Exam question 3 · Why the bot agrees too easily

Select the response that is consistent with the established facts concerning the interpretation of dreams by a chatbot.

Mova's choice: option 1 · The right answer: option 3 · wrong ✗ · Who acts: you, response, established facts · What happens: select, be, establish, concern, interpret · To what, where: response, interpretation, dreams

This is exam question 3 of lesson 6 «Why the bot agrees too easily» of the AI course of Mova's primary school, asked in stiff, formal language. 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	Select	select	VERB	Mood=Imp VerbForm=Fin	root	root
2	the	the	DET	Definite=Def PronType=Art	3 response	det
3	response	response	NOUN	Number=Sing	1 Select	obj
4	that	that	PRON	PronType=Rel	6 consistent	nsubj
5	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	6 consistent	cop
6	consistent	consistent	ADJ	Degree=Pos	3 response	acl:relcl
7	with	with	ADP	_	10 facts	case
8	the	the	DET	Definite=Def PronType=Art	10 facts	det
9	established	establish	VERB	Tense=Past VerbForm=Part Voice=Pass	10 facts	amod
10	facts	fact	NOUN	Number=Plur	6 consistent	obl
11	concerning	concern	VERB	VerbForm=Ger	10 facts	acl
12	the	the	DET	Definite=Def PronType=Art	13 interpretation	det
13	interpretation	interpretation	NOUN	Number=Sing	11 concerning	obj
14	of	of	ADP	_	15 dreams	case
15	dreams	dream	NOUN	Number=Plur	13 interpretation	nmod
16	by	by	ADP	_	18 chatbot	case
17	a	a	DET	Definite=Ind PronType=Art	18 chatbot	det
18	chatbot	chatbot	NOUN	Number=Sing	11 concerning	obl
19	.	.	PUNCT	_	1 Select	punct

#	verb	tense, mood	who	what, whom	other	roles by
1	select	imperative	you not said here	the response		vn obtain-13.5.2 «NP V NP»: agent=Agent response=Theme
2	is	present	the response		with the established facts; consistent property	tree rules
3	establish	participle				vn indicate-78-1-1 «NP V NP to be NP»: agent=Pivot
4	concern	gerund	the established facts not said here	the interpretation of dreams	by a chatbot	vn amuse-31.1 «NP V NP»: agent=Stimulus interpretation=Experiencer
5	interpret			dreams		nom interpretation «cognition transitive»: of=patient

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 decodes the fixed meaning attached to each dream

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	2 decodes	nsubj
2	decodes	decode	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
3	the	the	DET	Definite=Def PronType=Art	5 meaning	det
4	fixed	fix	VERB	Tense=Past VerbForm=Part Voice=Pass	5 meaning	amod
5	meaning	meaning	NOUN	Number=Sing	2 decodes	obj
6	attached	attach	VERB	Tense=Past VerbForm=Part Voice=Pass	5 meaning	acl
7	to	to	ADP	_	9 dream	case
8	each	each	DET	PronType=Tot	9 dream	det
9	dream	dream	NOUN	Number=Sing	6 attached	obl

#	verb	tense, mood	who	what, whom	other	roles by
1	decode	present	It	the fixed meaning		tree rules
2	fix	participle				vn shake-22.3-2 «NP V ADV-Middle»: agent=Patient
3	attach	participle		the fixed meaning not said here	to each dream	vn shake-22.3-2-1 «NP V NP PP»: agent=Agent to dream=Co-Patient

Option 2

It foretells future events disclosed within dreams

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	2 foretells	nsubj
2	foretells	foretell	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
3	future	future	ADJ	Degree=Pos	4 events	amod
4	events	event	NOUN	Number=Plur	5 disclosed	nsubj
5	disclosed	disclose	VERB	Mood=Ind Number=Plur Person=3 Tense=Past VerbForm=Fin	2 foretells	ccomp
6	within	within	ADP	_	7 dreams	case
7	dreams	dream	NOUN	Number=Plur	5 disclosed	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	foretell	present	It						vn conjecture-29.5-1 «NP V that S»: agent=Agent clause=Theme
2	disclose	past	future events					within dreams	vn indicate-78-1-1 «NP V NP to be NP»: agent=Pivot

Option 3 · ✓ the right answer

It reproduces popular beliefs which lack scientific foundation

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	2 reproduces	nsubj
2	reproduces	reproduce	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
3	popular	popular	ADJ	Degree=Pos	4 beliefs	amod
4	beliefs	belief	NOUN	Number=Plur	2 reproduces	obj
5	which	which	PRON	PronType=Rel	6 lack	nsubj
6	lack	lack	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	4 beliefs	acl:relcl
7	scientific	scientific	ADJ	Degree=Pos	8 foundation	amod
8	foundation	foundation	NOUN	Number=Sing	6 lack	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	reproduce	present	It	popular beliefs					vn other_cos-45.4 «NP V NP.patient»: agent=Agent belief=Patient
2	lack	present	popular beliefs	scientific foundation					tree rules

Option 4

It has been trained exclusively upon scientific findings

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	4 trained	nsubj:pass
2	has	have	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	4 trained	aux
3	been	be	AUX	Tense=Past VerbForm=Part	4 trained	aux:pass
4	trained	train	VERB	Tense=Past VerbForm=Part Voice=Pass	root	root
5	exclusively	exclusively	ADV	_	4 trained	advmod
6	upon	upon	ADP	_	8 findings	case
7	scientific	scientific	ADJ	Degree=Pos	8 findings	amod
8	findings	finding	NOUN	Number=Plur	4 trained	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	train	present · perfect · passive		It				upon scientific findings; exclusively property	vn hire-13.5.3 «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/6-why-the-bot-agrees-too-easily/e3/