Exam question 1 · Stories, jokes and riddles with a chatbot

Which of the following statements most accurately characterises the term "hallucination" as applied to a chatbot?

Mova's choice: option 2 · The right answer: option 4 · wrong ✗ · What happens: follow, characteris, apply · To what, where: term

This is exam question 1 of lesson 4 «Stories, jokes and riddles with a chatbot» 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 term	det
10	term	term	NOUN	Number=Sing	8 characterises	obj
11	"	"	PUNCT	_	12 hallucination	punct
12	hallucination	hallucination	NOUN	Number=Sing	10 term	appos
13	"	"	PUNCT	_	12 hallucination	punct
14	as	as	SCONJ	_	15 applied	mark
15	applied	apply	VERB	Tense=Past VerbForm=Part Voice=Pass	8 characterises	advcl
16	to	to	ADP	_	18 chatbot	case
17	a	a	DET	Definite=Ind PronType=Art	18 chatbot	det
18	chatbot	chatbot	NOUN	Number=Sing	15 applied	obl
19	?	?	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 term	of the following statements; accurately property	tree rules
3	apply	participle		to a chatbot	vn use-105.1 «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

The repetition of a joke previously heard by the user

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 repetition	det
2	repetition	repetition	NOUN	Number=Sing	7 heard	nsubj:pass
3	of	of	ADP	_	5 joke	case
4	a	a	DET	Definite=Ind PronType=Art	5 joke	det
5	joke	joke	NOUN	Number=Sing	2 repetition	nmod
6	previously	previously	ADV	_	7 heard	advmod
7	heard	hear	VERB	Tense=Past VerbForm=Part Voice=Pass	root	root
8	by	by	ADP	_	10 user	case
9	the	the	DET	Definite=Def PronType=Art	10 user	det
10	user	user	NOUN	Number=Sing	7 heard	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	hear	participle · passive	the user	the repetition of a joke				previously property	vn see-30.1-1-1 «NP V S»: agent=Experiencer subject=Stimulus
2	repeat		a joke						nom repetition «event intransitive»: of=agent

Option 2 · ← Mova's choice

The perception of images by the chatbot during sleep

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	2 perception	det
2	perception	perception	NOUN	Number=Sing	root	root
3	of	of	ADP	_	4 images	case
4	images	image	NOUN	Number=Plur	2 perception	nmod
5	by	by	ADP	_	7 chatbot	case
6	the	the	DET	Definite=Def PronType=Art	7 chatbot	det
7	chatbot	chatbot	NOUN	Number=Sing	2 perception	nmod
8	during	during	ADP	_	9 sleep	case
9	sleep	sleep	NOUN	Number=Sing	7 chatbot	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	perceive		the chatbot during sleep	images					nom perception «cognition transitive»: of=patient by=agent

Option 3

The deliberate concealment of a correct answer

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	3 concealment	det
2	deliberate	deliberate	ADJ	Degree=Pos	3 concealment	amod
3	concealment	concealment	NOUN	Number=Sing	root	root
4	of	of	ADP	_	7 answer	case
5	a	a	DET	Definite=Ind PronType=Art	7 answer	det
6	correct	correct	ADJ	Degree=Pos	7 answer	amod
7	answer	answer	NOUN	Number=Sing	3 concealment	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	conceal			a correct answer					nom concealment «state transitive»: of=patient

Option 4 · ✓ the right answer

The confident production of an answer that is untrue

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	3 production	det
2	confident	confident	ADJ	Degree=Pos	3 production	amod
3	production	production	NOUN	Number=Sing	root	root
4	of	of	ADP	_	6 answer	case
5	an	a	DET	Definite=Ind PronType=Art	6 answer	det
6	answer	answer	NOUN	Number=Sing	3 production	nmod
7	that	that	PRON	PronType=Rel	9 untrue	nsubj
8	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	9 untrue	cop
9	untrue	untrue	ADJ	Degree=Pos	6 answer	acl:relcl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	a answer					untrue property	tree rules
2	produce			a answer					nom production «act transitive»: of=patient

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/4-stories-jokes-and-riddles/e1/