Writing a Writer Richard P. Gabriel Only mystery enables us to live - - PowerPoint PPT Presentation

Richard P. Gabriel

Writing a Writer

Only mystery enables us to live Only mystery

–Federico Garcia Lorca

deep in the dark— the power of snow walking in the deepness

–InkWell, December 2014

He gives his harness bells a cloud To ask if there is some spot. The only other music is the illusion Of worn wind and cold mound. The logs are good, glad, and tight. But I have words to keep And miles to go before I sleep, And miles to go before I sleep. revise Frost’s “Stopping by Woods” sound like Hemingway; use short words

awake in the dark— the edge of the water can spread in your presence scrupulous in the twilight— the price of gold chases the way of the world in power time of life issue: a bird of prey pulls up

• ut of the way into the palm

–InkWell, December 2014

Whitman: Adam Smith: Bible:

He gives his harness bells a whip To ask if there is some end. The only other show is the push Of a couple of winds and a falling chip. The woods are clean, murky, and vigorous. But I have roots to preserve And miles to go before I sleep, And miles to go before I sleep. revise Frost’s “Stopping by Woods” sound like Whitman; use short words

tuned adrenalin my music, a beat-boogied headful day after day in the man’s can a man can a crooked rag day— by myself dunking distracted sardines

Whose sums these are I express I know. His unit is in the body though; He will not see me entering existing To consider his sums operate up with snow. My smaller horse must evaluate it interesting To keep in without a family discriminating Between the sums and polar form The darkest mean solar day of the fundamental quantity. He gives his influence devices an exit To pass along if there is some statement. The only other element is the use Of benign context and yielding element. The sums are logical, insensitive, and severe. But I have expressions to position, And large indefinite amounts to go before I sleep in, And large indefinite amounts to go before I position.

Bob Harper Long words Anger halo

not this fatalist murderousness, deathwatch, but your dead subroutine functional function? the orchid— even when it’s Lisped functionally

But InkWell’s Haiku are Crazy!

Shoved off the stairs— falling I become a rainbow

–Ban’ya Natsuishi, 1999

under the sea a fish becomes human in an air pocket

– Annie Bachini, 2002

InkWell is Fallible

a dado of greenweeds,

• f its daughter

the mother’s son dadoing a queen not this study scene, black fly, but your one challenge

So Are “Real” Poets

I am aware of the damp souls of housemaid Sprouting despondently at area gates. Every street-lamp that I pass Beats like a fatalistic drum To-day, this insect, and the world I breathe Where once the waters of your face Spun to my screws…

{ {

• T. S. Eliot

Dylan Thomas

Research Question

Can a program manipulate language like a poet? Can a program think like a poet?

Information Transfer

The summer homes on Long Island were

• closed. Tonight I watched a ferry begin its

crossing to Connecticut. The moon was rising, and as it rose I thought about how the houses are not part of the natural world and what the island looked like to early Dutch sailors coming upon it—like something new.

Literary Writing

Most of the big shore places were closed now and there were hardly any lights except the shadowy, moving glow of a ferryboat across the Sound. And as the moon rose higher the inessential houses began to melt away until gradually I became aware of the old island here that flowered once for Dutch sailors’ eyes—a fresh, green breast of the new world.

–F. Scott Fitzgerald, The Great Gatsby

Writerly Thinking

• (literary) writers think about words
• how they work
• how they interact

Research Goals

• assist human creativity
• mimic a specific writer

Key Idea

The woods are lovely dark and deep alder attractive black abysmal ash beautiful caliginous bottomless balsa colorful dim heavy bamboo dishy dusky intense beech exquisite gloomy profound birch fair subdued unsounded cedar fine-looking unlit wide

Simulated Annealing

…a generic probabilistic metaheuristic for locating a good approximation to the global optimum of a given function in a large, discrete search space….

…(let ((trial (funcall trial-swap))) (setq this-trial-cost (funcall trial-cost trial)) (let ((delta (- current-cost this-trial-cost))) ;;; Is this a good swap? (cond ((< 0 delta) ;;; then do it (funcall finalize-trial trial) (incf swaps) (setq current-cost this-trial-cost)) ;;; has there been an arithmetic problem with the Metropolis computation? (temperature-error ;;; yes, so just skip it (funcall forget-trial trial)) ;;; Metroplis step (t (block metropolis (let ((p (inkwell-random 1.0))) (cond ((< p (handler-bind ((arithmetic-error #'(lambda (c) ;;; Arithmetic error means that the temperature ;;; schedule was too aggressive - going to 0 too fast (declare (ignore c)) (setq temperature-error t) (funcall forget-trial trial) (return-from metropolis nil)))) (exp (/ delta temperature)))) ;;; just make the swap anyway (funcall finalize-trial trial) (setq current-cost this-trial-cost) (incf swaps)) (t (funcall forget-trial trial))))))))))…

Assist Creativity

• use conservative or wild synonym choice

(associative versus dissociative writing)— search diameter, search relevance, decay rate, preference for nearby words, preference for far away words, which synonym aspects to use (hypernyms, meronyms, etc)

• obey or defy n-grams—that is, use familiar or

novel phrasing

Assist Creativity

• satisfy constraints such as word-length,

alternative meanings, word rhythms

• favor rhymes and echoes (similar sounding

words)

• select words based on ontology (concepts) or a

cluster of word-centric concepts to favor or avoid

Mimic Writers

• Big 5 personality traits & their overall weight
• openness, conscientiousness, extroversion,

agreeableness, neuroticism

• a writer’s corpus—to sound like that writer
• whether to favor common words
• an initial halo to establish mood and a bonus for using it
• a bonus for staying close to seed words in the synonym

Mimic Writers

• bonuses for 2-, 3-, 4-, and 5-gram compliance (general

literature and writer)

• multi-word constraint bonus (e.g., :different)
• rhyme & Echo bonuses (:rhyme, :echo, all-rhyme, all-

echo)

• penalty for using words from a corpus of words to avoid
• bonuses for complying with local halos
• bonus for local predicates:

(dog noun-animal pl :predicate #'begins-with- d)

dachshund dachsie dalmatian dandie dinmont dandie dinmont terrier deerhound doggie doggy domestic dog dog

Mimic Writers

• all bonuses can be positive or negative
• it’s possible to sound like another writer
• r to sound unlike that writer

I love holy dogs. King James Bible I favor maddened curs. King James Bible

Template Other Constraints Optimization Function Parallel Simulated Annealing Engine Transformational Touch-up Final English Text English Text Compiler

+ +

Templates

• a domain-specific language for generating text
• in some ways like Christopher Alexander’s

patterns: you can use the solution a million times over, without ever doing it the same way twice

(with-personality-traits (*writer-big-five*) (with-global-constraints ((all-echo)(all-different)) (with-pervasive-predicates (#'syllable-bonus-few) (bind ((w1 (know verb-cognitive)) (w2 (snow noun-substance)) (w3 (or (queer adj) (odd adj) (unusual adj))) (w4 (or (year noun-quantity) (week noun-quantity) (month noun-quantity) (season noun-quantity))) (w5 (shake verb)) (w6 (flake noun)) (here (here adj)) (near (near adj)) (mile (mile noun-quantity pl)) (sleep (sleep verb)) (woods (wood noun-plant pl :+sense [forest] :-sense [wood]))) "Whose (ref woods) these are I (think verb-cognition) I (ref w1). His (house noun) is in the (village noun) though; He will not see me (stop verb gerund) (ref here :rhyme near) To (watch verb-perception) his (ref woods) (fill verb) up with (ref w2 :different w1 :rhyme w1). ...

... "My (little adj) (horse noun-animal) must (think verb-cognition) it (ref w3 :echo w1) To (stop verb) without a (farmhouse noun) (binding near :rhyme w3) Between the (ref woods) and (frozen adj) (lake noun) The (darkest adj) (evening noun) of the (ref w4 :different w3 :rhyme w3). He gives his (harness noun) (bell noun pl) a (ref w5 :echo w3) To (ask verb) if there is some (mistake noun :rhyme w5). The only other (sound noun) is the (sweep verb) Of (easy adj) (wind noun) and (downy adj) (ref w6 :different w5 :rhyme w5). The (ref woods) are (lovely adj), (dark adj), and (deep adj). But I have (promise noun pl) to (keep verb :rhyme sleep), And (ref mile) to go before I (ref sleep), And (ref mile) to go before I (sleep verb :different sleep :rhyme sleep).”))))

(with-personality-traits (*writer-big-five*) (with-global-constraints ((all-echo)(all-different)) (with-pervasive-predicates (#'syllable-bonus-few) (with-typographic-style (poem) (bind ((w1 (<choose> verb-cognition :+sense [know certain])) (w2 (snow noun-substance :rhyme [though])) (w3 (<choose> adj :+sense [queer odd unusual weird demented stupid silly])) (w4 (or (year noun-quantity) (week noun-quantity) (month noun-quantity) (season noun-quantity))) (w5 (<choose> verb-motion :+sense [cause move back forth shake])) (w6 (<choose> noun-object :+sense [small fragment broken break whole flake])) (here (here adj)) (near (near adj)) (mile (mile noun-quantity pl)) (sleep (sleep verb)) (woods (<choose> noun-plant pl :+sense [forest trees plants wooded area] :-sense [wood]))) "Whose (ref woods) these are I (<choose> verb-cognition :+sense [think guess surmise]) I (ref w1). His (house noun) is in the (village noun) though; He will not see me (stop verb gerund) (ref here :rhyme near) To (watch verb-perception) his (ref woods) (fill verb) up with (ref w2 :different w1 :rhyme w1). ...

My (<choose> adj :sense little-sense) (horse noun-animal) must (<choose> verb-cognition :sense think-sense) it (ref w3 :echo w1) To (stop verb) without a (<choose> noun :sense farmhouse-sense) (binding near :rhyme w3) Between the (ref woods) and (frozen adj) (<choose> noun-object :sense lake-sense) The (<choose> adj -est :sense darkest-sense) (<choose> noun-time :sense evening-sense)

• f the (ref w4 :different w3 :rhyme w3).

He gives his (harness noun) (bell noun pl) a (ref w5 :echo w3) To (ask verb) if there is some (mistake noun :rhyme w5). The only other (<choose> noun :sense sound-sense) is the (<choose> noun-act :sense arc-sense) Of (<choose> ADJ :sense easy-sense) (wind noun) and (<choose> ADJ :sense downy-sense) (ref w6 :different w5 :rhyme w5). The (ref woods) are (<choose> adj :sense lovely-sense), (<choose> adj :sense dark-sense), and (<choose> adj :sense deep-sense), But I have (promise noun pl) to (keep verb :rhyme sleep), And (ref mile) to go before I (ref sleep), And (ref mile) to go before I (sleep verb :different sleep :rhyme sleep)."))))

little-sense little small diminuitive tiny puny farmhouse-sense farm house farmhouse shed lake-sense body fresh water surrounded surround land lake darkest-sense devoid deficient light brightness shadowed shadow black color have hue dark evening-sense latter day period decreasing decrease daylight late afternoon nightfall early part night dinner bedtime spent spend special way evening sound-sense particular auditory effect produce give given cause subjective sensation hear hearing mechanical vibration transmitted transmit an elastic medium sound arc-sense movement arc sweep easy-sense pose posing difficulty require little effort hurried hurry forced force free worry anxiety easy lovely-sense lovely pretty appealing dark-sense dark devoid light black dismal dejected unilluminated deep-sense deep depth penetration extreme intense strong

InkWell

• expanded WordNet synonym dictionary: 160,000

words

• 20,000 most common words
• expanded CMU phonetic dictionary: 220,000 words
• rhyming dictionary: 42,000 words
• stem dictionary: 163,000 entries (+ Porter Stemmer +

InkWell

• n-grams: 50m from general literature (heavily

processed Google 2–5-grams);100,000– 1,000,000 per writer (~75 writers pre-compiled)

• ~40,000 lines of (Common Lisp) code
• 15gb image when all this is loaded and running

Static Bonuses

• *writer-word-bonus*
• *common-word-bonus*
• *halo-word-bonus*
• *avoid-word-penalty*
• *synonym-proximity-bonus*
• *local-halo-bonus*
• *local-sense-bonus*
• *local-predicates-bonus*

Dynamic Bonus Types

• general constraint
• echo
• rhyme
• all-rhyme
• all-echo
• all-different
• numeric-constraint
• general n-grams (4)
• writer-n-grams (4)
• personality traits (10)

Personality: Big Five

• Openness to experience
• Conscientiousness vs. Unconscientious
• Extraversion vs. Introversion
• Agreeableness vs. Disagreeable
• Emotional stability vs. Neuroticism

Personality in 100,000 Words: A large-scale analysis of personality and word use among bloggers

Tal Yarkoni University of Colorado at Boulder

Abstract

Previous studies have found systematic associations between personality and individual differences in word use. Such studies have typically focused on broad associations between major personality domains and aggregate word categories, potentially masking more specific associations. Here I report the results of a large-scale analysis of personality and word use in a large sample of blogs (N=694). The size of the dataset enabled pervasive correlations with personality to be identified for a broad range of lexical variables, including both aggregate word categories and individual English words. The results replicated category-level findings from previous offline studies, identified numerous novel associations at both a categorical and single-word level, and underscored the value of complementary approaches to the study of personality and word use. People differ considerably from each other in their habitual patterns of thought, feeling and

• action. Not surprisingly, these differences are reflected not only in what people think, feel, and

do, but also in what they say about what they think, feel, or do. Recent studies have identified systematic associations between personality and language use in a variety of different contexts,

NIH Public Access

Author Manuscript

J Res Pers. Author manuscript; available in PMC 2011 June 1.

Published in final edited form as: J Res Pers. 2010 June 1; 44(3): 363–373. doi:10.1016/j.jrp.2010.04.001.

NIH-PA Author Manuscript NIH-PA Author Manuscript

Sentiment Analysis

Linguistic Inquiry and Word Count

1 All pronouns 18 Anger 35 Family 52 Home 2 1st person singular 19 Sadness 36 Humans 53 Sport/exercise 3 1st person plural 20 Cognition 37 Time 54 TV/movies 4 Total 1st person 21 Cause@Causation 38 Past 55 Music 5 Total 2nd person 22 Insight 39 Present 56 Money 6 Total 3rd person 23 Discrepancy 40 Future 57 Metaphysical 7 Negations 24 Inhibition 41 Space 58 Religion 8 Assents 25 Tentativeness 42 Up 59 Death 9 Articles 26 Certainty 43 Down 60 Physical states/factors 10 Prepositions 27 Sensation/perception 44 Inclusion 61 Symptoms & sensations 11 Numbers 28 Seeing 45 Exclusion 62 Sexual 12 Affect 29 Hearing 46 Motion 63 Eating/drinking 13 Positive affect 30 Touching 47 Occupation 64 Sleeping/dreaming 14 Positive feelings 31 Social 48 School 65 Grooming 15 Optimism 32 Communication 49 Job 66 Swear words 16 Negative affect 33 Reference to others 50 Achievement 67 Non-fluencies 17 anxiety 34 Friends 51 Leisure 68 Fillers

Tr =

n

X

1

YiPi

• Scan text, count instances of categories
• Pi is the percentage of words in category i
• Yi is the Yarkoni coefficient for category i
• n is the number of categories
• Tr is the resulting strength of trait

I (<choose> verb-emotion :+sense [like favor love]) (or (<choose> adj :+sense [happy]) (<choose> adj :+sense [sad]) (<choose> adj :+sense [angry])) (<choose> noun-animal pl :+sense [dog wolf]).

I love happy dogs. No Personality Target I love passionate bird dogs. High Extraversion: 46.15% I relish unclean housedogs. Low Openness: -54.20% I yearn for humiliated attack dogs. High Neuroticism: 32.36%

ABBREVIATION-FOR NIL ALSO-SEE NIL ANTONYM NIL ATTRIBUTE NIL BASIC-SYNS (("canis_familiaris" NOUN) ("dog" NOUN)) CAUSE NIL DERIVATIONALLY-RELATED-FORM NIL DOMAIN-OF-SYNSET-REGION NIL DOMAIN-OF-SYNSET-TOPIC NIL DOMAIN-OF-SYNSET-USAGE NIL ENTAILMENT NIL GLOSS "a member of the genus Canis (probably descended from the common wolf) that has been domesticated by man since prehistoric times; occurs in many breeds; ‘the dog barked all night’ " GLOSS-WORDS ("breed" "many" "in" "occur" "time" "prehistoric" "man" "by" "domesticate" "domesticated" “be" "have" "wolf" "common" "descend" "probably" "canis" "genus" "member" "a") HYPERNYM (("domestic_animal" NOUN 1317541) ("domesticated_animal" NOUN 1317541) ("canine" NOUN 2083346) ("canid" NOUN 2083346)) HYPERNYM-CHAIN ("domestic_dog" "domestic" "dog" "physical_entity" "entity" "physical_object" "object" "whole" "animate_thing" "thing" "being" "domesticated_animal" "carnivore" "chordate" "vertebrate" "mammalian" "eutherian" "canine" "animal") HYPONYM (("puppy" NOUN 1322604) ("bow-wow" NOUN 2084732) ("barker" NOUN 2084732) ("doggy" NOUN 2084732) ("doggie" NOUN 2084732) ("pooch" NOUN 2084732) ("mutt" NOUN 2084861) ("mongrel" NOUN 2084861) ("cur" NOUN 2084861) ("lapdog" NOUN 2085272) ("toy" NOUN 2085374) ("toy_dog" NOUN 2085374) ("hunting_dog" NOUN 2087122) ("working_dog" NOUN 2103406) ("carriage_dog" NOUN 2110341) ("coach_dog" NOUN 2110341) ("dalmatian" NOUN 2110341) ("basenji" NOUN 2110806) ("pug-dog" NOUN 2110958) ("pug" NOUN 2110958) ("leonberg" NOUN 2111129) ("newfoundland_dog" NOUN 2111277) ("newfoundland" NOUN 2111277) ("great_pyrenees" NOUN 2111500) ("spitz" NOUN 2111626) ("belgian_griffon" NOUN 2112497) ("brussels_griffon" NOUN 2112497) ("griffon" NOUN 2112497) ("welsh_corgi" NOUN 2112826) ("corgi" NOUN 2112826) ("poodle_dog" NOUN 2113335) ("poodle" NOUN 2113335) ("mexican_hairless" NOUN 2113978))

WordNet

INSTANCE-HYPERNYM NIL INSTANCE-HYPONYM NIL MEMBER-HOLONYM (("genus_canis" NOUN 2083863) ("canis" NOUN 2083863) ("pack" NOUN 7994941)) MEMBER-MERONYM NIL MEMBER-OF-THIS-DOMAIN-REGION NIL MEMBER-OF-THIS-DOMAIN-TOPIC NIL MEMBER-OF-THIS-DOMAIN-USAGE NIL ORDER 1 ORIGINAL-WORD "domestic_dog" PART-HOLONYM NIL PART-MERONYM (("flag" NOUN 2158846)) PARTICIPLE-OF-VERB NIL PERTAINYM-PERTAINS-TO-NOUN NIL POINTER-SYNS NIL PRIMARY-SYNONYMS ("genus_canis" "canis" "pack" "flag" "domestic_animal" "domesticated_animal" "canine" "canid" "puppy" "bow-wow" "barker" "doggy" "doggie" "pooch" "mutt" "mongrel" "cur" "lapdog" "toy" "toy_dog" "hunting_dog" "working_dog" "carriage_dog" "coach_dog" "dalmatian" "basenji" "pug-dog" "pug" "leonberg" "newfoundland_dog" "newfoundland" "great_pyrenees" "spitz" "belgian_griffon" "brussels_griffon" "griffon" "welsh_corgi" "corgi" "poodle_dog" "poodle" "mexican_hairless" "canis_familiaris" "dog" "domestic_dog") RELATED-TERM NIL SEMANTIC-TYPE NOUN-ANIMAL SENSE-DATA NIL SIMILAR-TO NIL SUBSTANCE-HOLONYM NIL SUBSTANCE-MERONYM NIL SYNSET-ID (2084071 NOUN) TYPE NOUN VERB-GROUP NIL WORD "domestic_dog" WORD-SENSE "domestic_dog%1"

WordNet

Weird WordNet Entries

• hypernym: more general


(hypernym(“tent”) = “shelter”)

• hyponym: more specific, inverse of above
• instance-hyponym: specific example


(instance-hyponym(“river”) = “Mississippi River”)

• instance-hypernym: inverse of above


(instance-hypernym(“Mississippi River”) =

Weird WordNet Entries

• holonym: whole that contains the specified part

(part-holonym(“fuselage”) =“airplane”)

• meronym: inverse of above

CMU Phonetic Dictionary

"fiction" (((F) (IH 1) (K) (SH) (AH 0) (N))) "fictional" (((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L))) "fictional_animal" (((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L) (AE 1) (N) (AH 0) (M) (AH 0) (L))) "fictional_character" (((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L) (K) (EH 1) (R) (IH 0) (K) (T) (ER 0))) "fictionalize" (((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L) (AY 2) (Z))) "fictionalized" (((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L) (AY 2) (Z) (D))) "fictions" (((F) (IH 1) (K) (SH) (AH 0) (N) (Z))) "fictitious" (((F) (IH 0) (K) (T) (IH 1) (SH) (AH 0) (S))) "fictitious_character" (((F) (IH 0) (K) (T) (IH 1) (SH) (AH 0) (S) (K) (EH 1) (R) (IH 0) (K) (T) (ER 0))) "fictitious_name" (((F) (IH 0) (K) (T) (IH 1) (SH) (AH 0) (S) (N) (EY 1) (M))) "fictitious_place" (((F) (IH 0) (K) (T) (IH 1) (SH) (AH 0) (S) (P) (L) (EY 1) (S))) "fictitiously" (((F) (IH 0) (K) (T) (IH 1) (SH) (AH 0) (S) (L) (AY 1))) "ficus" (((F) (IY 1) (S) (IY 1) (Y) (UW 1) (EH 1) (S)) ((F) (IY 1) (K) (AH 1) (S)) ((F) (AY 1) (S) (IY 1) (Y) (UW 1) (EH 1) (S)) ((F) (AY 1) (K) (AH 1) (S)))

(IH 1) = (<sound> <stress>)

Algorithmic Rhyming

• rhyme computation for words and phrases
• how much do vowels and consonants

contribute to rhyme?

• how much do early syllables in a word or

phrase contribute to rhyminess?

Vowels Rhyme This Much

[AA, AO]: 0.5 [AE, AH]: 0.5 [AA, AW]: 0.4 [AH, EH]: 0.35 [AH, AO]: 0.35 [AA, AH]: 0.3 [AE, EH]: 0.3 [AA, AE]: 0.3 [AH, IH]: 0.25 [AH, UH]: 0.25 [AH, AW]: 0.2 [AA, EH]: 0.2 [AY, EY]: 0.2 [OW, UW]: 0.2 [AE, IH]: 0.2 [EH, IH]: 0.2 [IH, UH]: 0.2 [UH, UW]:0.15 [AA, IH]: 0.15 [AO, UH]: 0.15 [AA, OW]:0.15 [AH, OW]: 0.13 [AO, AW]:0.1 [EH, UW]:0.1 [AE, AO]: 0.1

Consonants Rhyme This Much

[G, K]: 0.97 [CH, JH]: 0.95 [F, V]: 0.95 [DH, TH]: 0.95 [SH, ZH]: 0.9 [B, P]: 0.9 [S, Z]: 0.9 [N, NG]: 0.7 [G, T]: 0.6 [D, P]: 0.6 [D, T]: 0.6 [B, K]: 0.6 [B, G]: 0.6 [K, P]: 0.6 [K, T]: 0.6 [P, T]: 0.6 [D, K]: 0.6 [D, G]: 0.6 [B, D]: 0.6 [B, T]: 0.6 [G, P]: 0.6 [M, N]: 0.4 [M, NG]: 0.4 [L, R]: 0.4 [F, S]: 0.2 [F, TH]: 0.2 [S, TH]: 0.2 [SH, TH]: 0.2 [TH, ZH]: 0.2 [DH, ZH]: 0.2 [V, ZH]: 0.2 [TH, Z]: 0.2 [F, ZH]: 0.2 [DH, Z]: 0.2 [DH, SH]: 0.2 [TH, V]: 0.2 [S, ZH]: 0.2 [DH, V]: 0.2 [V, Z]: 0.2 [F, Z]: 0.2 [DH, F]: 0.2 [F, SH]: 0.2 [DH, S]: 0.2 [SH, Z]: 0.2 [S, SH]: 0.2 [S, V]: 0.2 [SH, V]: 0.2 [Z, ZH]: 0.2 [W, Y]: 0.1

fictional / critical

• get phonetic spelling for each word
• scan from back to front
• as you scan left, reduce the strength of possible

rhymes

• syllables near the front of words count less

fictional / critical

• compare rhyminess phoneme by phoneme
• vowel/vowel: lookup rhyminess, count similarity of

stresses

• consonant/consonant: lookup rhyminess
• vowel/consonant: realign and compute offset

distance

• when one word ends, compute how many

phonemes are left in the other word

fictional / critical

• compute a complicated expression that takes

into account

• how many opportunities there were to compare

sounds (phoneme alignments)

• how much those opportunities sounded alike
• how well the stresses lined up
• how many offsets were required to align the words
• how much final consonants sounded alike (ends of

words)

✓ M · .98|F | · 2V (p1 + p2) · 2S (y1 + y2) ◆1.1

• M is the rhyminess of the last consonant
• F is the number of offsets needed to align the words
• V is the total amount of overlap (phonemes that lined up)
• pi is the number of phonemes in wordi
• S is the stress similarity
• yi is the number of syllables in wordi

((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L)) ((K) (R) (IH 1) (T) (IH 0) (K) (AH 0) (L)

• L/L: similarity 1.0
• (AH 0)/(AH 0): similarity 1.0, discounted to .9
• N/K: similarity 0.0
• (AH 0)/(IH 0): similarity 0.25, discounted to 0.18
• K-SH/T: similarity 0.12, discounted to 0.08
• (IH 1)/(IH 1): similarity 1.0, discounted to 0.6
• F/K-R: similarity 0.0

((F) (IH 1) (K) (SH) (AH 0) (N) (AH 0) (L)) ((K) (R) (IH 1) (T) (IH 0) (K) (AH 0) (L)

• offsets: 2
• comparable phonemes w/discounting: 2.75
• stress similarity: 3.0
• leftover phonemes: 0
• result = 50%

Rhyme Cache

"$boatspot: 0.5924662 "$chipwhip: 0.67664785 "'draw_upfuckup: 0.6016158 "&bundletrouble: 0.7353128 "%brookprick: 0.7495342 "$tripskip: 0.6957108 "%stompslip: 0.5133457

clever representation to speed up hashing

Echoes

• counts the number common sounds, weighted by

their sonic similarity

• takes int0 account similar ordering of common

sounds—how close do the words come to rhyming

• echo scores are larger than rhyme scores (because
• f ordering in rhymes); echo and rhyme scores are

not commensurable

• “fictional” and “critical” echo this much: 70%

Echo Cache

"$paleplague: 0.9090182 "$sortwrought: 0.9025195 ")propheticdecrepit: 0.91340137 "$deemmeat: 0.9029019 "+neighboringtapering: 0.9001467 "%wholehollow: 0.9090182 "(skeletalselect: 0.9000825 "'presentpristine: 0.9177177 "'load_uphold_up: 0.94193936 "'destinediagnose: 0.90495605 "'presentresident: 0.92621255

Best Rhymes in King James for “programming”

• protesting (64%)
• the crackling (54%)
• no reckoning (54%)

Notable Echoes of “computer programmer”

• provoked me to anger (King James Bible)
• most persecuted by man (Origin of Species, Darwin)
• compound for grey amber (Moby Dick, Melville)
• come from yond poor girl (Sonnets & Plays,

Shakespeare)

• program a computer (Patterns of Software, rpg)

What is an N-Gram?

are huge and 0.14455404

• ne copy of

0.380291 sooner rather than 0.3726525 was wrong and 0.32407436 be candid with 0.12155247 decided to sleep 0.12155247 had appeared as 0.20447502 up the remnants 0.11795887 its opinion the 0.121112496 answer is absolutely 0.1 which are irrelevant 0.122132495

• f bare ground

0.10501691

n-Grams

"$!\"!iamajournalist": #(("$!\"!iamajournalist" . 0.146445)) "$!\"!iamalawyer": #(("$!\"!iamalawyer" . 0.166102)) "$!\"!iamaliber": #(("$!\"!iamaliberal" . 0.107989)) "$!\"!iamalifelong": #(("$!\"!iamalifelong" . 0.122386)) "$!\"!iamamarri": #(("$!\"!iamamarried" . 0.104837)) "$!\"!iamaperson": #(("$!\"!iamaperson" . 0.238564))

Counting 2-Grams

[Most of] [of the] [the big] [big shore] [shore places] [places were] [were closed] [closed now] [now and] [and there] [there were] [were hardly] [hardly any] [any lights] [lights except] [except the] [the shadowy] [shadowy moving] [moving glow] [glow of] [of a] [a ferryboat] [ferryboat across] [across the] [the Sound] [Sound And] [And as] [as the] [the moon] [moon rose] [rose higher] [higher the] [the inessential] [inessential houses] [houses began] [began to] [to melt] [melt away] [away until] [until gradually] [gradually I] [I became] [became aware] [aware of] [of the] [the

• ld] [old island] [island here] [here that] [that flowered] [flowered once]

[once for] [for Dutch] [Dutch sailors] [sailors eyes] [eyes a] [a fresh] [fresh green] [green breast] [breast of] [of the] [the new] [new world]

53/63

I (<choose> verb-emotion :+sense [like favor love]) (or (<choose> adj :+sense [happy]) (<choose> adj :+sense [sad]) (<choose> adj :+sense [angry])) (<choose> noun-animal pl :+sense [dog wolf]).

I hero-worship easygoing working dogs. High Conscientiousness: 30.67% High Music, Echoes: 300 Unusual wording Common Word Bonus: -200.0 2-Gram Bonus: -100.0 3-Gram Bonus: -100.0 4-Gram Bonus: -100.0 5-Gram Bonus: -100.0

Final Word Adjustments

• tenses, plurals, possessives, comparatives,

superlatives

• words and phrases
• lots of code
• large cache

Adjust Word Cache

("hard_to_please" ADJ (-ER)): "harder to please" ("hard_to_please" ADJ (-EST)): "hardest to please" ("hard_to_please" ADJ (CAP)): "Hard to please" ("hard_to_please" ADJ NIL): "hard to please"

(RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 128)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 137)))) 100.0) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 128)) (WORD (SENTENCE-WORD WA-WORD 119))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 128)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 119)))) 100.0) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 99)) (WORD (SENTENCE-WORD WA-WORD 75))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 99)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 75)))) 1000) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 75)) (WORD (SENTENCE-WORD WA-WORD 83))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 75)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 83)))) 100.0) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 65)) (WORD (SENTENCE-WORD WA-WORD 44))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 65)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 44)))) 1000) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 51)) (WORD (SENTENCE-WORD WA-WORD 44))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 51)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 44)))) 100.0) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 34)) (WORD (SENTENCE-WORD WA-WORD 7))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 34)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 7)))) 1000) (* (MAX (RHYME? (WORD (SENTENCE-WORD WA-WORD 25)) (WORD (SENTENCE-WORD WA-WORD 51))) (RHYME? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 25)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 51)))) 100.0))) (- 200.0 (+ (IF (STRING-DIFFERENT (WORD (SENTENCE-WORD WA-WORD 128)) (WORD (SENTENCE-WORD WA-WORD 137))) 50.0 0.0) (IF (STRING-DIFFERENT (WORD (SENTENCE-WORD WA-WORD 99)) (WORD (SENTENCE-WORD WA-WORD 75))) 50.0 0.0) (IF (STRING-DIFFERENT (WORD (SENTENCE-WORD WA-WORD 65)) (WORD (SENTENCE-WORD WA-WORD 44))) 50.0 0.0) (IF (STRING-DIFFERENT (WORD (SENTENCE-WORD WA-WORD 34)) (WORD (SENTENCE-WORD WA-WORD 7))) 50.0 0.0))) (- 200.0 (+ (* (MAX (ECHO? (WORD (SENTENCE-WORD WA-WORD 75)) (WORD (SENTENCE-WORD WA-WORD 44))) (ECHO? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 75)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 44)))) 100.0) (* (MAX (ECHO? (WORD (SENTENCE-WORD WA-WORD 44)) (WORD (SENTENCE-WORD WA-WORD 7))) (ECHO? (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 44)) (WORD-ADJUSTED-WORDS (SENTENCE-WORD WA-WORD 7)))) 100.0))) (- 100.0 (+ (* (ALL-ECHO? (STRING-APPEND (WORD (SENTENCE-WORD WA-WORD 1)) (WORD (SENTENCE-WORD WA-WORD 5)) (WORD (SENTENCE-WORD WA-WORD 7)) (WORD (SENTENCE-WORD WA-WORD 11)) (WORD (SENTENCE-WORD WA-WORD 15)) (WORD (SENTENCE-WORD WA-WORD 24)) (WORD (SENTENCE-WORD WA-WORD 25)) (WORD (SENTENCE-WORD WA-WORD 28)) (WORD (SENTENCE-WORD WA-WORD 30)) (WORD (SENTENCE-WORD WA-WORD 31)) (WORD (SENTENCE-WORD WA-WORD 34)) (WORD (SENTENCE-WORD WA-WORD 39)) (WORD (SENTENCE-WORD WA-WORD 40)) (WORD (SENTENCE-WORD WA-WORD 42)) (WORD (SENTENCE-WORD WA-WORD 47)) (WORD (SENTENCE-WORD WA-WORD 50)) (WORD (SENTENCE-WORD WA-WORD 51)) (WORD (SENTENCE-WORD WA-WORD 55)) (WORD (SENTENCE-WORD WA-WORD 57)) (WORD (SENTENCE-WORD WA-WORD 58)) (WORD (SENTENCE-WORD WA-WORD 61)) (WORD (SENTENCE-WORD WA-WORD 62)) (WORD (SENTENCE-WORD WA-WORD 72)) (WORD (SENTENCE-WORD WA-WORD 73)) (WORD (SENTENCE-WORD WA-WORD 75)) (WORD (SENTENCE-WORD WA-WORD 78)) (WORD (SENTENCE-WORD WA-WORD 83)) (WORD (SENTENCE-WORD WA-WORD 89)) (WORD (SENTENCE-WORD WA-WORD 92)) (WORD (SENTENCE-WORD WA-WORD 95))

For a Very Short Run

• optimization function invoked 200,000 times
• algorithmic rhyme invoked 3,200,000 times
• algorithmic echo invoked 181,400,000 times
• n-gram computation 400,000 times
• personality computation 1,000,000 times
• all-different 200,000 times

Performance?

• Parallel word and phrase choice
• Precompute lots of stuff
• Parallel simulated annealing
• Clever representations
• Algorithm hacking
• Big caches & lots of them
• Minimize synchronization

Parallel Word and Phrase Choice

• Obvious
• Includes parallel computation of wording

alternatives and static constraints

Parallel Simulated Annealing

• Run n independent copies of the SA engine
• Collect best from each & combine
• Not proven “correct,” but is effective

Clever Representations

length of word1 2-gram representation (e.g.) use a string= hash table indexed by stem(word1)·stem(word2) string char2word1word2 char1 number of words

Caches

• *adjustword-cache*
• *all-different-cache*
• *all-echo-cache*
• *all-rhyme-cache*
• *dynamic-2-gram-cache*
• *dynamic-3-gram-cache*
• *dynamic-4-gram-cache*
• *dynamic-5-gram-cache*
• *dynamic-writer-2-gram-cache*
• *dynamic-writer-3-gram-cache*
• *dynamic-writer-4-gram-cache*
• *dynamic-writer-5-gram-cache*
• *echo-cache*
• *marshall-alternatives-cache*
• *morphy-cache*
• *rhyme-cache*
• *rhyme-group-cache*

For rhymes, steady state is 12x improvement

Minimize Synchronization

• Each SA process fills common caches
• Hash tables are atomic, so unsynchronized

access might be nutty at times but not “wrong”—the steady state is all-reads

Compilers

• Template -> minimization function + constraints -> Lisp

code

• string patterns -> Lisp code
• Text -> writer personalities + language models (n-grams)
• LIWC phrases -> Lisp code
• constructed hash tables -> fast loadable hash tables
• touchup transformations -> Lisp code

Senses + Semantic Types

I like (<choose> noun-animal pl :+sense [dog wolf]). semantic type sense

Semantic Types

• help select synonym sets (synsets)
• used in synonym spreading
• when absent, heuristics are used to guess the

sense of a word

WordNet

dog, NOUN Senses: 1: domestic_dog, NOUN-ANIMAL: a member of the genus Canis… 2: dog, NOUN-PERSON: a dull unattractive unpleasant girl or woman… 3: dog, NOUN-PERSON: informal term for a man; "you lucky dog" 4: cad, NOUN-PERSON: someone who is morally reprehensible; "you dirty dog" 5: wiener, NOUN-FOOD: a smooth-textured sausage of minced beef or pork… 6: detent, NOUN-ARTIFACT: a hinged catch that fits into a notch… 7: dog, NOUN-ARTIFACT: metal supports for logs in a fireplace…

I like (dog noun pl)

I like detents I like franks I like clicks I like cads I like wieners I like heels I like hounds I like frankfurters I like weenies I like wienerwursts I like hotdogs I like bounders I like blackguards I like firedogs I like frumps I like andirons I like dog-irons I like pawls I like domestic dogs I like hot dogs

no semantic help

I like (dog noun-animal pl)

I like curs I like animals I like Pekes I like toys I like beasts I like creatures I like puppies I like wolves I like foxes I like barkers I like Newfoundlands I like canines I like brutes I like strays I like corgis I like lapdogs I like doggies

semantic type

Senses

• data structure consisting of words + relevances,

based on decaying synonym-network spreading

• can be used to compute semantic similarity of

words / similarity of meaning, kind of like a cosine distance

• like a magnet passed over all the words InkWell

knows—it picks up to various heights words attracted to it

arctic_wolf 0.75 canis_niger 0.75 doggy 0.75 mongrel 0.75 red_wolf 0.75 barker 0.75 canis_rufus 0.75 domestic_dog 0.75 mutt 0.75 spitz 0.75 basenji 0.75 carriage_do g 0.75 gray_wolf 0.75 newfoundland 0.75 timber_wolf 0.75 belgian_griffon 0.75 coach_dog 0.75 great_pyrenees 0.75 newfoundland _dog 0.75 toy 0.75 bow-wow 0.75 corgi 0.75 grey_wolf 0.75 pooch 0.75 toy_dog 0.75 brush_wolf 0.75 coydog 0.56 griffon 0.75 poodle 0.75 welsh_corgi 0.75 brussels_griffo n 0.75 coyote 0.75 hunting_dog 0.75 poodle_dog 0.75 white_wolf 0.75 canis_familiari s 0.75 cur 0.75 lapdog 0.75 prairie_wolf 0.75 wolf 1 canis_latrans 0.75 dalmatian 0.75 leonberg 0.75 pug 0.75 wolf_cub 0.75 canis_lupus 0.75 dog 1 maned_wolf 0.75 pug-dog 0.75 wolf_pup 0.75 canis_lupus_ tundrarum 0.75 doggie 0.75 mexican_hairles s 0.75 puppy 0.75 working_dog 0.75

I like dogs I like toys I like Newfoundlands I like huskies I like retrievers I like hounds I like cubs I like puppies I like pups I like whelps I like Canidaes I like wolfhounds I like Carnivoras I like Canises I like jackals I like curs I like Pekes I like Leonbergs I like coydogs I like Pomeranians

I like (<choose> noun-animal pl :+sense [dog wolf])

NOUN-ANIMAL: any of several breeds of very small dogs kept purely as pets NOUN-ANIMAL: offspring

• f a coyote and a dog

n-Grams

(<choose> noun-animal pl :+sense [dog wolf]) (or is are) animals. n-grams select right verb

Dogs are animals. Toys are animals. Huskies are animals. Hounds are animals. Cubs are animals. Pups are animals. Puppies are animals. Coyotes are animals.

(<choose> noun-animal pl :+sense [dog wolf]) (or is are) animals.

(in-3-grams "dogs" "are" "animals"): 0.0 (in-2-grams "dogs" "are"): 0.36829454 (in-2-grams "are" "animals"): 0.27010748 (in-3-grams "dogs" "is" "animals"): 0.0 (in-2-grams "dogs" "is"): 0.23805899 (in-2-grams "is" "animals"): 0.13000134

<null-word>

(<choose> noun-animal pl :+sense [dog wolf]) (or is are) (or a an <null-word>) animals. n-grams eliminate stupid word

Pups are animals. Dogs are animals. Coyotes are animals. Puppies are animals. Cubs are animals. Hounds are animals. Huskies are animals. Toys are animals. Wolves are animals. Foxes are animals.

(<choose> noun-animal pl :+sense [dog wolf]) (or is are) (or a an <null-word>) animals.

Text n-gram score

• Dogs are a animals: 5.11

Dogs are an animals: 5.35 Dogs is a animals: 5.99 Dogs is an animals: 6.66 Dogs is animals: 7.89 Dogs are animals: 8.79

The woods are bright, light, and high The woods are lovely, dark, and deep

Delighted, Ebullient, Ecstatic, Elated, Energetic, Enthusiastic, Euphoric, Excited, Exhilarated, Overjoyed, Thrilled, Tickled pink, Turned on, Vibrant, Zippy

Happiness Halo

Halos

The woods are hot, rough, and cold The woods are lovely, dark, and deep

Affronted, Belligerent, Bitter, Burned up, Enraged, Fuming, Furious, Heated, Incensed, Infuriated, Intense, Outraged, Provoked, Seething, Storming, Truculent, Vengeful, Vindictive, Wild

Anger Halo

Halos

• Anger.halo
• Caring.halo
• Confusion.halo
• Depression.halo
• Fear.halo
• Frost.halo
• Happiness.halo
• Hurt.halo
• Inadequateness.halo
• Loneliness.halo
• Remorse.halo

English Haiku

A haiku in English is a very short poem in the English language, following to a greater or lesser extent the form and style of the Japanese haiku. A typical haiku is a three-line, quirky observation about a fleeting moment involving nature.

–Wikipedia

Base Senses

• flower-sense-base: [flower red pink white blue]

noun

• horse-sense-base: [horse pony] noun
• road-sense-base: [road street trail highway] noun
• eating-sense-base: [eat chew bite] verb

Compressed Templates

(make-full-haiku '(as for the (flower-plant-sense noun-plant) (return) (preposition) the (road-sense noun-artifact) (hyphen) (return) my (horse-sense noun-animal ([horse pony] noun)) (eating-sense verb-consumption nil past) it))

as for the orange upon the scene— my dog ate it

Making a Haiku

• choose a random template (including self-

haiku)

• compute senses from user-supplied text +

haiku base senses

• choose a random halo
• choose random InkWell parameters modulo

avoid-words and n-grams

• produce 20 haiku candidates
• show the one with the best n-gram score

ice river bridge snow wind cold trees

small sample from a random writer text

global sense

(make-full-haiku '(as for the (flower-plant-sense noun-plant) (return) (preposition) the (road-sense noun-artifact) (hyphen) (return) my (horse-sense noun-animal ([horse pony] noun)) (eating-sense verb-consumption nil past) it))

In Cold Blood state death penalty demanded friday first date Shakespeare (Richard III) repeat curse small time heart grossly captive honey words

Computed Senses

• flower-sense: [ice river bridge snow wind cold

trees state death penalty demanded friday first date
 flower red pink white blue] noun

• horse-sense: [ice river bridge snow wind cold

trees state death penalty demanded friday first date 
 horse pony] noun

• road-sense: [ice river bridge snow wind cold

trees state death penalty demanded friday first date 
 road street trail highway] noun

Random Parameters

• except for parameters that influence local sense

making

• all InkWell parameters are set randomly

as for the sticker in the morgue— my deathwatch employed it

Making Sense

• InkWell works “best” when it knows what you

want to mean (though craziness is good, too)

• Not solved yet (by anyone)—it’s an AI holy grail
• InkWell is getting there

Making Sense

• Parse the sentence
• Analyze which words need to make sense

together, and by how much

• Gather all possible senses
• Optimize assignment of senses to words using

SA & cosine similarity + bias toward most common

Parsing

“I like dogs.”

(root (s (np (prp i)) (vp (vbp like) (np (nns dogs))) (<period> <period>)))

Which Words Need to Jive?

dog like by 99.99% because they are right next to each other

Make Senses

instance-hypernym instance-hyponym member-holonym substance-holonym part-holonym member-meronym substance-meronym part-meronym hypernym hyponym similar-to also-see basic-syns related-term pertainym-pertains-to- noun domain-of-synset-region domain-of-synset-topic derivationally-related-form hypernym chain minus the antonyms plus a 25% dose of the gloss words

animal, canid, canine, canis, dog, domestic, domesticated_animal, domestic_animal, barker, basenji, being, belgian_griffon, bow-wow, brussels_griffon, canis_familiaris, carriage_dog, chordate, coach_dog, corgi, cur, dalmatian, doggie, doggy, domestic_dog, genus_canis, great_pyrenees, griffon, hunting_dog, lapdog, leonberg, mexican_hairless, mongrel, mutt, newfoundland, newfoundland_dog, pooch, poodle, poodle_dog, pug, pug-dog, puppy, spitz, toy, toy_dog, welsh_corgi, working_dog, animate_thing, carnivore, entity, eutherian, flag, mammalian,

• bject, pack, physical_entity, physical_object, thing, vertebrate, whole, adult, bark, breed, common, fellow, genus, male,

man, member, night, period, period_of_time, time, time_period, variety, wolf, abel, acrodont, adam, adonis, adult_male, amah, amusement_park, ancestry, angostura, angostura_bark, animal_group, animate_being, arctic_wolf, areopagite, associate, attribute, ayah, baboo, babu, bachelor, beast, beau, bey, biped, black_man, blood, bloodline, bloodstock, blood_line, board_member, boy, boyfriend, bozo, brother, bruiser, brush_wolf, brute, bull, buster, cabalist, cain, canella, canella_bark, canis_latrans, canis_lupus, canis_lupus_tundrarum, canis_niger, canis_rufus, captive, cascara, cascara_sagrada, cascarilla_bark, case, cassia_bark, castrate, cat, central_park, charter_member, chinese_cinnamon, chittam_bark, chittem_bark, cinchona, cinchona_bark, cinnamon, cinnamon_bark, clansman, clanswoman, clan_member, clip, clotheshorse, club_member, commissioner, committee_member, commons, component, component_part, conceptus, conservative, cork, councillor, council_member, cover, covering, coyote, creature, creepy-crawly, crepuscle, crepuscule, critter, cry, dandy, dark, darkness, darter, derivation, descent, divorced_man, domestic_help, dude, dusk, ectotherm, ejaculator, eleuthera_bark, embryo, esq, esquire, eunuch, evenfall, ex, ex-boyfriend, ex-husband, example, experience, fall, fashion_plate, father-figure, father_figure, father_surrogate, fauna, feeder, fellow_member, female, fertilized_egg, fictional_animal, filiation, foot_soldier, fop, form, funfair, gallant, galoot, game, geezer, gentleman, giant, gloam, gloaming, golden_boy, grass_widower, graybeard, gray_wolf, green, greybeard, grey_wolf, grownup, guy, ham, he-man, herbivore, herr, hexapod, hombre, homeboy, homegirl, homeotherm, home_help, homoiotherm, homotherm, hooray_henry, housefather, housekeeper, housemaid, house_servant, huddler, hunk, inamorato, individual, inductee, insectivore, instance, instant, invertebrate, ironman, ironside, iron_man, japheth, jesuit's_bark, joiner, kibbutznik, kind, kolkhoznik, larva, line, lineage, line_of_descent, lover, macho-man, magnolia, maid, maidservant, male_person, mammal_genus, maned_wolf, marine_animal, marine_creature, mate, metazoan, methuselah, mezereum, middle-aged_man, migrator, minute, molter, moment, monsieur, mortal, moulter, mutant, natural_covering, nightfall, nighttime, noise, offspring, old_boy,

• ld_man, omnivore, organism, origin, parcel, parcel_of_land, parentage, park, paterfamilias, patriarch, pedigree, peeper,

person, peruvian_bark, pest, pet, peter_pan, phellem, philanderer, piece_of_ground, piece_of_land, pleasure_ground, pledge, pleurodont, poikilotherm, ponce, portion, posseman, prairie_wolf, predator, predatory_animal, prey, pureblood, purebred, quarry, racer, range_animal, red_wolf, retainer, rosicrucian, rotarian, samson, scavenger, sea_animal, sea_creature, second, senhor, servant, seth, shaver, sheik, shem, signior, signor, signore, sir, sister, skivvy, slavey, social_unit, sodalist, sort, soul, stayer, stemma, stiff, stock, strain, strapper, stud, stunt, subordinate, subsidiary, survivor, swain, sweetwood_bark, swell, tanbark, tapa, tapa_bark, tappa, tappa_bark, tarzan, taxon, taxonomic_category, taxonomic_group, thoroughbred, timber_wolf, time_unit, tract, tribesman, twilight, underling, unit, unit_of_time, unmarried_man, varment, varmint, village_green, wedding_night, weeknight, white_cinnamon, white_man, white_wolf, widower, widowman, winter's_bark, wolf_cub, wolf_pup, womaniser, womanizer, wonder_boy, work_animal, yellow_man,

Optimize Assignments

• care {like} [VERB-EMOTION:1]: prefer or wish

to do something; “Do you care to try this dish?”; “Would you like to come along to the movies?”

• domestic_dog {dog} [NOUN-ANIMAL:1]: a

member of the genus Canis (probably descended from the common wolf) that has been domesticated by man since prehistoric times; occurs in many breeds; “the dog barked all night”

“Dogs bark.”

1: bark, VERB-COMMUNICATION: speak in an unfriendly tone; “She barked into the dictaphone” 2: bark, VERB-CONTACT: cover with bark 3: bark, VERB-CONTACT: remove the bark of a tree 4: bark, VERB-COMMUNICATION: make barking sounds; “The dogs barked at the stranger” 5: bark, VERB-CHANGE: tan (a skin) with bark tannins

bark, Verb Senses:

“Dogs bark.”

• domestic_dog {dog} [NOUN-ANIMAL:1]: a

member of the genus Canis (probably descended from the common wolf) that has been domesticated by man since prehistoric times; occurs in many breeds; “the dog barked all night”

• bark {bark} [VERB-COMMUNICATION:4]: make

barking sounds; “The dogs barked at the stranger”

“I like dogs with bread and ketchup.”

• like

dog bread ketchup like

• dog

0.95

• bread

0.69833726 0.85737497

• ketchup

0.46329114 0.69833726 0.95

• care {like} [VERB-EMOTION:1]: prefer or wish

to do something;

• wiener {dog} [NOUN-FOOD:5]: a smooth-

textured sausage of minced beef or pork usually smoked; often served on a bread roll

• staff_of_life {bread} [NOUN-FOOD:1]: food

made from dough of flour or meal and usually raised with yeast or baking powder and then baked

• cetchup {ketchup} [NOUN-FOOD:1]: thick spicy

sauce made from tomatoes

Google Translate Fails

• Je aime les chiens avec du pain et du

ketchup.

• Me gustan los perros con pan y salsa

de tomate.

• Ich mag Hunde mit Brot und Ketchup.
• I favor woofers with damper and dead

horse.

• Sense is not easily machine learned

“I like dogs with bread and ketchup.”

“terse condensations” “evocative” “took the top of my head off” “funny and profound” “natural, personal, and rhythmic” “compact fluid energy” “wry and elliptical” “whimsical elegance”

“wow” “combines ideas beautifully” “very cool” “everything works very effectively” “yes very subtle” “playful” “fantastic” “wonderful” “taught something, changed something” “wonderful humor” “there is whimsy in these” “surprising language” “ominous and pretty wonderful too”

“powerful image—large and small at the same time” “like a war going on between the two sides of the brain, but the same brain” “amazing variety—funny, serious, simple, complex, philosophical, plainspoken; language, words, and phrases never heard before

the powerful head designates its powerful head to support cognition parted in the middle— the authority of the air conditioner perfection in the brightness this grave— no one sees it mortality, mortality

a few days— by myself, browsing guitar-shaped coloring the hostile defense leads its problematic rear, the rear of frustration rural signal, cannot understand Oregon —agricultural

a reasonable assumption— by myself, sampling in chocolate the maiden condominium

• pens its award-winning gametocyte

in the control room of the banquet

an immature animal or plant cell that develops into a gamete by meiosis

many darks in the cream and not dead yet— the end of season an on-the-far-side summer night— whipping up high tea, we stripped pickles

deep in the dark— the power of snow walking in the deepness

–InkWell, December 2014

Richard P. Gabriel

Writing a Writer

All is riddle

–Ralph Waldo Emerson

All is riddle and the key to a riddle is another riddle All is riddle and the key to a riddle