Mova0.5 pre-release⌕

☰

home / corpora / questions / AI / Bots are not doctors, helplines are pe… / t8

Test 8 · ★★ · Bots are not doctors, helplines are people

Your friend says, "I can always tell AI pictures, easy." What's a humble reply?

Mova's choice: option 1 · The right answer: option 3 · wrong ✗ · Who acts: friend · What happens: say, tell, be · To what, where: AI pictures, humble reply · Speech: someone speaks here

This is test 8 · ★★ of lesson 15 «Bots are not doctors, helplines are 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: Your friend says, "I can always tell AI pictures, easy."

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Your	your	PRON	Case=Gen Person=2 Poss=Yes PronType=Prs	2 friend	nmod:poss
2	friend	friend	NOUN	Number=Sing	3 says	nsubj
3	says	say	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	,	,	PUNCT	_	9 tell	punct
5	"	"	PUNCT	_	9 tell	punct
6	I	I	PRON	Case=Nom Number=Sing Person=1 PronType=Prs	9 tell	nsubj
7	can	can	AUX	VerbForm=Fin	9 tell	aux
8	always	always	ADV	PronType=Tot	9 tell	advmod
9	tell	tell	VERB	VerbForm=Inf	3 says	ccomp
10	AI	ai	NOUN	Number=Sing	11 pictures	compound
11	pictures	picture	NOUN	Number=Plur	9 tell	obj
12	,	,	PUNCT	_	13 easy	punct
13	easy	easy	ADJ	Degree=Pos	9 tell	advcl
14	.	.	PUNCT	_	9 tell	punct
15	"	"	PUNCT	_	9 tell	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	say speech: assert	present	Your friend						vn say-37.7-1-1 «NP V that S»: agent=Agent clause=Topic
2	tell speech: assert in a quote	can	Your friend = friend	AI pictures				always property	vn transfer_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent picture=Recipient

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's a humble reply?

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	What	what	PRON	PronType=Int	5 reply	nsubj
2	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	5 reply	cop
3	a	a	DET	Definite=Ind PronType=Art	5 reply	det
4	humble	humble	ADJ	Degree=Pos	5 reply	amod
5	reply	reply	NOUN	Number=Sing	root	root
6	?	?	PUNCT	_	5 reply	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	present		a humble reply					tree rules

The options

Option 1 · ← Mova's choice

You're right, they always look fake if you look

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	You	you	PRON	Case=Nom Person=2 PronType=Prs	3 right	nsubj
2	're	be	AUX	Mood=Ind Number=Sing Person=2 Tense=Pres VerbForm=Fin	3 right	cop
3	right	right	ADJ	Degree=Pos	root	root
4	,	,	PUNCT	_	7 look	punct
5	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	7 look	nsubj
6	always	always	ADV	PronType=Tot	7 look	advmod
7	look	look	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	3 right	conj
8	fake	fake	ADJ	Degree=Pos	7 look	xcomp
9	if	if	SCONJ	_	11 look	mark
10	you	you	PRON	Case=Nom Person=2 PronType=Prs	11 look	nsubj
11	look	look	VERB	Mood=Ind Number=Sing Person=2 Tense=Pres VerbForm=Fin	7 look	advcl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	You					right property	tree rules
2	look	present	they					always, fake property	vn stimulus_subject-30.4 «NP V ADJ»: agent=Stimulus
3	look a condition, not said to happen	present	you						vn stimulus_subject-30.4 «NP V PP.attribute»: agent=Stimulus

Option 2

AI pictures have watermarks always

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	AI	ai	NOUN	Number=Sing	2 pictures	compound
2	pictures	picture	NOUN	Number=Plur	3 have	nsubj
3	have	have	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
4	watermarks	watermark	NOUN	Number=Plur	3 have	obj
5	always	always	ADV	PronType=Tot	3 have	advmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	have	present	AI pictures	watermarks				always property	vn birth-28.2-1 «NP V NP»: agent=Agent watermark=Patient

Option 3 · ✓ the right answer

Even grown-ups get it wrong, so check sources

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Even	even	ADV	_	4 ups	advmod
2	grown	grow	VERB	Tense=Past VerbForm=Part Voice=Pass	4 ups	amod
3	-	-	PUNCT	_	2 grown	punct
4	ups	up	NOUN	Number=Plur	5 get	nsubj
5	get	get	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
6	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	5 get	obj
7	wrong	wrong	ADJ	Degree=Pos	5 get	xcomp
8	,	,	PUNCT	_	10 check	punct
9	so	so	ADV	_	10 check	advmod
10	check	check	VERB	VerbForm=Inf	5 get	conj
11	sources	source	NOUN	Number=Plur	10 check	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	grow	participle							vn appear-48.1.1 «NP V»: agent=Theme
2	get	present	grown ups	it				wrong property	vn comprehend-87.2-1 «NP V NP»: agent=Experiencer it=Stimulus
3	check	infinitive	grown ups not said here	sources					vn assessment-34.1 «NP V NP»: agent=Agent source=Theme

Option 4

Only experts can see pictures

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Only	only	ADV	_	2 experts	advmod
2	experts	expert	NOUN	Number=Plur	4 see	nsubj
3	can	can	AUX	VerbForm=Fin	4 see	aux
4	see	see	VERB	VerbForm=Inf	root	root
5	pictures	picture	NOUN	Number=Plur	4 see	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	see	can	experts	pictures					vn comprehend-87.2-1-1 «NP V NP»: agent=Experiencer picture=Stimulus

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/15-bots-are-not-doctors-helplines-are-people/t8/