Mova0.5 pre-release⌕

☰

home / corpora / questions / AI / In the news: tricked bots, real discov… / t9

Test 9 · ★★ · In the news: tricked bots, real discoveries, careful words

A book with a famous author's name looks odd and full of mistakes. What might be going on?

Mova's choice: option 2 · The right answer: option 2 · right ✓ · Who acts: book, famous author · What happens: look, name, go on

This is test 9 · ★★ 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

Sentence 1: A book with a famous author's name looks odd and full of mistakes.

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	2 book	det
2	book	book	NOUN	Number=Sing	9 looks	nsubj
3	with	with	ADP	_	8 name	case
4	a	a	DET	Definite=Ind PronType=Art	6 author	det
5	famous	famous	ADJ	Degree=Pos	6 author	amod
6	author	author	NOUN	Number=Sing	8 name	nmod:poss
7	's	's	PART	_	6 author	case
8	name	name	NOUN	Number=Sing	2 book	nmod
9	looks	look	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
10	odd	odd	ADJ	Degree=Pos	9 looks	xcomp
11	and	and	CCONJ	_	12 full	cc
12	full	full	ADJ	Degree=Pos	10 odd	conj
13	of	of	ADP	_	14 mistakes	case
14	mistakes	mistake	NOUN	Number=Plur	12 full	nmod
15	.	.	PUNCT	_	9 looks	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	look	present	a book with a famous author's name					odd property	vn stimulus_subject-30.4 «NP V ADJ»: agent=Stimulus
2	name		a famous author						nom name «communication transitive»: poss=agent

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 might be going on?

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	What	what	PRON	PronType=Int	4 going	nsubj
2	might	might	AUX	VerbForm=Fin	4 going	aux
3	be	be	AUX	VerbForm=Inf	4 going	aux
4	going	go	VERB	Tense=Pres VerbForm=Part	root	root
5	on	on	ADP	_	4 going	compound:prt
6	?	?	PUNCT	_	4 going	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	go on	might · progressive							vn function-105.2.1 «NP V»: agent=Theme

The options

Option 1

It must be her first ever book

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	7 book	nsubj
2	must	must	AUX	VerbForm=Fin	7 book	aux
3	be	be	AUX	VerbForm=Inf	7 book	cop
4	her	her	PRON	Case=Gen Gender=Fem Number=Sing Person=3 Poss=Yes PronType=Prs	7 book	nmod:poss
5	first	first	ADJ	Degree=Pos NumForm=Word NumType=Ord	7 book	amod
6	ever	ever	ADV	PronType=Ind	7 book	advmod
7	book	book	NOUN	Number=Sing	root	root

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	must	It	her first book			ever		tree rules

Option 2 · ← Mova's choice · ✓ the right answer

It could be a fake made under her name

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	5 fake	nsubj
2	could	could	AUX	VerbForm=Fin	5 fake	aux
3	be	be	AUX	VerbForm=Inf	5 fake	cop
4	a	a	DET	Definite=Ind PronType=Art	5 fake	det
5	fake	fake	NOUN	Number=Sing	root	root
6	made	make	VERB	Tense=Past VerbForm=Part Voice=Pass	5 fake	acl
7	under	under	ADP	_	9 name	case
8	her	her	PRON	Case=Gen Gender=Fem Number=Sing Person=3 Poss=Yes PronType=Prs	9 name	nmod:poss
9	name	name	NOUN	Number=Sing	6 made	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	could	It	a fake					tree rules
2	make	participle		a fake not said here		her name			vn build-26.1-1 «NP.asset V NP»: agent=Asset
3	name		her = she						nom name «communication transitive»: poss=agent

Option 3

Famous authors always make mistakes

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Famous	famous	ADJ	Degree=Pos	2 authors	amod
2	authors	author	NOUN	Number=Plur	4 make	nsubj
3	always	always	ADV	PronType=Tot	4 make	advmod
4	make	make	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
5	mistakes	mistake	NOUN	Number=Plur	4 make	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	make	present	Famous authors	mistakes				always property	vn build-26.1-1 «NP.asset V NP»: agent=Asset mistake=Product

Option 4

The printer changed her words

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 printer	det
2	printer	printer	NOUN	Number=Sing	3 changed	nsubj
3	changed	change	VERB	Mood=Ind Number=Sing Person=3 Tense=Past VerbForm=Fin	root	root
4	her	she	PRON	Case=Acc Gender=Fem Number=Sing Person=3 PronType=Prs	3 changed	obj
5	words	word	NOUN	Number=Plur	3 changed	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	change	past	the printer	her = she					tree rules

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/t9/