Mova0.5 pre-release⌕

☰

home / corpora / questions / AI / What is AI? Pattern-guessers, not people / t5

Test 5 · What is AI? Pattern-guessers, not people

Chloe's teacher holds up a ginger fluffy cushion and the app says "cat". What should the class learn?

Mova's choice: option 1 · The right answer: option 3 · wrong ✗ · Who acts: teacher, app, class · What happens: hold up, say, learn · To what, where: ginger fluffy cushion, cat · Speech: someone speaks here

This is test 5 of lesson 1 «What is AI? Pattern-guessers, not people» of the AI course of Mova's primary school. The page gives the question's syntax tree — a dependency tree in the style of Universal Dependencies — and its pragmatics clause by clause, then the 4 options as the student saw them, each with its tree and pragmatics. Every text is parsed by Mova itself. How the student answered it, with the score of every option and why: the test at school.

The question

Sentence 1: Chloe's teacher holds up a ginger fluffy cushion and the app says "cat".

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Chloe	Chloe	PROPN	Number=Sing	3 teacher	nmod:poss
2	's	's	PART	_	1 Chloe	case
3	teacher	teacher	NOUN	Number=Sing	4 holds	nsubj
4	holds	hold	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
5	up	up	ADP	_	4 holds	compound:prt
6	a	a	DET	Definite=Ind PronType=Art	9 cushion	det
7	ginger	ginger	NOUN	Number=Sing	9 cushion	compound
8	fluffy	fluffy	ADJ	Degree=Pos	9 cushion	amod
9	cushion	cushion	NOUN	Number=Sing	4 holds	obj
10	and	and	CCONJ	_	13 says	cc
11	the	the	DET	Definite=Def PronType=Art	12 app	det
12	app	app	NOUN	Number=Sing	13 says	nsubj
13	says	say	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	9 cushion	conj
14	"	"	PUNCT	_	15 cat	punct
15	cat	cat	NOUN	Number=Sing	13 says	obj
16	"	"	PUNCT	_	15 cat	punct
17	.	.	PUNCT	_	4 holds	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	hold up	present	Chloe's teacher	a ginger fluffy cushion					vn support-15.3-1 «NP V NP»: agent=Pivot cushion=Theme
2	say speech: assert	present	the app	cat					vn say-37.7-1-1 «NP V NP.topic»: agent=Agent cat=Topic

One row per clause the reader finds. «not said here»: a role filled from the clause above. «roles by»: a VerbNet class and frame when one fits the verb, else the reader's rules on the tree.

Sentence 2: What should the class learn?

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	What	what	PRON	PronType=Int	5 learn	obj
2	should	should	AUX	VerbForm=Fin	5 learn	aux
3	the	the	DET	Definite=Def PronType=Art	4 class	det
4	class	class	NOUN	Number=Sing	5 learn	nsubj
5	learn	learn	VERB	VerbForm=Inf	root	root
6	?	?	PUNCT	_	5 learn	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	learn	should	the class						vn learn-14-2-1 «NP V NP»: agent=Agent what=Topic

The options

Option 1 · ← Mova's choice

The cushion must contain cat hair

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 cushion	det
2	cushion	cushion	NOUN	Number=Sing	4 contain	nsubj
3	must	must	AUX	VerbForm=Fin	4 contain	aux
4	contain	contain	VERB	VerbForm=Inf	root	root
5	cat	cat	NOUN	Number=Sing	6 hair	compound
6	hair	hair	NOUN	Number=Sing	4 contain	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	contain	must	the cushion	cat hair					vn comprise-107.2-2 «NP V NP»: agent=Pivot hair=Theme

Option 2

The app is cleverer than the class

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 app	det
2	app	app	NOUN	Number=Sing	4 cleverer	nsubj
3	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	4 cleverer	cop
4	cleverer	clever	ADJ	Degree=Cmp	root	root
5	than	than	ADP	_	7 class	case
6	the	the	DET	Definite=Def PronType=Art	7 class	det
7	class	class	NOUN	Number=Sing	4 cleverer	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	the app					than the class; clever property	tree rules

Option 3 · ✓ the right answer

The app learned a look, not what a cat really is

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 app	det
2	app	app	NOUN	Number=Sing	3 learned	nsubj
3	learned	learn	VERB	Mood=Ind Number=Sing Person=3 Tense=Past VerbForm=Fin	root	root
4	a	a	DET	Definite=Ind PronType=Art	5 look	det
5	look	look	NOUN	Number=Sing	3 learned	obj
6	,	,	PUNCT	_	8 what	punct
7	not	not	PART	Polarity=Neg	8 what	advmod
8	what	what	PRON	PronType=Int	3 learned	ccomp
9	a	a	DET	Definite=Ind PronType=Art	10 cat	det
10	cat	cat	NOUN	Number=Sing	8 what	nsubj
11	really	really	ADV	_	8 what	advmod
12	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	8 what	cop

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	learn	past	the app	a look					vn learn-14-2-1 «NP V NP»: agent=Agent look=Topic
2	not is a	present	a cat						tree rules

Option 4

Cushions and cats are the same to everyone

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Cushions	cushion	NOUN	Number=Plur	6 same	nsubj
2	and	and	CCONJ	_	3 cats	cc
3	cats	cat	NOUN	Number=Plur	1 Cushions	conj
4	are	be	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	6 same	cop
5	the	the	DET	Definite=Def PronType=Art	6 same	det
6	same	same	ADJ	Degree=Pos	root	root
7	to	to	ADP	_	8 everyone	case
8	everyone	everyone	PRON	Number=Sing PronType=Tot	6 same	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	Cushions and cats					to everyone; same property	tree rules

Text: the tests of Mova's primary school, written for Mova (world/data/school/), as the course runner gave them to the student. Trees: Mova's own parse — the en model on the CPU, when the site is built — not checked by a teacher; they may be wrong. Frames: Mova's frames reader (prag), each text read on its own. Elamur Cosmic License.

This page in Markdown → https://md.mova.elamur.ai/free/en/corpora/questions/ai/1-what-is-ai/t5/