Test 11 · Stories, jokes and riddles with a chatbot

"bots never make stuff up, they just look it up" Is that right?

Mova's choice: option 1 · The right answer: option 1 · right ✓ · Who acts: bots, that · What happens: not make up, look up, not be · To what, where: stuff

This is test 11 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

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	4 make	punct
2	bots	bot	NOUN	Number=Plur	4 make	nsubj
3	never	never	ADV	PronType=Neg	4 make	advmod
4	make	make	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
5	stuff	stuff	NOUN	Number=Sing	4 make	obj
6	up	up	ADP	_	4 make	compound:prt
7	,	,	PUNCT	_	10 look	punct
8	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	10 look	nsubj
9	just	just	ADV	_	10 look	advmod
10	look	look	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	4 make	conj
11	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	10 look	obj
12	up	up	ADP	_	10 look	compound:prt
13	"	"	PUNCT	_	10 look	punct
14	Is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	16 right	cop
15	that	that	PRON	Number=Sing PronType=Dem	16 right	nsubj
16	right	right	ADJ	Degree=Pos	4 make	xcomp
17	?	?	PUNCT	_	4 make	punct

#	verb	tense, mood	who	what, whom	other	roles by
1	not make up in a quote	present	bots	stuff		vn comprise-107.2-1 «NP V NP»: agent=Theme stuff=Pivot
2	look up in a quote	present	bots = bot	stuff		vn seem-109-1-1 «NP V NP»: agent=Theme it=Attribute
3	not is	present	that		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.

The options

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

No, they can make up confident answers that are false

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	No	no	INTJ	Polarity=Neg	5 make	discourse
2	,	,	PUNCT	_	1 No	punct
3	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	5 make	nsubj
4	can	can	AUX	VerbForm=Fin	5 make	aux
5	make	make	VERB	VerbForm=Inf	root	root
6	up	up	ADP	_	5 make	compound:prt
7	confident	confident	ADJ	Degree=Pos	8 answers	amod
8	answers	answer	NOUN	Number=Plur	5 make	obj
9	that	that	PRON	PronType=Rel	11 false	nsubj
10	are	be	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	11 false	cop
11	false	false	ADJ	Degree=Pos	8 answers	acl:relcl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	make up	can	they	confident answers					vn comprise-107.2-1 «NP V NP»: agent=Theme answer=Pivot
2	is	present	confident answers					false property	tree rules

Option 2

Yes, they look everything up in a big encyclopedia first

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Yes	yes	INTJ	Polarity=Pos	4 look	discourse
2	,	,	PUNCT	_	4 look	punct
3	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	4 look	nsubj
4	look	look	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
5	everything	everything	PRON	Number=Sing PronType=Tot	4 look	obj
6	up	up	ADP	_	4 look	compound:prt
7	in	in	ADP	_	10 encyclopedia	case
8	a	a	DET	Definite=Ind PronType=Art	10 encyclopedia	det
9	big	big	ADJ	Degree=Pos	10 encyclopedia	amod
10	encyclopedia	encyclopedia	NOUN	Number=Sing	4 look	obl
11	first	first	ADV	NumForm=Word NumType=Ord	4 look	advmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	look up	present	they	everything		a big encyclopedia		first property	vn seem-109-1-1 «NP V NP»: agent=Theme everything=Attribute

Option 3

No, they never answer questions at all

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	No	no	INTJ	Polarity=Neg	5 answer	discourse
2	,	,	PUNCT	_	1 No	punct
3	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	5 answer	nsubj
4	never	never	ADV	PronType=Neg	5 answer	advmod
5	answer	answer	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
6	questions	question	NOUN	Number=Plur	5 answer	obj
7	at	at	ADP	_	8 all	case
8	all	all	DET	PronType=Tot	5 answer	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	not answer speech: assert	present	they	questions		all			vn reciprocate-112-1 «NP V PP»: agent=Agent question=Eventuality

Option 4

Yes, every answer is copied from a website

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Yes	yes	INTJ	Polarity=Pos	6 copied	discourse
2	,	,	PUNCT	_	1 Yes	punct
3	every	every	DET	PronType=Tot	4 answer	det
4	answer	answer	NOUN	Number=Sing	6 copied	nsubj:pass
5	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	6 copied	aux:pass
6	copied	copy	VERB	Tense=Past VerbForm=Part Voice=Pass	root	root
7	from	from	ADP	_	9 website	case
8	a	a	DET	Definite=Ind PronType=Art	9 website	det
9	website	website	NOUN	Number=Sing	6 copied	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	copy	present · passive		every answer		a website			vn scribble-25.2 «NP V NP»: subject=Theme

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/t11/