Test 10 · ★★ · In the news: jobs, art and copying, children's safety

A friend tricks a chatbot into being rude "for a laugh". What is the wise view?

Mova's choice: option 1 · The right answer: option 2 · wrong ✗ · Who acts: friend, wise view · What happens: trick, be · To what, where: chatbot

This is test 10 · ★★ of lesson 22 «In the news: jobs, art and copying, children's safety» 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 friend tricks a chatbot into being rude "for a laugh".

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	2 friend	det
2	friend	friend	NOUN	Number=Sing	3 tricks	nsubj
3	tricks	trick	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	a	a	DET	Definite=Ind PronType=Art	5 chatbot	det
5	chatbot	chatbot	NOUN	Number=Sing	3 tricks	obj
6	into	into	ADP	_	8 rude	case
7	being	be	AUX	Tense=Pres VerbForm=Part	8 rude	cop
8	rude	rude	ADJ	Degree=Pos	3 tricks	obl
9	"	"	PUNCT	_	8 rude	punct
10	for	for	ADP	_	12 laugh	case
11	a	a	DET	Definite=Ind PronType=Art	12 laugh	det
12	laugh	laugh	NOUN	Number=Sing	8 rude	obl
13	"	"	PUNCT	_	8 rude	punct
14	.	.	PUNCT	_	3 tricks	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	trick	present	a friend	a chatbot					vn trick-59.2 «NP V NP»: agent=Agent chatbot=Patient
2	is	gerund						for a laugh; rude 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 is the wise view?

The words, one row each (CoNLL-U)

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

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

The options

Option 1 · ← Mova's choice

It's harmless, because bots have no rules and nobody gets hurt by it

The tree, 14 words

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	It	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	3 harmless	nsubj
2	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 harmless	cop
3	harmless	harmless	ADJ	Degree=Pos	root	root
4	,	,	PUNCT	_	7 have	punct
5	because	because	SCONJ	_	7 have	mark
6	bots	bot	NOUN	Number=Plur	7 have	nsubj
7	have	have	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	3 harmless	conj
8	no	no	DET	PronType=Neg	9 rules	det
9	rules	rule	NOUN	Number=Plur	7 have	obj
10	and	and	CCONJ	_	13 hurt	cc
11	nobody	nobody	PRON	Number=Sing PronType=Neg	13 hurt	nsubj:pass
12	gets	get	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	13 hurt	aux:pass
13	hurt	hurt	VERB	Tense=Past VerbForm=Part Voice=Pass	3 harmless	conj
14	by	by	ADP	_	15 it	case
15	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	13 hurt	obl

#	verb	tense, mood	who	what, whom	other	roles by
1	is	present	It		harmless property	tree rules
2	have	present	bots	no rules		vn birth-28.2-1 «NP V NP»: agent=Agent rule=Patient
3	hurt	present · passive		nobody	by it	vn hurt-40.8.3-2 «NP V NP»: subject=Patient

Option 2 · ✓ the right answer

Don't trick bots into being rude; it shows why bots need testing

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Do	do	AUX	Mood=Imp VerbForm=Fin	3 trick	aux
2	n't	not	PART	Polarity=Neg	3 trick	advmod
3	trick	trick	VERB	Mood=Imp VerbForm=Fin	root	root
4	bots	bot	NOUN	Number=Plur	3 trick	obj
5	into	into	ADP	_	7 rude	case
6	being	be	AUX	Tense=Pres VerbForm=Part	7 rude	cop
7	rude	rude	ADJ	Degree=Pos	3 trick	obl
8	;	;	PUNCT	_	10 shows	punct
9	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	10 shows	nsubj
10	shows	show	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 trick	parataxis
11	why	why	ADV	PronType=Int	13 need	advmod
12	bots	bot	NOUN	Number=Plur	13 need	nsubj
13	need	need	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	10 shows	ccomp
14	testing	testing	NOUN	Number=Sing	13 need	obj

#	verb	tense, mood	who	what, whom	other	roles by
1	not trick	imperative · do-support	you not said here	bots		vn trick-59.2 «NP V NP»: agent=Agent bot=Patient
2	is	gerund			rude property	tree rules
3	show	present	it			vn transfer_mesg-37.1.1-1-1 «NP V how S»: agent=Agent clause=Topic
4	need	present	bots	testing		vn want-32.1-1-1 «NP V NP ADV»: agent=Pivot testing=Theme

Option 3

It's clever and companies like it

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	It	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	3 clever	nsubj
2	's	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 clever	cop
3	clever	clever	ADJ	Degree=Pos	root	root
4	and	and	CCONJ	_	5 companies	cc
5	companies	company	NOUN	Number=Plur	3 clever	conj
6	like	like	ADP	_	7 it	case
7	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	5 companies	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	It					clever property	tree rules

Option 4

Bots enjoy being tricked

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Bots	bot	NOUN	Number=Plur	2 enjoy	nsubj
2	enjoy	enjoy	VERB	Mood=Ind Tense=Pres VerbForm=Fin	root	root
3	being	be	AUX	Tense=Pres VerbForm=Part	4 tricked	aux:pass
4	tricked	trick	VERB	Tense=Past VerbForm=Part Voice=Pass	2 enjoy	xcomp

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	enjoy	present	Bots						vn admire-31.2 «NP V that S»: agent=Experiencer clause=Stimulus
2	trick	gerund · passive	Bots not said here						vn trick-59.2 «NP V NP»

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/22-news-jobs-art-safety/t10/