Exam question 1 · Why the bot agrees too easily

Which of the following statements most accurately characterises the expression "Great question!" when employed by a chatbot?

Mova's choice: option 1 · The right answer: option 3 · wrong ✗ · What happens: follow, characteris, employ · To what, where: expression

This is exam question 1 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	Which	which	PRON	PronType=Rel	8 characterises	nsubj
2	of	of	ADP	_	5 statements	case
3	the	the	DET	Definite=Def PronType=Art	5 statements	det
4	following	follow	VERB	VerbForm=Ger	5 statements	amod
5	statements	statement	NOUN	Number=Plur	8 characterises	obl
6	most	most	ADV	Degree=Sup	7 accurately	advmod
7	accurately	accurately	ADV	_	8 characterises	advmod
8	characterises	characteris	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
9	the	the	DET	Definite=Def PronType=Art	10 expression	det
10	expression	expression	NOUN	Number=Sing	8 characterises	obj
11	"	"	PUNCT	_	13 question	punct
12	Great	great	ADJ	Degree=Pos	13 question	amod
13	question	question	NOUN	Number=Sing	10 expression	appos
14	!	!	PUNCT	_	13 question	punct
15	"	"	PUNCT	_	13 question	punct
16	when	when	ADV	PronType=Int	17 employed	advmod
17	employed	employ	VERB	Tense=Past VerbForm=Part Voice=Pass	8 characterises	advcl
18	by	by	ADP	_	20 chatbot	case
19	a	a	DET	Definite=Ind PronType=Art	20 chatbot	det
20	chatbot	chatbot	NOUN	Number=Sing	17 employed	obl
21	?	?	PUNCT	_	8 characterises	punct

#	verb	tense, mood	what, whom	other	roles by
1	follow	gerund			vn occur-48.3-1 «NP V»: agent=Theme
2	characteris	present	the expression	of the following statements; accurately property	tree rules
3	employ	participle		by a chatbot	vn hire-13.5.3 «NP V NP»: agent=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.

The options

Option 1 · ← Mova's choice

An indication that the subsequent answer is erroneous

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	An	a	DET	Definite=Ind PronType=Art	2 indication	det
2	indication	indication	NOUN	Number=Sing	root	root
3	that	that	SCONJ	_	8 erroneous	mark
4	the	the	DET	Definite=Def PronType=Art	6 answer	det
5	subsequent	subsequent	ADJ	Degree=Pos	6 answer	amod
6	answer	answer	NOUN	Number=Sing	8 erroneous	nsubj
7	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	8 erroneous	cop
8	erroneous	erroneous	ADJ	Degree=Pos	2 indication	acl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	the subsequent answer	a indication not said here				erroneous property	tree rules

Option 2

A rigorous and impartial evaluation of the merit of the question asked

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	5 evaluation	det
2	rigorous	rigorous	ADJ	Degree=Pos	5 evaluation	amod
3	and	and	CCONJ	_	4 impartial	cc
4	impartial	impartial	ADJ	Degree=Pos	2 rigorous	conj
5	evaluation	evaluation	NOUN	Number=Sing	root	root
6	of	of	ADP	_	8 merit	case
7	the	the	DET	Definite=Def PronType=Art	8 merit	det
8	merit	merit	NOUN	Number=Sing	5 evaluation	nmod
9	of	of	ADP	_	11 question	case
10	the	the	DET	Definite=Def PronType=Art	11 question	det
11	question	question	NOUN	Number=Sing	8 merit	nmod
12	asked	ask	VERB	Tense=Past VerbForm=Part Voice=Pass	11 question	acl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	ask speech: ask	participle		the question not said here					vn inquire-37.1.2 «NP V»: agent=Agent
2	evaluate			the merit of the question					nom evaluation «act transitive»: of=patient

Option 3 · ✓ the right answer

A customary courtesy implying no genuine assessment of the question

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	3 courtesy	det
2	customary	customary	NOUN	Number=Sing	3 courtesy	compound
3	courtesy	courtesy	NOUN	Number=Sing	root	root
4	implying	imply	VERB	VerbForm=Ger	3 courtesy	acl
5	no	no	DET	PronType=Neg	7 assessment	det
6	genuine	genuine	ADJ	Degree=Pos	7 assessment	amod
7	assessment	assessment	NOUN	Number=Sing	4 implying	obj
8	of	of	ADP	_	10 question	case
9	the	the	DET	Definite=Def PronType=Art	10 question	det
10	question	question	NOUN	Number=Sing	7 assessment	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	imply	gerund	a customary courtesy not said here	no genuine assessment of the question					vn indicate-78 «NP V NP»: agent=Pivot assessment=Topic
2	assess			the question					nom assessment «cognition transitive»: of=patient

Option 4

A declaration of personal admiration for the user

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	2 declaration	det
2	declaration	declaration	NOUN	Number=Sing	root	root
3	of	of	ADP	_	5 admiration	case
4	personal	personal	ADJ	Degree=Pos	5 admiration	amod
5	admiration	admiration	NOUN	Number=Sing	2 declaration	nmod
6	for	for	ADP	_	8 user	case
7	the	the	DET	Definite=Def PronType=Art	8 user	det
8	user	user	NOUN	Number=Sing	2 declaration	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	declare			personal admiration				for the user	nom declaration «communication transitive»: of=patient for=obl

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/e1/