# US 5,299,125 A · Natural language processing system and method for parsing a plurality of input symbol sequences into syntactically or pragmatically correct word messages > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 5,299,125 A - Document ID: US5299125A - Status: Granted - Kind: A - Application number: 08/015,290 - Filed: 1993-02-08 - Granted: 1994-03-29 - Earliest claimed: 1990-08-09 - Assignees: Semantic Compaction Systems - Inventors: Bruce R. Baker; Eric H. Nyberg - Web page: https://patentgrep.com/patent/US5299125A ## CPC - G09B 21/00: Teaching, or communicating with, the blind, deaf or mute (audible presentation of material to be studied G09B5/04; devices or methods for replacing direct visual or auditory perception by another kind of perception A61F9/08, A61F11/04; audible indication of meter readings or of colour G01D7/12; watches for blind persons G04B25/02; speech analysis, speech recognition G10L; sound-recording or reproducing, per se G11B) - G06F 40/253: Grammatical analysis; Style critique - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A Natural Language Processing System utilizes a symbol parsing layer in combination with an intelligent word parsing layer to produce a syntactically or pragmatically correct output sentence or other word message. Initially, a plurality of polysemic symbol sequences are input through a keyboard segmented into a plurality of semantic, syntactic, or pragmatic segments including agent, action and patient segments, for example. One polysemic symbol sequence, including a plurality of polysemic symbols, is input from each of the three segments of the keyboard. A symbol parsing device, in a symbol parsing layer, then parses each of the plurality of symbols in each polysemic symbol sequence to access a previously stored word, morpheme, or phrase. The word, morpheme, or phrase is accessed which corresponds to the polysemic symbol sequence and further corresponds to one of the designated agent, action or patient segments. Each accessed word, morpheme, or phrase further accesses corresponding and previously stored grammatical and semantic information. An intelligent word parsing layer then receives and subsequently applies each of the plurality of words, morphemes, or phrases to a predetermined hierarchy of rules based upon the grammatical and semantic information corresponding to each of the plurality of words, morphemes, or phrases. The intelligent word parsing device in the word parsing layer subsequently parses the received plurality of accessed words, morphemes, or phrases into a syntactically or pragmatically correct output sentence or other word message. ## Claims ### Claim 1 A natural language processing system for initially parsing each of a plurality of sequences of input polysemic symbols, each sequence including a plurality of input polysemic symbols and accessing a single word, morpheme, or phrase, and subsequently combining each of the single words, morphemes, or phrases into a syntactically or pragmatically correct word message, the system comprising: input means, segmented into a plurality of syntactical, semantic, or pragmatic segments, each such segment including a plurality of keys, each key including one of said polysemic symbols, for inputting syntactic, semantic, or pragmatic segment information and the corresponding polysemic symbol of an actuated key; first memory means for storing a plurality of symbol sequences, each of said symbol sequences including a plurality of polysemic symbols and syntactic, semantic, or pragmatic segment information, a word, morpheme, or phrase for each of said plurality of symbol sequences, and grammatical and semantic information corresponding to each word, morpheme, or phrase; symbol parsing means, operatively connected to said input means and said memory means, for detecting each of a plurality of actuated keys, parsing a plurality of polysemic symbols corresponding to sequentially actuated keys, and comparing said parsed sequence of polysemic symbols and syntactic, semantic, or pragmatic segment information corresponding to the sequentially actuated keys, to thereby access a previously stored word, morpheme or phrase and corresponding previously stored grammatical and semantic information; and word combining means, operatively connected to said symbol parsing means, for sequentially accessing each of a plurality of predetermined rules and applying the plurality of predetermined rules to said grammatical and semantic information corresponding to a plurality of words, morphemes, or phrases received from said symbol parsing means to obtain a syntactically or pragmatically correct word message. ### Claim 2 (depends on 1) The natural language processing system of claim 1, further including: second memory means, operatively connected to said word combining means, for storing said plurality of predetermined rules. ### Claim 3 (depends on 2) The natural language processing system of claim 2, wherein said first and second memory means are erasable programmable read only memories (EPROMs). ### Claim 4 (depends on 3) The natural language processing system of claim 3, further comprising: voice synthesizing means, operatively connected to said word combining means, for receiving and voice synthesizing said syntactically or pragmatically correct word message; and output means, operatively connected to said voice synthesizing means, for receiving and outputting said voice synthesized syntactically or pragmatically correct word message as an audible message. ### Claim 5 (depends on 4) The natural language processing system of claim 4, wherein said output means is a speaker. ### Claim 6 (depends on 5) The natural language processing system of claim 5, wherein said syntactic, semantic, or pragmatic segments includes an agent segment, an action segment, and a patient segment, each including a plurality of keys. ### Claim 7 (depends on 6) The natural language processing system of claim 6, wherein said word combining means receives a word, morpheme, or phrase corresponding to a sequence of polysemic symbols from each of said agent segment, said action segment, and said patient segment. ### Claim 8 (depends on 7) The natural language processing system of claim 7, wherein said word combining means integrates said received plurality of words, morphemes, or phases irrespective of sequential receiving order from said symbol parsing means, corresponding to said agent segment, said action segment, and said patient segment. ### Claim 9 (depends on 8) The natural language processing system of claim 8, wherein said word combining means sequentially applies each of the plurality of predetermined rules to the grammatical and semantic information, corresponding to each of the plurality of words, morphemes, or phrases upon receipt of each of the plurality of words, morphemes, or phrases to thereby produce said syntactically or pragmatically correct word message. ### Claim 10 (depends on 8) The natural language processing system of claim 8, wherein said word combining means applies each of the sequentially accessed plurality of predetermined rules to the grammatical and semantic information, corresponding to each of the plurality of words, morphemes, or phrases, upon receipt of all of the plurality of words, morphemes, or phrases from said symbol parsing means. ### Claim 11 (depends on 3) The natural language processing system of claim 3, further comprising: language translation means, operatively connected to said word combining means, for receiving and translating said syntactically or pragmatically correct word message from a first language into a designated target language; and output means, operatively connected to said language translation means, for receiving and outputting said translated word message as an audible message. ### Claim 12 (depends on 11) The natural language processing system of claim 11, wherein said output means is a speaker. ### Claim 13 (depends on 1) The natural language processing system of claim 1, further comprising: voice synthesizing means, operatively connected to said word combining means, for receiving and voice synthesizing said syntactically or pragmatically correct word message; and output means, operatively connected to said voice synthesizing means, for receiving and outputting said voice synthesized syntactically or pragmatically correct word message as an audible message. ### Claim 14 (depends on 13) The natural language processing system of claim 13, wherein said output means is a speaker. ### Claim 15 (depends on 1) The natural language processing system of claim 1, further comprising: language translation means, operatively connected to said word combining means, for receiving and translating said syntactically or pragmatically correct word message from a first language into a designated target language; and output means, operatively connected to said language translation means, for receiving and outputting said translated word message as an audible message. ### Claim 16 (depends on 15) The natural language processing system of claim 15, wherein said output means is a speaker. ### Claim 17 (depends on 1) The natural language processing system of claim 1, wherein said syntactic, semantic, or pragmatic segments include an agent segment, an action segment, and a patient segment, each including a plurality of keys. ### Claim 18 (depends on 17) The natural language processing system of claim 17, wherein said word combining means receives a word, morpheme, or phrase corresponding to a sequence of polysemic symbols from each of said agent segment, said action segment, and said patient segment. ### Claim 19 (depends on 18) The natural language processing system of claim 18, wherein said word combining means integrates said received plurality of words, morphemes, or phrases, irrespective of sequential receiving order from said symbol parsing means, corresponding to said agent segment, said action segment, and said patient segment. ### Claim 20 (depends on 1) The natural language processing system of claim 1, wherein said word combining means sequentially applies each of the plurality of predetermined rules to the grammatical and semantic information, corresponding to each of the plurality of words, morphemes, or phrases upon receipt of each of the plurality of words, morphemes, or phrases, to thereby produce said syntactically or pragmatically correct word message. ### Claim 21 (depends on 1) The natural language processing system of claim 1, wherein said word combining means applies, to the grammatical and semantic information, corresponding to each of the plurality or words, morphemes, or phrases, each of said sequentially accessed plurality of predetermined rules, upon receipt of all of the plurality of words, morphemes, or phrases from said symbol parsing means. ### Claim 22 (depends on 1) The natural language processing system of claim 1, wherein said input means includes, input storage means, for actuating a storage mode and for allowing input and subsequent storage in said first memory means of a plurality of symbols forming a new symbol sequence. ### Claim 23 (depends on 22) The natural language processing system of claim 22 wherein said input means further includes, input character means for actuating a character input mode and for allowing input, designation and subsequent storage in said first memory means of a word, morpheme, or phrase corresponding to said stored new symbol sequence. ### Claim 24 (depends on 23) The natural language processing system of claim 23, wherein said input means further includes, input spell mode means for actuating a grammatical and semantic information mode and for allowing input, designation, and subsequent storage in said first memory means of grammatical and semantic information corresponding to said stored new symbol sequence. ### Claim 25 (depends on 23) The natural language processing system of claim 23, further comprising: display means, operatively connected to said input spell mode means, for displaying a plurality of sequential menus containing grammatical and semantic information for designation by said input spell mode means. ### Claim 26 (depends on 25) The natural language processing system of claim 25, where said sequential menus include a part of speech menu, a grammatical features menu, a semantic category menu, and a semantic subcategory menu. ### Claim 27 (depends on 22) The natural language processing system of claim 22, further comprising: voice synthesizing means, operatively connected to said word combining means, for receiving and voice synthesizing said syntactically or pragmatically correct word message; output means, operatively connected to said voice synthesizing means, for receiving and outputting said voice synthesized syntactically or pragmatically correct word message as an audible message. ### Claim 28 (depends on 27) The natural language processing system of claim 27, where said sequential menus include a part of speech menu, a grammatical features menu, a semantic category menu, and a semantic subcategory menu. ### Claim 29 (depends on 28) The natural language processing system of claim 28, wherein grammatical and semantic information is designated, input, and stored via said input spell mode means by a user sequentially selecting information displayed on each of said sequential means. ### Claim 30 A natural language processing system for initially detecting each of a plurality of sequences of input polysemic symbols, each sequence including a plurality of input polysemic symbols, to produce a plurality of words or morphemes and subsequently combining the plurality of words or morphemes into a syntactically or pragmatically correct word message, the system comprising: a keyboard, segmented into a plurality of syntactic, semantic, or pragmatic category keyboard sections, each syntactic, semantic, or pragmatic category section including a plurality of keys, each key including one of said polysemic symbols; first memory for storing a plurality of symbol sequences, each symbol sequence corresponding to a predetermined syntactic, semantic, or pragmatic category and including a plurality of polysemic symbols, said first memory further storing at least one of a plurality of words or morphemes and grammatical and semantic word parsing information corresponding each of said plurality of symbol sequences and a predetermined syntactic, semantic, or pragmatic category; detecting means, operatively connected to said keyboard, for detecting actuation of each of a plurality of sequentially depressed keys, including corresponding syntactic, semantic, or pragmatic category information and each corresponding polysemic symbol; comparison means, operatively connected to said detecting means and said first memory, for comparing said detected symbol sequence and corresponding syntactic, semantic, or pragmatic category, to access said at least one of a plurality of words or morphemes and grammatical and semantic word parsing information corresponding to said detected symbol sequence and corresponding syntactic, semantic, or pragmatic category information from said memory; word combining means, operatively connected to said comparison means, for receiving a plurality of words or morphemes accessed by said comparison means, and for applying a plurality of predetermined rules to each of the plurality of words or morphemes based upon the grammatical and semantic word parsing information corresponding to each of the plurality of received words or morphemes, and for combining said plurality of received words or morphemes into a syntactically or pragmatically correct word message. ### Claim 31 (depends on 30) The natural language processing system of claim 30, wherein said plurality of syntactic, semantic, or pragmatic categories and predetermined syntactic, semantic, or pragmatic categories include at least one of an agent, action, and patient. ### Claim 32 (depends on 31) The natural language parsing system of claim 31, wherein said plurality of words or morphemes received by said word combining means, includes at least one word corresponding to each of a symbol sequence of the agent syntactic category, the patient syntactic category and the action syntactic category. ### Claim 33 (depends on 32) The natural language processing system of claim 32, wherein said word combining means integrates said received plurality of words or morphemes, irrespective of sequential receiving order from said comparison means, corresponding to said agent syntactic category, patient syntactic category and action syntactic category. ### Claim 34 (depends on 30) The natural language processing system of claim 30, wherein said word combining means may add words, to said plurality of received words or morphemes, to produce said syntactically or pragmatically correct word message, dependent upon said application of said plurality of predetermined rules. ### Claim 35 (depends on 30) The natural language processing system of claim 30, further including: second memory, operatively connected to said combining means, for storing said plurality of predetermined rules. ### Claim 36 (depends on 35) The natural language processing system of claim 35, wherein said first and second memories are erasable programmable read only memories (EPROMs). ### Claim 37 (depends on 30) The natural language processing system of claim 30, further comprising: voice synthesizing means, operatively connected to said word parsing means, for receiving and voice synthesizing said syntactically or pragmatically correct word message output; output means, operatively connected to said voice synthesizing means, for receiving and outputting said voice synthesized syntactically or pragmatically correct word message as an audible message. ### Claim 38 (depends on 37) The natural language processing system of claim 37, wherein said output means is a speaker. ### Claim 39 (depends on 30) The natural language processing system of claim 30, further comprising: language translation means, operatively connected to said word combining means, for receiving and translating said syntactically or pragmatically correct word message from a first language into a designated target language; output means, operatively connected to said language translation means, for receiving and outputting said translated word message as an audible message. ### Claim 40 (depends on 39) The natural language processing system of claim 39, wherein said output means is a speaker. ### Claim 41 (depends on 30) The natural language processing system of claim 30, wherein said word combining means sequentially applies the plurality of predetermined rules to the grammatical and semantic information, corresponding to each of the plurality of words or morphemes upon receipt of each of the plurality of words or morphemes to thereby produce said syntactically or pragmatically correct word message. ### Claim 42 (depends on 30) The natural language processing system of claim 30, wherein said word combining means applies the plurality of predetermined rules to the grammatical and semantic information, corresponding to each of the plurality of words or morphemes upon receipt of each of the plurality of words or morphemes from said comparison means. ### Claim 43 (depends on 30) The natural language processing system of claim 30, wherein said input means includes, input storage means, for actuating a storage mode and for allowing input and subsequent storage in said first memory of a plurality of symbols for a new symbol sequence. ### Claim 44 (depends on 23) The natural language processing system of claim 23 wherein said input means includes, input character means for actuating a character input mode and for allowing input, designation and subsequent storage in said first memory means of a word, morpheme, or a plurality of words corresponding to said stored new symbol sequence. ### Claim 45 (depends on 44) The natural language processing system of claim 44, wherein said input means further includes, input spell mode means for actuating a grammatical and semantic information mode and for allowing input, designation, and subsequent storage in said first memory means of grammatical and semantic information corresponding to said stored new symbol sequence. ### Claim 46 (depends on 45) The natural language processing system of claim 45, further comprising: display means, operatively connected to said input spell mode means, for displaying a plurality of sequential menus containing grammatical and semantic information for designation by said input spell mode means. ### Claim 47 (depends on 46) The natural language processing system of claim 46, where said sequential menus include a part of speech menu, a grammatical features menu, a semantic category menu, and a semantic subcategory menu. ### Claim 48 (depends on 47) The natural language processing system of claim 47, wherein grammatical and semantic information is designated, input, and stored via said input spell mode means by a user sequentially selecting information displayed on each of said sequential menus. ### Claim 49 A natural language processing system for initially parsing each of a plurality of sequences of input polysemic symbols, each sequence including a plurality of input polysemic symbols, to produce a plurality of words or morphemes and subsequently combine the plurality of words or morphemes into a syntactically correct word message, the system comprising: input means for inputting each of a plurality of polysemic symbols, each polysemic symbol input upon actuation of an input key, said actuation of each input key further including syntactic segment information designating each corresponding polysemic symbol as one of an agent, action, and patient; symbol parsing means, operatively connected to said input means, for parsing a plurality of sequentially input polysemic symbols, into a plurality of input symbol sequences and accessing each of a plurality of words or morphemes previously stored with symbol sequences corresponding to each of said input symbol sequences and a corresponding one of the designated agent, action, and patient, each said accessed word or morpheme further accessing corresponding, and previously stored, grammatical and semantic information; word combining means, operatively connected to said symbol parsing means, for receiving and subsequently applying a plurality of predetermined rules to each of the plurality of accessed words or morphemes and, based upon the corresponding grammatical and semantic information, for combining said received plurality of accessed words or morphemes, into a syntactically correct word message. ### Claim 50 (depends on 49) The natural language processing system of claim 49, wherein the symbol parsing means includes: first memory means for storing each of a plurality of symbol sequences, each of a plurality of words or morphemes and corresponding grammatical and semantic information, accessible upon inputting of a corresponding symbol sequence and a corresponding designated one of an agent, action and patient. ### Claim 51 (depends on 50) The natural language processing system of claim 50, wherein said input means includes, input storage means for actuating a storage mode and for allowing input and subsequent storage in said first memory means of a plurality of symbols forming a new symbol sequence. ### Claim 52 (depends on 51) The natural language processing system of claim 51, wherein said input means further includes, input character means for actuating a character input mode and for allowing input, designation and subsequent storage in said first memory means of a word, morpheme, or plurality of words corresponding to said stored new symbol sequence. ### Claim 53 (depends on 52) The natural language processing system of claim 52 wherein said input means further includes, input spell mode means for actuating a grammatical and semantic information mode and for allowing input, designation, and subsequent storage in said first memory means of grammatical and semantic information corresponding to said stored new symbols sequence. ### Claim 54 (depends on 53) The natural language processing system of claim 53, further comprising: display means, operatively connected to said input spell mode means, for displaying a plurality of sequential menus containing grammatical and semantic information for designation by said input spell mode means. ### Claim 55 (depends on 50) The natural language processing system of claim 50, wherein the word combining means includes: second memory means for storing said plurality of predetermined rules. ### Claim 56 (depends on 55) The natural language processing system of claim 55, wherein said first and second memory means are erasable programmable read only memories (EPROMs). ### Claim 57 (depends on 49) The natural language processing system of claim 49, further comprising: voice synthesizing means, operatively connected to said word combining means, for receiving and voice synthesizing said syntactically correct word message; output means, operatively connected to said voice synthesizing means, for receiving and outputting said voice synthesized syntactically correct word message as an audible message. ### Claim 58 (depends on 57) The natural language processing system of claim 57, wherein said output means is a speaker. ### Claim 59 (depends on 49) The natural language processing system of claim 49, further comprising: language translation means, operatively connected to said word combining means, for receiving and translating said syntactically correct word message form a first language into a designated target language; output means, operatively connected to said language translation means, for receiving and outputting said translated word message as an audible message. ### Claim 60 (depends on 59) The natural language processing system of claim 59, wherein said output means is a speaker. ### Claim 61 (depends on 49) The natural language processing system of claim 49, wherein said word combining means receives each of the plurality of words or morphemes corresponding to a sequence of polysemic symbols from each of said agent, action, and patient grammatical segments. ### Claim 62 (depends on 61) The natural language processing system of claim 61, wherein said word combining means applies said plurality of predetermined rules to said received plurality of accessed words or morphemes irrespective of sequential receiving order, from said symbol parsing means, corresponding to said agent, action, and patient syntactic segments. ### Claim 63 (depends on 49) The natural language processing system of claim 49, wherein said word combining means sequentially applies said plurality of predetermined rules to each of the plurality of accessed words or morphemes, as sequentially received based upon corresponding grammatical and semantical information to thereby combine said sequentially received plurality of words or morphemes into a syntactically correct word message. ### Claim 64 (depends on 49) The natural language processing system of claim 49, wherein said word combining means applies said plurality of predetermined rules to each of the plurality of accessed words or morphemes based upon corresponding grammatical and semantic information, to thereby combine upon receipt of all of the words or morphemes, said words or morphemes into a syntactically correct word message. ### Claim 65 A natural language processing method for initially parsing each of a plurality of sequences of input polysemic symbols, each sequence including a plurality of input polysemic symbols and accessing a single word, morpheme, or phrase, and subsequently combining each of the single words, morphemes, or phrases into a syntactically or pragmatically correct word message, comprising the steps of: (a) inputting syntactic, semantic, or pragmatic segment information and a corresponding polysemic symbol upon actuation of a key on a keyboard segmented into syntactical, semantic, and pragmatic segments, the keyboard including a plurality of keys and a plurality of corresponding polysemic symbols; (b) storing a plurality of symbol sequences in a memory, each of the symbol sequences including a plurality of polysemic symbols and syntactic, semantic, or pragmatic segment information, a word, morpheme, or phrase for each of the plurality of symbol sequences, and grammatical and semantic information corresponding to each word, morpheme, or phrase; (c) detecting each of a plurality of actuated keys, parsing a plurality of polysemic symbols corresponding to sequentially actuated keys, and comparing the parsed sequence of polysemic symbols and syntactic, semantic, or pragmatic segment information corresponding to the sequentially actuated keys, to thereby access a previously stored word, morpheme or phrase and corresponding previously stored grammatical and semantic information; and (d) accessing, sequentially, each of a plurality of predetermined rules and applying the plurality of predetermined rules to the grammatical and semantic information corresponding to a plurality of words, morphemes, or phrases received, to obtain a syntactically or pragmatically correct word message. ### Claim 66 (depends on 65) The natural language processing method of claim 65, further comprising the step of: (e) storing the plurality of predetermined rules. ### Claim 67 (depends on 65) The natural language processing method of claim 65, further comprising the steps of: (e) receiving and voice synthesizing the syntactically or pragmatically correct word message of step (d); and (f) receiving and outputting the voice synthesized syntactically or pragmatically correct word message of step (e) as an audible message. ### Claim 68 (depends on 65) The natural language processing method of claim 65, further comprising the steps of: (e) receiving and translating the syntactically or pragmatically correct word message of step (d) from a first language into a designated target language; and (f) receiving and outputting the translated word message of step (e) as an audible message. ### Claim 69 (depends on 65) The natural language processing method of claim 65, wherein each of the plurality of predetermined rules are sequentially applied to the grammatical and semantic information, corresponding to each of the plurality of words, morphemes, or phrases upon receipt of each of the plurality of words, morphemes, or phrases, to thereby produce said syntactically or pragmatically correct word message. ### Claim 70 (depends on 65) The natural language processing method of claim 65, wherein to the grammatical and semantic information, corresponding to each of the plurality of words, morphemes, or phrases, each of the sequentially accessed plurality of predetermined rules are applied upon receipt of all of the plurality of words, morphemes, or phrases. ### Claim 71 A natural language processing method for initially detecting each of a plurality of sequences of input polysemic symbols, each sequence including a plurality of input polysemic symbols, to produce a plurality of words or morphemes and subsequently combining the plurality of words or morphemes into a syntactically or pragmatically correct word message, the method comprising the steps of: (a) inputting syntactic, semantic, or pragmatic information and a corresponding polysemic symbol from a keyboard, segmented into a plurality of syntactic, semantic, or pragmatic category keyboard sections upon key actuation, each syntactic, semantic, or pragmatic category section including a plurality of keys, each key including one of the polysemic symbols; (b) storing a plurality of symbol sequences, each symbol sequence corresponding to a predetermined syntactical, semantic, or pragmatic category and including a plurality of polysemic symbols in a first memory, the first memory further storing at least one of a plurality of words or morphemes and grammatical and semantic word parsing information corresponding each of the plurality of symbol sequences and a predetermined syntactic, semantic, or pragmatic category; (c) detecting actuation of each of a plurality of sequentially depressed keys, including corresponding syntactic, semantic, or pragmatic category information and each corresponding polysemic symbol; (d) comparing the detected symbol sequence and corresponding syntactic, semantic, or pragmatic category, to access the at least one of a plurality of words or morphemes and grammatical and semantic word parsing information corresponding to the detected symbol sequence and corresponding syntactic, semantic, or pragmatic category information from the first memory; (e) receiving a plurality of words or morphemes accessed in step (d) and applying a plurality of predetermined rules to each of the plurality of words or morphemes based upon the grammatical and semantic word parsing information corresponding to each of the plurality of received words or morphemes, and combining the plurality of received words or morphemes into a syntactically or pragmatically correct word message. ### Claim 72 (depends on 71) The natural language processing method of claim 71, wherein words may be added to the plurality of received words or morphemes, to produce the syntactically or pragmatically correct word message output, dependent upon the application of the plurality of predetermined rules. ### Claim 73 (depends on 71) The natural language processing method of claim 71, further including the steps of: (f) storing the plurality of predetermined rules in a second memory. ### Claim 74 (depends on 71) The natural language processing method of claim 71, further comprising the steps of: (f) receiving and voice synthesizing the syntactically or pragmatically correct word message of step (e); (g) receiving and outputting the voice synthesized syntactically or pragmatically correct word message of step (f) as an audible message. ### Claim 75 (depends on 71) The natural language processing method of claim 71, further comprising the steps of: (f) receiving and translating the syntactically or pragmatically correct word message of step (e) from a first language into a designated target language; and (g) receiving and outputting said translated word message of step (f) as an audible message. ### Claim 76 (depends on 71) The natural language processing method of claim 71, wherein the plurality of predetermined rules are sequentially applied to the grammatical and semantic information, corresponding to each of the plurality of words or morphemes upon receipt of each of the plurality of words or morphemes to thereby produce said syntactically or pragmatically correct word message. ### Claim 77 (depends on 71) The natural language processing method of claim 71, wherein the plurality of predetermined rules are applied to the grammatical and semantic information, corresponding to each of the plurality of words or morphemes upon receipt of all of the plurality of words or morphemes. ### Claim 78 A natural language processing method for initially parsing each of a plurality of sequences of input polysemic symbols, to produce a plurality of words or morphemes and to combine the plurality of words or morphemes into a syntactically correct word message, the method comprising the steps of: (a) inputting each of a plurality of polysemic symbols, each polysemic symbol input upon actuation of an input key, the actuation of each input key further including syntactic segment information designating each corresponding polysemic symbol as one of an agent, action, and patient; (b) parsing a plurality of sequentially input polysemic symbols, into a plurality of input symbol sequences and accessing each of a plurality of words or morphemes previously stored with symbol sequences corresponding to each of the input symbol sequences and a corresponding one of the designated agent, action, and patient, each accessed word or morpheme further accessing corresponding, and previously stored, grammatical and semantic information; (c) receiving and subsequentially applying a plurality of predetermined rules to each of the plurality of accessed words or morphemes and, based upon the corresponding grammatical and semantic information, combining the received plurality of accessed words or morphemes, into a syntactically correct word message. ### Claim 79 (depends on 78) The natural language processing method of claim 78, further comprising: (d) receiving and voice synthesizing the syntactically correct word message of step (c); and (e) receiving and outputting the voice synthesized syntactically correct word message of step (d) as an audible message. ### Claim 80 (depends on 78) The natural language processing method of claim 78, further comprising the steps of: (d) receiving and translating the syntactically correct word message of step (c) from a first language into a designated target language; and (e) receiving and outputting the translated word message of step (d) as an audible message. ### Claim 81 (depends on 78) The natural language processing method of claim 78, wherein the plurality of predetermined rules are applied to said received plurality of accessed words or morphemes irrespective of sequential receiving order, corresponding to said agent, action, and patient syntactic segments. ### Claim 82 (depends on 78) The natural language processing method of claim 78, wherein the plurality of predetermined rules are sequentially applied to each of the plurality of accessed words or morphemes, as sequentially received, based upon corresponding grammatical and semantical information to thereby combine said sequentially received plurality of words or morphemes into a syntactically correct word message. ### Claim 83 (depends on 78) The natural language processing method of claim 78, wherein the plurality of predetermined rules are applied to each of the plurality of accessed words or morphemes based upon corresponding grammatical and semantic information, to thereby combine upon receipt of all of the words or morphemes, the words or morphemes into a syntactically correct word message.