Test 10 · ★★ · In the news: tricked bots, real discoveries, careful words

Which is the best example of a headline that overscares?

Mova's choice: option 1 · The right answer: option 2 · wrong ✗ · Who acts: that · What happens: be, overscare · To what, where: best example

This is test 10 · ★★ of lesson 23 «In the news: tricked bots, real discoveries, careful words» 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	Which	which	PRON	PronType=Rel	5 example	nsubj
2	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	5 example	cop
3	the	the	DET	Definite=Def PronType=Art	5 example	det
4	best	good	ADJ	Degree=Sup	5 example	amod
5	example	example	NOUN	Number=Sing	root	root
6	of	of	ADP	_	8 headline	case
7	a	a	DET	Definite=Ind PronType=Art	8 headline	det
8	headline	headline	NOUN	Number=Sing	5 example	nmod
9	that	that	PRON	PronType=Rel	10 overscares	nsubj
10	overscares	overscare	NOUN	Number=Plur	8 headline	conj
11	?	?	PUNCT	_	5 example	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	present		the best example				of a headline and overscares	tree rules
2	overscare		that						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

"It was reported that AI helped find antibiotics"

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	4 reported	punct
2	It	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	4 reported	nsubj:pass
3	was	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Past VerbForm=Fin	4 reported	aux:pass
4	reported	report	VERB	Tense=Past VerbForm=Part Voice=Pass	root	root
5	that	that	SCONJ	_	7 helped	mark
6	AI	ai	NOUN	Number=Sing	7 helped	nsubj
7	helped	help	VERB	Mood=Ind Number=Sing Person=3 Tense=Past VerbForm=Fin	4 reported	ccomp
8	find	find	VERB	VerbForm=Inf	7 helped	xcomp
9	antibiotics	antibiotic	NOUN	Number=Plur	8 find	obj
10	"	"	PUNCT	_	4 reported	punct

#	verb	tense, mood	who	what, whom	roles by
1	report in a quote	past · passive		It	vn characterize-29.2-1-2 «NP V NP to be ADJ»: subject=Theme clause=Attribute
2	help in a quote	past	AI		vn help-72.1-1-1 «NP V NP S_INF»: agent=Agent clause=Theme
3	find in a quote	infinitive	AI not said here	antibiotics	vn discover-84 «NP V NP»: agent=Agent antibiotic=Topic

Option 2 · ✓ the right answer

"Robots will take over the world by Friday!"

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	4 take	punct
2	Robots	robot	NOUN	Number=Plur	4 take	nsubj
3	will	will	AUX	VerbForm=Fin	4 take	aux
4	take	take	VERB	VerbForm=Inf	root	root
5	over	over	ADP	_	4 take	compound:prt
6	the	the	DET	Definite=Def PronType=Art	7 world	det
7	world	world	NOUN	Number=Sing	4 take	obj
8	by	by	ADP	_	9 Friday	case
9	Friday	Friday	PROPN	Number=Sing	4 take	obl
10	!	!	PUNCT	_	4 take	punct
11	"	"	PUNCT	_	4 take	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	take over in a quote	future	Robots	the world			friday		vn obtain-13.5.2 «NP V NP»: agent=Agent world=Theme

Option 3

"Schools allow chatbots with new rules"

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	3 allow	punct
2	Schools	school	NOUN	Number=Plur	3 allow	nsubj
3	allow	allow	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
4	chatbots	chatbot	NOUN	Number=Plur	3 allow	obj
5	with	with	ADP	_	7 rules	case
6	new	new	ADJ	Degree=Pos	7 rules	amod
7	rules	rule	NOUN	Number=Plur	3 allow	obl
8	"	"	PUNCT	_	3 allow	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	allow in a quote	present	Schools	chatbots				with new rules	vn allow-64.1-1 «NP V NP»: agent=Agent chatbot=Beneficiary

Option 4

"Study shows AI makes some mistakes"

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	"	"	PUNCT	_	3 shows	punct
2	Study	study	NOUN	Number=Sing	3 shows	nsubj
3	shows	show	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	AI	ai	NOUN	Number=Sing	5 makes	nsubj
5	makes	make	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 shows	ccomp
6	some	some	DET	PronType=Ind	7 mistakes	det
7	mistakes	mistake	NOUN	Number=Plur	5 makes	obj
8	"	"	PUNCT	_	3 shows	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	show in a quote	present	Study						vn transfer_mesg-37.1.1-1-1 «NP V how S»: agent=Agent clause=Topic
2	make in a quote	present	AI	some mistakes					vn build-26.1-1 «NP.asset V NP»: agent=Asset mistake=Product

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/23-news-tricked-bots-discoveries/t10/