Test 8 · Stories, jokes and riddles with a chatbot

Why do bots tell the same old jokes again and again?

Mova's choice: option 2 · The right answer: option 1 · wrong ✗ · Who acts: bots · What happens: tell · To what, where: same old jokes · Speech: someone speaks here

This is test 8 of lesson 4 «Stories, jokes and riddles with a chatbot» 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	Why	why	ADV	PronType=Int	4 tell	advmod
2	do	do	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	4 tell	aux
3	bots	bot	NOUN	Number=Plur	4 tell	nsubj
4	tell	tell	VERB	VerbForm=Inf	root	root
5	the	the	DET	Definite=Def PronType=Art	8 jokes	det
6	same	same	ADJ	Degree=Pos	8 jokes	amod
7	old	old	ADJ	Degree=Pos	8 jokes	amod
8	jokes	joke	NOUN	Number=Plur	4 tell	obj
9	again	again	ADV	_	4 tell	advmod
10	and	and	CCONJ	_	11 again	cc
11	again	again	ADV	_	9 again	conj
12	?	?	PUNCT	_	4 tell	punct

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	tell speech: assert	present · do-support	bots	the same old jokes			again		vn transfer_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent joke=Recipient

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 right answer

Those jokes appear most in what they learned

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Those	that	DET	Number=Plur PronType=Dem	2 jokes	det
2	jokes	joke	NOUN	Number=Plur	3 appear	nsubj
3	appear	appear	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
4	most	most	ADV	Degree=Sup	3 appear	advmod
5	in	in	ADP	_	6 what	case
6	what	what	PRON	PronType=Rel	3 appear	obl
7	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	8 learned	nsubj
8	learned	learn	VERB	Mood=Ind Number=Plur Person=3 Tense=Past VerbForm=Fin	6 what	acl:relcl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	appear	present	that jokes						vn appear-48.1.1 «NP V PP.location»: agent=Theme in what=Location
2	learn	past	jokes = joke						vn learn-14-1 «NP V»: agent=Agent

Option 2 · ← Mova's choice

Bots get paid more for old jokes

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Bots	bot	NOUN	Number=Plur	3 paid	nsubj:pass
2	get	get	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	3 paid	aux:pass
3	paid	pay	VERB	Tense=Past VerbForm=Part Voice=Pass	root	root
4	more	more	ADJ	Degree=Cmp	3 paid	obj
5	for	for	ADP	_	7 jokes	case
6	old	old	ADJ	Degree=Pos	7 jokes	amod
7	jokes	joke	NOUN	Number=Plur	3 paid	obl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	pay	present · passive		Bots				for old jokes	vn pay-68-1 «NP V NP NP PP.theme»: subject=Recipient more=Asset for joke=Theme

Option 3

Old jokes are the only funny ones

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Old	old	ADJ	Degree=Pos	2 jokes	amod
2	jokes	joke	NOUN	Number=Plur	7 ones	nsubj
3	are	be	AUX	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	7 ones	cop
4	the	the	DET	Definite=Def PronType=Art	7 ones	det
5	only	only	ADJ	Degree=Pos	7 ones	amod
6	funny	funny	ADJ	Degree=Pos	7 ones	amod
7	ones	one	NOUN	Number=Plur	root	root

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is a	present	Old jokes	the only funny ones					tree rules

Option 4

Bots have only one joke book, and they read it again and again

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Bots	bot	NOUN	Number=Plur	2 have	nsubj
2	have	have	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	root	root
3	only	only	ADV	_	4 one	advmod
4	one	one	NUM	NumForm=Word NumType=Card	6 book	nummod
5	joke	joke	NOUN	Number=Sing	6 book	compound
6	book	book	NOUN	Number=Sing	2 have	obj
7	,	,	PUNCT	_	10 read	punct
8	and	and	CCONJ	_	10 read	cc
9	they	they	PRON	Case=Nom Number=Plur Person=3 PronType=Prs	10 read	nsubj
10	read	read	VERB	Mood=Ind Number=Plur Person=3 Tense=Past VerbForm=Fin	2 have	parataxis
11	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	10 read	obj
12	again	again	ADV	_	10 read	advmod
13	and	and	CCONJ	_	14 again	cc
14	again	again	ADV	_	12 again	conj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	have	present	Bots	one joke book					vn birth-28.2-1 «NP V NP»: agent=Agent book=Patient
2	read	past	Bots = bot	book			again		vn transfer_mesg-37.1.1-1 «NP V NP»: agent=Agent it=Topic

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/t8/