Mova0.5 pre-release⌕

☰

home / corpora / questions / AI / Stories, jokes and riddles with a chat… / t4

Test 4 · Stories, jokes and riddles with a chatbot

A cartoon shows a bot doing 37 × 48 in its head and always being right. What should you think?

Mova's choice: option 1 · The right answer: option 4 · wrong ✗ · Who acts: cartoon, bot, you · What happens: show, do, be, think · To what, where: bot, 37, head

This is test 4 of lesson 4 «Stories, jokes and riddles with a chatbot» 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: A cartoon shows a bot doing 37 × 48 in its head and always being right.

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	2 cartoon	det
2	cartoon	cartoon	NOUN	Number=Sing	3 shows	nsubj
3	shows	show	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	a	a	DET	Definite=Ind PronType=Art	5 bot	det
5	bot	bot	NOUN	Number=Sing	3 shows	obj
6	doing	do	VERB	VerbForm=Ger	5 bot	acl
7	37	37	NUM	NumForm=Digit NumType=Card	6 doing	obj
8	×	×	SYM	_	9 48	case
9	48	48	NUM	NumForm=Digit NumType=Card	7 37	nmod
10	in	in	ADP	_	12 head	case
11	its	its	PRON	Case=Gen Gender=Neut Number=Sing Person=3 Poss=Yes PronType=Prs	12 head	nmod:poss
12	head	head	NOUN	Number=Sing	6 doing	obl
13	and	and	CCONJ	_	16 right	cc
14	always	always	ADV	PronType=Tot	16 right	advmod
15	being	be	AUX	Tense=Pres VerbForm=Part	16 right	cop
16	right	right	ADJ	Degree=Pos	12 head	conj
17	.	.	PUNCT	_	3 shows	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	show	present	a cartoon	a bot					vn transfer_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent bot=Recipient
2	do	gerund	a bot not said here	37		cartoon's head		× 48	vn act-114-1 «NP V NP»: agent=Agent 37=Eventuality
3	is	gerund	a bot not said here					always, right property	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 should you think?

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	What	what	PRON	PronType=Int	4 think	obj
2	should	should	AUX	VerbForm=Fin	4 think	aux
3	you	you	PRON	Case=Nom Person=2 PronType=Prs	4 think	nsubj
4	think	think	VERB	VerbForm=Inf	root	root
5	?	?	PUNCT	_	4 think	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	think speech: other	should	you						vn wish-62 «NP V NP»: agent=Pivot what=Theme

The options

Option 1 · ← Mova's choice

Bots can't do sums at all, not even 1 + 1

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Bots	bot	NOUN	Number=Plur	4 do	nsubj
2	ca	can	AUX	VerbForm=Fin	4 do	aux
3	n't	not	PART	Polarity=Neg	4 do	advmod
4	do	do	VERB	VerbForm=Inf	root	root
5	sums	sum	NOUN	Number=Plur	4 do	obj
6	at	at	ADP	_	7 all	case
7	all	all	DET	PronType=Tot	4 do	obl
8	,	,	PUNCT	_	11 1	punct
9	not	not	PART	Polarity=Neg	11 1	advmod
10	even	even	ADV	_	11 1	advmod
11	1	1	NUM	NumForm=Digit NumType=Card	4 do	obl
12	+	+	SYM	_	13 1	advmod
13	1	1	NUM	NumForm=Digit NumType=Card	11 1	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	not do	can	Bots	sums		all		1 1 obl	vn act-114-1 «NP V NP»: agent=Agent sum=Eventuality

Option 2

Only cartoons can do sums

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Only	only	ADV	_	2 cartoons	advmod
2	cartoons	cartoon	NOUN	Number=Plur	4 do	nsubj
3	can	can	AUX	VerbForm=Fin	4 do	aux
4	do	do	VERB	VerbForm=Inf	root	root
5	sums	sum	NOUN	Number=Plur	4 do	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	do	can	cartoons	sums					vn act-114-1 «NP V NP»: agent=Agent sum=Eventuality

Option 3

That is true, bots are perfect calculators

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	That	that	PRON	Number=Sing PronType=Dem	3 true	nsubj
2	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 true	cop
3	true	true	ADJ	Degree=Pos	root	root
4	,	,	PUNCT	_	8 calculators	punct
5	bots	bot	NOUN	Number=Plur	8 calculators	nsubj
6	are	be	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	8 calculators	cop
7	perfect	perfect	ADJ	Degree=Pos	8 calculators	amod
8	calculators	calculator	NOUN	Number=Plur	3 true	parataxis

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	That					true property	tree rules
2	is a	present	bots	perfect calculators					tree rules

Option 4 · ✓ the right answer

Real chatbots can get big sums wrong, so check

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Real	real	ADJ	Degree=Pos	2 chatbots	amod
2	chatbots	chatbot	NOUN	Number=Plur	4 get	nsubj
3	can	can	AUX	VerbForm=Fin	4 get	aux
4	get	get	VERB	VerbForm=Inf	root	root
5	big	big	ADJ	Degree=Pos	6 sums	amod
6	sums	sum	NOUN	Number=Plur	4 get	obj
7	wrong	wrong	ADJ	Degree=Pos	4 get	xcomp
8	,	,	PUNCT	_	10 check	punct
9	so	so	ADV	_	10 check	advmod
10	check	check	VERB	VerbForm=Inf	4 get	conj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	get	can	Real chatbots	big sums				wrong property	vn comprehend-87.2-1 «NP V NP»: agent=Experiencer sum=Stimulus
2	check	infinitive	Real chatbots not said here						vn assessment-34.1 «NP V NP»: agent=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/4-stories-jokes-and-riddles/t4/