![Page 2: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/2.jpg)
Natural Language Processing:• Let’s start with some classic examples:
• Eliza (Weizenbaum, 1966)• Example implementation: http://www.masswerk.at/elizabot/
• SHRDLU (Winograd, 1970)• http://hci.stanford.edu/~winograd/shrdlu/
![Page 3: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/3.jpg)
Natural Language Processing• SHRDLU is quite impressive for being form the late 60s
• So, is NLP solved nowadays? (after more than 40 years!)
![Page 4: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/4.jpg)
Natural Language Processing• SHRDLU is quite impressive for being form the late 60s
• So, is NLP solved nowadays? (after more than 40 years!)• Not at all!
• But SHRDLU worked pretty well, can we just not apply the algorithms in SHRDLU to other domains and be done?
![Page 5: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/5.jpg)
Natural Language Processing• SHRDLU is quite impressive for being form the late 60s
• So, is NLP solved nowadays? (after more than 40 years!)• Not at all!
• But SHRDLU worked pretty well, can we just not apply the algorithms in SHRDLU to other domains and be done?• SHRDLU worked on a “micro-world”, which masks most of the hard
problems in NLP (ambiguity, metaphor, noncompositionality, etc.)• Efforts to scale SHRDLU to larder domains have consistently failed.
For example, one of the best known examples is CyC (Lenat, 1984 - 2013)
![Page 6: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/6.jpg)
Outline
♦ Communication
♦ Grammar
♦ Syntactic analysis
♦ Problems
Chapter 22 2
![Page 7: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/7.jpg)
Communication
“Classical” view (pre-1953):language consists of sentences that are true/false (cf. logic)
“Modern” view (post-1953):language is a form of action
Wittgenstein (1953) Philosophical InvestigationsAustin (1962) How to Do Things with WordsSearle (1969) Speech Acts
Why?
Chapter 22 3
![Page 8: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/8.jpg)
Communication
“Classical” view (pre-1953):language consists of sentences that are true/false (cf. logic)
“Modern” view (post-1953):language is a form of action
Wittgenstein (1953) Philosophical InvestigationsAustin (1962) How to Do Things with WordsSearle (1969) Speech Acts
Why?
Chapter 22 4
![Page 9: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/9.jpg)
Communication
“Classical” view (pre-1953):language consists of sentences that are true/false (cf. logic)
“Modern” view (post-1953):language is a form of action
Wittgenstein (1953) Philosophical InvestigationsAustin (1962) How to Do Things with WordsSearle (1969) Speech Acts
Why?
Chapter 22 5
![Page 10: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/10.jpg)
Communication
“Classical” view (pre-1953):language consists of sentences that are true/false (cf. logic)
“Modern” view (post-1953):language is a form of action
Wittgenstein (1953) Philosophical InvestigationsAustin (1962) How to Do Things with WordsSearle (1969) Speech Acts
Why?
To change the actions of other agents
Chapter 22 6
![Page 11: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/11.jpg)
Speech acts
SITUATION
Speaker Utterance Hearer
Speech acts achieve the speaker’s goals:Inform “There’s a pit in front of you”Query “Can you see the gold?”Command “Pick it up”Promise “I’ll share the gold with you”Acknowledge “OK”
Speech act planning requires knowledge of– Situation– Semantic and syntactic conventions– Hearer’s goals, knowledge base, and rationality
Chapter 22 7
![Page 12: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/12.jpg)
Stages in communication (informing)
Intention S wants to inform H that PGeneration S selects words W to express P in context CSynthesis S utters words W
Perception H perceives W ′ in context C ′
Analysis H infers possible meanings P1, . . . Pn
Disambiguation H infers intended meaning Pi
Incorporation H incorporates Pi into KB
How could this go wrong?
Chapter 22 8
![Page 13: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/13.jpg)
Stages in communication (informing)
Intention S wants to inform H that PGeneration S selects words W to express P in context CSynthesis S utters words W
Perception H perceives W ′ in context C ′
Analysis H infers possible meanings P1, . . . Pn
Disambiguation H infers intended meaning Pi
Incorporation H incorporates Pi into KB
How could this go wrong?– Insincerity (S doesn’t believe P )– Speech wreck ignition failure– Ambiguous utterance– Differing understanding of current context (C ̸= C ′)
Chapter 22 9
![Page 14: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/14.jpg)
Grammar
Vervet monkeys, antelopes etc. use isolated symbols for sentences⇒ restricted set of communicable propositions, no generative capacity
(Chomsky (1957): Syntactic Structures)
Grammar specifies the compositional structure of complex messagese.g., speech (linear), text (linear), music (two-dimensional)
A formal language is a set of strings of terminal symbols
Each string in the language can be analyzed/generated by the grammar
The grammar is a set of rewrite rules, e.g.,
S → NP VPArticle → the | a | an | . . .
Here S is the sentence symbol, NP and VP are nonterminals
Chapter 22 10
![Page 15: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/15.jpg)
Grammar types
Regular: nonterminal → terminal[nonterminal ]
S → aSS → Λ
Context-free: nonterminal → anything
S → aSb
Context-sensitive: more nonterminals on right-hand side
ASB → AAaBB
Recursively enumerable: no constraints
Related to Post systems and Kleene systems of rewrite rules
Natural languages probably context-free, parsable in real time!
Chapter 22 11
![Page 16: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/16.jpg)
Wumpus lexicon
Noun → stench | breeze | glitter | nothing
| wumpus | pit | pits | gold | east | . . .
Verb → is | see | smell | shoot | feel | stinks
| go | grab | carry | kill | turn | . . .
Adjective → right | left | east | south | back | smelly | . . .
Adverb → here | there | nearby | ahead
| right | left | east | south | back | . . .
Pronoun → me | you | I | it | . . .
Name → John | Mary | Boston | UCB | PAJC | . . .
Article → the | a | an | . . .
Preposition → to | in | on | near | . . .
Conjunction → and | or | but | . . .
Digit → 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9
Divided into closed and open classes
Chapter 22 12
![Page 17: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/17.jpg)
Wumpus grammarS → NP VP I + feel a breeze
| S Conjunction S I feel a breeze + and + I smell a wumpus
NP → Pronoun I| Noun pits| Article Noun the + wumpus| Digit Digit 3 4| NP PP the wumpus + to the east| NP RelClause the wumpus + that is smelly
VP → Verb stinks| VP NP feel + a breeze| VP Adjective is + smelly| VP PP turn + to the east| VP Adverb go + ahead
PP → Preposition NP to + the eastRelClause → that VP that + is smelly
Chapter 22 14
![Page 18: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/18.jpg)
Grammaticality judgements
Formal language L1 may differ from natural language L2
L1 L2false positives
false negatives
Adjusting L1 to agree with L2 is a learning problem!
* the gold grab the wumpus* I smell the wumpus the gold
I give the wumpus the gold* I donate the wumpus the gold
Intersubjective agreement somewhat reliable, independent of semantics!Real grammars 10–500 pages, insufficient even for “proper” English
Chapter 22 15
![Page 19: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/19.jpg)
Parse trees
Exhibit the grammatical structure of a sentence
I shoot the wumpus
Chapter 22 16
![Page 20: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/20.jpg)
Parse trees
Exhibit the grammatical structure of a sentence
I shoot the wumpus
Pronoun Verb Article Noun
Chapter 22 17
![Page 21: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/21.jpg)
Parse trees
Exhibit the grammatical structure of a sentence
I shoot the wumpus
Pronoun Verb Article Noun
NP VP NP
Chapter 22 18
![Page 22: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/22.jpg)
Parse trees
Exhibit the grammatical structure of a sentence
I shoot the wumpus
Pronoun Verb Article Noun
NP VP NP
VP
Chapter 22 19
![Page 23: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/23.jpg)
Parse trees
Exhibit the grammatical structure of a sentence
I shoot the wumpus
Pronoun Verb Article Noun
NP VP NP
VP
S
Chapter 22 20
![Page 24: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/24.jpg)
Syntax in NLP
Most view syntactic structure as an essential step towards meaning;“Mary hit John” ̸= “John hit Mary”
“And since I was not informed—as a matter of fact, since I did not knowthat there were excess funds until we, ourselves, in that checkup after thewhole thing blew up, and that was, if you’ll remember, that was the incidentin which the attorney general came to me and told me that he had seen amemo that indicated that there were no more funds.”
Chapter 22 21
![Page 25: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/25.jpg)
Syntax in NLP
Most view syntactic structure as an essential step towards meaning;“Mary hit John” ̸= “John hit Mary”
“And since I was not informed—as a matter of fact, since I did not knowthat there were excess funds until we, ourselves, in that checkup after thewhole thing blew up, and that was, if you’ll remember, that was the incidentin which the attorney general came to me and told me that he had seen amemo that indicated that there were no more funds.”
“Wouldn’t the sentence ’I want to put a hyphen between the words Fishand And and And and Chips in my Fish-And-Chips sign’ have been clearerif quotation marks had been placed before Fish, and between Fish and and,and and and And, and And and and, and and and And, and And and and,and and and Chips, as well as after Chips?”
Chapter 22 22
![Page 26: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/26.jpg)
Logical grammars
BNF notation for grammars too restrictive:– difficult to add “side conditions” (number agreement, etc.)– difficult to connect syntax to semantics
Idea: express grammar rules as logic
X → YZ becomes Y (s1) ∧ Z(s2) ⇒ X(Append(s1, s2))X → word becomes X([“word”])X → Y | Z becomes Y (s) ⇒ X(s) Z(s) ⇒ X(s)
Here, X(s) means that string s can be interpreted as an X
Chapter 22 24
![Page 27: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/27.jpg)
Logical grammars contd.
Now it’s easy to augment the rules
NP (s1) ∧ EatsBreakfast(Ref(s1)) ∧ V P (s2)
⇒ NP (Append(s1, [“who”], s2))
NP (s1) ∧ Number(s1, n) ∧ V P (s2) ∧ Number(s2, n)
⇒ S(Append(s1, s2))
Parsing is reduced to logical inference:Ask(KB, S([“I” “am” “a” “wumpus”]))
(Can add extra arguments to return the parse structure, semantics)
Generation simply requires a query with uninstantiated variables:Ask(KB, S(x))
If we add arguments to nonterminals to construct sentence semantics, NLPgeneration can be done from a given logical sentence:
Ask(KB, S(x,At(Robot, [1, 1]))
Chapter 22 25
![Page 28: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/28.jpg)
Real language
Real human languages provide many problems for NLP:
♦ ambiguity
♦ anaphora
♦ indexicality
♦ vagueness
♦ discourse structure
♦ metonymy
♦ metaphor
♦ noncompositionality
Chapter 22 26
![Page 29: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/29.jpg)
Ambiguity
Squad helps dog bite victim
Chapter 22 27
![Page 30: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/30.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human flies
Chapter 22 28
![Page 31: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/31.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up Germans
Chapter 22 29
![Page 32: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/32.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
Chapter 22 30
![Page 33: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/33.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
salad
Chapter 22 31
![Page 34: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/34.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
saladabandon
Chapter 22 32
![Page 35: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/35.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
saladabandona fork
Chapter 22 33
![Page 36: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/36.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
saladabandona forka friend
Chapter 22 34
![Page 37: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/37.jpg)
Ambiguity
Squad helps dog bite victimHelicopter powered by human fliesAmerican pushes bottle up GermansI ate spaghetti with meatballs
saladabandona forka friend
Ambiguity can be lexical (polysemy), syntactic, semantic, referential
Chapter 22 35
![Page 38: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/38.jpg)
Anaphora
Using pronouns to refer back to entities already introduced in the text
After Mary proposed to John, they found a preacher and got married.
Chapter 22 36
![Page 39: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/39.jpg)
Anaphora
Using pronouns to refer back to entities already introduced in the text
After Mary proposed to John, they found a preacher and got married.
For the honeymoon, they went to Hawaii
Chapter 22 37
![Page 40: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/40.jpg)
Anaphora
Using pronouns to refer back to entities already introduced in the text
After Mary proposed to John, they found a preacher and got married.
For the honeymoon, they went to Hawaii
Mary saw a ring through the window and asked John for it
Chapter 22 38
![Page 41: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/41.jpg)
Anaphora
Using pronouns to refer back to entities already introduced in the text
After Mary proposed to John, they found a preacher and got married.
For the honeymoon, they went to Hawaii
Mary saw a ring through the window and asked John for it
Mary threw a rock at the window and broke it
Chapter 22 39
![Page 42: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/42.jpg)
Indexicality
Indexical sentences refer to utterance situation (place, time, S/H, etc.)
I am over here
Why did you do that?
Chapter 22 40
![Page 43: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/43.jpg)
Metonymy
Using one noun phrase to stand for another
I’ve read Shakespeare
Chrysler announced record profits
The ham sandwich on Table 4 wants another beer
Chapter 22 41
![Page 44: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/44.jpg)
Metaphor
“Non-literal” usage of words and phrases, often systematic:
I’ve tried killing the process but it won’t die. Its parent keeps it alive.
Chapter 22 42
![Page 45: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/45.jpg)
Noncompositionality
basketball shoes
Chapter 22 43
![Page 46: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/46.jpg)
Noncompositionality
basketball shoesbaby shoes
Chapter 22 44
![Page 47: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/47.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoes
Chapter 22 45
![Page 48: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/48.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoes
Chapter 22 46
![Page 49: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/49.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
Chapter 22 47
![Page 50: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/50.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red book
Chapter 22 48
![Page 51: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/51.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred pen
Chapter 22 49
![Page 52: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/52.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hair
Chapter 22 50
![Page 53: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/53.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
Chapter 22 51
![Page 54: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/54.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moon
Chapter 22 52
![Page 55: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/55.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moonlarge molecule
Chapter 22 53
![Page 56: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/56.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moonlarge moleculemere child
Chapter 22 54
![Page 57: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/57.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moonlarge moleculemere childalleged murderer
Chapter 22 55
![Page 58: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/58.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moonlarge moleculemere childalleged murdererreal leather
Chapter 22 56
![Page 59: CS 380: ARTIFICIAL INTELLIGENCE NATURAL LANGUAGEsanti/teaching/2017/CS380/CS... · 2017-11-17 · Natural Language Processing • SHRDLU is quite impressive for being form the late](https://reader033.vdocument.in/reader033/viewer/2022050217/5f62eb6d125da70c025cbde9/html5/thumbnails/59.jpg)
Noncompositionality
basketball shoesbaby shoesalligator shoesdesigner shoesbrake shoes
red bookred penred hairred herring
small moonlarge moleculemere childalleged murdererreal leatherartificial grass
Chapter 22 57