Mova0.5 pre-release⌕

☰

home / corpora / questions / AI / Olympiad: thinking like a machine, Beb… / t4

Test 4 · ★★★ · Olympiad: thinking like a machine, Bebras puzzles ★★★

"my mate's AI app keeps saying his husky's a wolf whenever it's in the snow lol". What would help fix the sorter most?

Mova's choice: option 1 · The right answer: option 1 · right ✓ · Who acts: AI app, husky, it · What happens: keep, say, be, help, fix · To what, where: wolf, snow, sorter · Speech: someone speaks here

This is test 4 · ★★★ of lesson 31 «Olympiad: thinking like a machine, Bebras puzzles ★★★» 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: "my mate's AI app keeps saying his husky's a wolf whenever it's in the snow lol".

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	7 keeps	punct
2	my	my	PRON	Case=Gen Number=Sing Person=1 Poss=Yes PronType=Prs	3 mate	nmod:poss
3	mate	mate	NOUN	Number=Sing	6 app	nmod:poss
4	's	's	PART	_	3 mate	case
5	AI	ai	NOUN	Number=Sing	6 app	compound
6	app	app	NOUN	Number=Sing	7 keeps	nsubj
7	keeps	keep	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
8	saying	say	VERB	VerbForm=Ger	7 keeps	xcomp
9	his	his	PRON	Case=Gen Gender=Masc Number=Sing Person=3 Poss=Yes PronType=Prs	10 husky	nmod:poss
10	husky	husky	NOUN	Number=Sing	13 wolf	nsubj
11	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	13 wolf	cop
12	a	a	DET	Definite=Ind PronType=Art	13 wolf	det
13	wolf	wolf	NOUN	Number=Sing	8 saying	ccomp
14	whenever	whenever	ADV	PronType=Rel	8 saying	ccomp
15	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	19 snow	nsubj
16	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	19 snow	cop
17	in	in	ADP	_	19 snow	case
18	the	the	DET	Definite=Def PronType=Art	19 snow	det
19	snow	snow	NOUN	Number=Sing	14 whenever	parataxis
20	lol	lol	INTJ	_	19 snow	discourse
21	"	"	PUNCT	_	19 snow	punct
22	.	.	PUNCT	_	7 keeps	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	keep in a quote	present	my mate's AI app						tree rules
2	say speech: assert in a quote	gerund	my mate's AI app not said here						vn say-37.7-1-1 «NP V that S»: agent=Agent
3	is a in a quote	present	app's husky	a wolf					tree rules
4	is in a quote	present	it			the snow			tree rules

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 would help fix the sorter most?

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	What	what	PRON	PronType=Int	3 help	nsubj
2	would	would	AUX	VerbForm=Fin	3 help	aux
3	help	help	VERB	VerbForm=Inf	root	root
4	fix	fix	VERB	VerbForm=Inf	3 help	xcomp
5	the	the	DET	Definite=Def PronType=Art	6 sorter	det
6	sorter	sorter	NOUN	Number=Sing	4 fix	obj
7	most	most	ADV	Degree=Sup	4 fix	advmod
8	?	?	PUNCT	_	3 help	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	help	would							vn help-72.1-1-1 «NP V NP S_INF»: agent=Agent clause=Theme
2	fix	infinitive		the sorter					vn shake-22.3-2 «NP V NP together»: agent=Agent sorter=Patient

The options

Option 1 · ← Mova's choice · ✓ the right answer

Training it on wolves without snow and huskies in snow

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Training	train	VERB	Tense=Pres VerbForm=Part	root	root
2	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	1 Training	obj
3	on	on	ADP	_	4 wolves	case
4	wolves	wolf	NOUN	Number=Plur	1 Training	obl
5	without	without	ADP	_	6 snow	case
6	snow	snow	NOUN	Number=Sing	1 Training	obl
7	and	and	CCONJ	_	8 huskies	cc
8	huskies	husky	NOUN	Number=Plur	6 snow	conj
9	in	in	ADP	_	10 snow	case
10	snow	snow	NOUN	Number=Sing	1 Training	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	train	gerund		it		wolves		without snow and huskies; in snow	vn hire-13.5.3 «NP V NP»: agent=Agent it=Theme

Option 2

Turning the brightness of every photo right up

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Turning	turn	VERB	Tense=Pres VerbForm=Part	root	root
2	the	the	DET	Definite=Def PronType=Art	3 brightness	det
3	brightness	brightness	NOUN	Number=Sing	1 Turning	obj
4	of	of	ADP	_	6 photo	case
5	every	every	DET	PronType=Tot	6 photo	det
6	photo	photo	NOUN	Number=Sing	3 brightness	nmod
7	right	right	ADV	_	8 up	advmod
8	up	up	ADV	_	1 Turning	advmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	turn	gerund		the brightness of every photo					vn roll-51.3.1 «NP V NP.theme»: agent=Agent brightness=Theme

Option 3

Showing it lots more wolves standing in the snow

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Showing	show	VERB	Tense=Pres VerbForm=Part	root	root
2	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	1 Showing	obj
3	lots	lot	NOUN	Number=Plur	1 Showing	obj
4	more	more	ADJ	Degree=Cmp	5 wolves	amod
5	wolves	wolf	NOUN	Number=Plur	3 lots	conj
6	standing	stand	VERB	VerbForm=Ger	5 wolves	acl
7	in	in	ADP	_	9 snow	case
8	the	the	DET	Definite=Def PronType=Art	9 snow	det
9	snow	snow	NOUN	Number=Sing	6 standing	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	show	gerund		it					vn transfer_mesg-37.1.1-1-1 «NP V NP-Dative NP»: agent=Agent it=Recipient lot=Topic
2	stand	gerund	more wolves not said here			the snow			vn assuming_position-50 «NP V PP.location»: agent=Agent in snow=Location

Option 4

Telling it once, very firmly, that it's wrong

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Telling	tell	VERB	VerbForm=Ger	11 wrong	csubj
2	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	1 Telling	obj
3	once	once	ADV	NumForm=Word NumType=Mult	1 Telling	advmod
4	,	,	PUNCT	_	6 firmly	punct
5	very	very	ADV	_	6 firmly	advmod
6	firmly	firmly	ADV	_	1 Telling	advmod
7	,	,	PUNCT	_	11 wrong	punct
8	that	that	SCONJ	_	11 wrong	mark
9	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	11 wrong	nsubj
10	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	11 wrong	cop
11	wrong	wrong	ADJ	Degree=Pos	root	root

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	tell speech: assert	gerund			it			firmly, once property	vn transfer_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent it=Recipient
2	is	present	it					wrong 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/31-olympiad-thinking-like-a-machine/t4/