Test 1 · Voice assistants and recommendations

"why does the speaker keep getting nan's songs wrong, is it deaf" Best answer?

Mova's choice: option 1 · The right answer: option 2 · wrong ✗ · Who acts: speaker, nan · What happens: do, keep, get, be, sing · To what, where: songs · Speech: someone speaks here

This is test 1 of lesson 17 «Voice assistants and recommendations» 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	"	"	PUNCT	_	3 does	punct
2	why	why	ADV	PronType=Int	3 does	advmod
3	does	do	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	the	the	DET	Definite=Def PronType=Art	5 speaker	det
5	speaker	speaker	NOUN	Number=Sing	6 keep	nsubj
6	keep	keep	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	3 does	ccomp
7	getting	get	VERB	VerbForm=Ger	6 keep	xcomp
8	nan	nan	NOUN	Number=Sing	10 songs	nmod:poss
9	's	's	PART	_	8 nan	case
10	songs	song	NOUN	Number=Plur	7 getting	obj
11	wrong	wrong	ADJ	Degree=Pos	7 getting	xcomp
12	,	,	PUNCT	_	15 deaf	punct
13	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	15 deaf	cop
14	it	it	PRON	Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs	15 deaf	nsubj
15	deaf	deaf	ADJ	Degree=Pos	3 does	conj
16	"	"	PUNCT	_	18 answer	punct
17	Best	good	ADJ	Degree=Sup	18 answer	amod
18	answer	answer	NOUN	Number=Sing	15 deaf	conj
19	?	?	PUNCT	_	3 does	punct

#	verb	tense, mood	who	what, whom	other	roles by
1	do in a quote	present				tree rules
2	keep in a quote	present	the speaker			tree rules
3	get in a quote	gerund	the speaker not said here	nan's songs	wrong property	vn comprehend-87.2-1 «NP V NP»: agent=Experiencer song=Stimulus
4	is in a quote	present	speaker		deaf property	tree rules
5	sing in a quote		nan			nom song «communication intransitive»: 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.

The options

Option 1 · ← Mova's choice

It hears perfectly well but just doesn't like her kind of music

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 hears	nsubj
2	hears	hear	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
3	perfectly	perfectly	ADV	_	4 well	advmod
4	well	well	ADV	Degree=Pos	2 hears	advmod
5	but	but	CCONJ	_	9 like	cc
6	just	just	ADV	_	9 like	advmod
7	does	do	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	9 like	aux
8	n't	not	PART	Polarity=Neg	9 like	advmod
9	like	like	VERB	VerbForm=Inf	2 hears	conj
10	her	her	PRON	Case=Gen Gender=Fem Number=Sing Person=3 Poss=Yes PronType=Prs	11 kind	nmod:poss
11	kind	kind	NOUN	Number=Sing	9 like	obj
12	of	of	ADP	_	13 music	case
13	music	music	NOUN	Number=Sing	11 kind	nmod

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	hear	present	It					well property	vn see-30.1-1-1 «NP V PP.stimulus»: agent=Experiencer
2	not like	present · do-support		her kind of music					vn want-32.1-1-1 «NP V NP ADV»: agent=Pivot kind=Theme

Option 2 · ✓ the right answer

It guesses words from sounds, and accents and noise trip it up

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 guesses	nsubj
2	guesses	guess	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
3	words	word	NOUN	Number=Plur	2 guesses	obj
4	from	from	ADP	_	5 sounds	case
5	sounds	sound	NOUN	Number=Plur	3 words	nmod
6	,	,	PUNCT	_	11 trip	punct
7	and	and	CCONJ	_	11 trip	cc
8	accents	accent	NOUN	Number=Plur	11 trip	nsubj
9	and	and	CCONJ	_	10 noise	cc
10	noise	noise	NOUN	Number=Sing	8 accents	conj
11	trip	trip	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	2 guesses	conj
12	it	it	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	11 trip	obj
13	up	up	ADP	_	11 trip	compound:prt

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	guess	present	It	words		sounds			vn conjecture-29.5-1 «NP V NP»: agent=Agent word=Theme
2	trip up	present	accents and noise	noise					vn run-51.3.2-2 «NP V NP»: agent=Agent it=Theme

Option 3

It only understands young people's voices

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	3 understands	nsubj
2	only	only	ADV	_	3 understands	advmod
3	understands	understand	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	root	root
4	young	young	ADJ	Degree=Pos	5 people	amod
5	people	people	NOUN	Number=Plur	7 voices	nmod:poss
6	's	's	PART	_	5 people	case
7	voices	voice	NOUN	Number=Plur	3 understands	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	understand	present	It	young people's voices					vn comprehend-87.2-1-1-1 «NP V NP PP.attribute»: agent=Experiencer voice=Stimulus

Option 4

It is deaf, speakers have no microphones

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	3 deaf	nsubj
2	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 deaf	cop
3	deaf	deaf	ADJ	Degree=Pos	root	root
4	,	,	PUNCT	_	6 have	punct
5	speakers	speaker	NOUN	Number=Plur	6 have	nsubj
6	have	have	VERB	Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin	3 deaf	parataxis
7	no	no	DET	PronType=Neg	8 microphones	det
8	microphones	microphone	NOUN	Number=Plur	6 have	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	is	present	It					deaf property	tree rules
2	have	present	speakers	no microphones					vn birth-28.2-1 «NP V NP»: agent=Agent microphone=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/17-voice-assistants-recommendations/t1/