claim 15 , wherein a document orchestration module comprises one or more of a morphology processor, an orthography processor, or a morphophonology processor.

17. The method of claim 16 , further comprising:
invoking a morphology processor;
applying morphology rules an input of the input language file to generate natural language;
substituting a base word form in the input with an inflected word form of a lexicon by searching the lexicon for the base word form and determining which inflected form from the lexicon to substitute;
utilizing a base word form for other realization operations, by determining other morphological changes to the input; and
outputting a natural language output comprising a morphological output.

18. The method of claim 16 , further comprising:
invoking a morphophonology processor;
applying morphophonology rules to an input of the input language file to generate natural language; and
outputting a natural language output comprising a morphophonological output.

19. The method of claim 16 , further comprising:
invoking a orthography processor;
applying orthography rules to an input of t

Assignees

• Arria Data2Text Ltd

Inventors

• Reiter Ehud Baruch
• Ponnamperuma Arachchi Kapila Annuruddha
• Schlafli Michael Simon
• Burnett Neil Stuart
• Dinesh Nikhil

Classifications

• G06F40/56 Primary

  Natural language generation · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G06F40/232

  Orthographic correction, e.g. spell checking or vowelisation · CPC title