Test 2 · ★★★ · Olympiad: thinking like a machine, Bebras puzzles ★★★

"my bot said strawberry has 2 r's. sus or nah?"

Mova's choice: option 4 · The right answer: option 4 · right ✓ · Who acts: bot, strawberry · What happens: say, have · To what, where: 2 r · Speech: someone speaks here

This is test 2 · ★★★ 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

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	4 said	punct
2	my	my	PRON	Case=Gen Number=Sing Person=1 Poss=Yes PronType=Prs	3 bot	nmod:poss
3	bot	bot	NOUN	Number=Sing	4 said	nsubj
4	said	say	VERB	Mood=Ind Number=Sing Person=3 Tense=Past VerbForm=Fin	root	root
5	strawberry	strawberry	NOUN	Number=Sing	6 has	nsubj
6	has	have	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	4 said	ccomp
7	2	2	NUM	NumForm=Digit NumType=Card	8 r	nummod
8	r	r	NOUN	Number=Sing	6 has	obj
9	's	's	PART	_	8 r	case
10	.	.	PUNCT	_	11 sus	punct
11	sus	sus	NOUN	Number=Sing	4 said	ccomp
12	or	or	CCONJ	_	13 nah	cc
13	nah	nah	INTJ	_	11 sus	conj
14	?	?	PUNCT	_	11 sus	punct
15	"	"	PUNCT	_	11 sus	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	say speech: ask in a quote	past	my bot						vn say-37.7-1-1 «NP V that S»: agent=Agent clause=Topic
2	have in a quote	present	strawberry	2 r					vn birth-28.2-1 «NP V NP»: agent=Agent r=Patient

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.

The options

Option 1

Nah it's right, bots never get spelling wrong

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Nah	nah	INTJ	_	4 right	discourse
2	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	4 right	nsubj
3	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	4 right	cop
4	right	right	ADJ	Degree=Pos	6 bots	amod
5	,	,	PUNCT	_	4 right	punct
6	bots	bot	NOUN	Number=Plur	8 get	nsubj
7	never	never	ADV	PronType=Neg	8 get	advmod
8	get	get	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
9	spelling	spelling	NOUN	Number=Sing	8 get	obj
10	wrong	wrong	ADJ	Degree=Pos	8 get	xcomp

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	it					right property	tree rules
2	not get	present	right bots	spelling				wrong property	vn comprehend-87.2-1 «NP V NP»: agent=Experiencer spelling=Stimulus

Option 2

No cap, it's 2, since the double r only counts once

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	No	no	DET	PronType=Neg	2 cap	det
2	cap	cap	NOUN	Number=Sing	13 counts	nsubj
3	,	,	PUNCT	_	2 cap	punct
4	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	6 2	nsubj
5	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	6 2	cop
6	2	2	NUM	NumForm=Digit NumType=Card	2 cap	appos
7	,	,	PUNCT	_	2 cap	punct
8	since	since	ADP	_	11 r	case
9	the	the	DET	Definite=Def PronType=Art	11 r	det
10	double	double	ADJ	Degree=Pos	11 r	amod
11	r	r	NOUN	Number=Sing	13 counts	obl
12	only	only	ADV	_	13 counts	advmod
13	counts	count	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
14	once	once	ADV	NumForm=Word NumType=Mult	13 counts	advmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	present	cap	2					tree rules
2	count	present	no cap				since the double r	once property	vn matter-91 «NP V»: agent=Stimulus

Option 3

Sus, it's actually 4 if you count the capital

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Sus	sus	NOUN	Number=Sing	root	root
2	,	,	PUNCT	_	6 4	punct
3	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	6 4	nsubj
4	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	6 4	cop
5	actually	actually	ADV	_	6 4	advmod
6	4	4	NUM	NumForm=Digit NumType=Card	1 Sus	appos
7	if	if	SCONJ	_	9 count	mark
8	you	you	PRON	Case=Nom Person=2 PronType=Prs	9 count	nsubj
9	count	count	VERB	Mood=Ind Number=Sing Person=2 Tense=Pres VerbForm=Fin	6 4	advcl
10	the	the	DET	Definite=Def PronType=Art	11 capital	det
11	capital	capital	NOUN	Number=Sing	9 count	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	present	Sus	4				actually property	tree rules
2	count a condition, not said to happen	present	you	the capital					vn multiply-108 «NP V NP»: agent=Agent capital=Theme

Option 4 · ← Mova's choice · ✓ the right answer

Sus: there are 3, and bots read in chunks, not letter by letter

The tree, 13 words

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Sus	sus	NOUN	Number=Sing	root	root
2	:	:	PUNCT	_	4 are	punct
3	there	there	PRON	PronType=Dem	4 are	expl
4	are	be	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	1 Sus	parataxis
5	3	3	NUM	NumForm=Digit NumType=Card	4 are	nsubj
6	,	,	PUNCT	_	9 read	punct
7	and	and	CCONJ	_	9 read	cc
8	bots	bot	NOUN	Number=Plur	9 read	nsubj
9	read	read	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	4 are	conj
10	in	in	ADP	_	11 chunks	case
11	chunks	chunk	NOUN	Number=Plur	9 read	obl
12	,	,	PUNCT	_	14 letter	punct
13	not	not	PART	Polarity=Neg	14 letter	advmod
14	letter	letter	NOUN	Number=Sing	1 Sus	conj
15	by	by	ADP	_	16 letter	case
16	letter	letter	NOUN	Number=Sing	14 letter	nmod

#	verb	tense, mood	who	where	roles by
1	be	present	3	there	vn exist-47.1 «NP V»: agent=Theme
2	read	present	bots	chunks	vn transfer_mesg-37.1.1-1 «NP V»: agent=Agent
3	letter		letter		nom letter «communication transitive»: by=agent

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/t2/