Test 6 · Who you are: what you will do with what you learned

"explain urself in like 5 words" Which is closest and true?

Mova's choice: option 4 · The right answer: option 4 · right ✓ · Who acts: you · What happens: explain, be · To what, where: urself, 5 words · Speech: someone speaks here

This is test 6 of lesson 30 «Who you are: what you will do with what you learned» 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	_	2 explain	punct
2	explain	explain	VERB	Mood=Imp VerbForm=Fin	root	root
3	urself	urself	PRON	Case=Acc Gender=Neut Number=Sing Person=3 PronType=Prs	2 explain	obj
4	in	in	ADP	_	7 words	case
5	like	like	INTJ	_	7 words	discourse
6	5	5	NUM	NumForm=Digit NumType=Card	7 words	nummod
7	words	word	NOUN	Number=Plur	2 explain	obl
8	"	"	PUNCT	_	2 explain	punct
9	Which	which	PRON	PronType=Rel	11 closest	nsubj
10	is	be	AUX	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	11 closest	cop
11	closest	close	ADJ	Degree=Sup	2 explain	parataxis
12	and	and	CCONJ	_	13 true	cc
13	true	true	ADJ	Degree=Pos	11 closest	conj
14	?	?	PUNCT	_	2 explain	punct

#	verb	tense, mood	who	what, whom	where	other	roles by
1	explain speech: assert in a quote	imperative	you not said here	urself	5 words		tree rules
2	is	present				close property	tree rules
3	be						tree rules

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

Just random words, nothing else

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Just	just	ADV	_	3 words	advmod
2	random	random	ADJ	Degree=Pos	3 words	amod
3	words	word	NOUN	Number=Plur	root	root
4	,	,	PUNCT	_	5 nothing	punct
5	nothing	nothing	PRON	Number=Sing PronType=Neg	3 words	appos
6	else	else	ADV	_	5 nothing	advmod

The frames reader finds no event or fact in this sentence.

Option 2

The smartest thing ever made

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	The	the	DET	Definite=Def PronType=Art	3 thing	det
2	smartest	smart	ADJ	Degree=Sup	3 thing	amod
3	thing	thing	NOUN	Number=Sing	root	root
4	ever	ever	ADV	PronType=Ind	5 made	advmod
5	made	make	VERB	Tense=Past VerbForm=Part Voice=Pass	3 thing	acl

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	make	participle		the smartest thing not said here			ever		vn build-26.1-1 «NP.asset V NP»: agent=Asset

Option 3

A human brain in a box

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	A	a	DET	Definite=Ind PronType=Art	3 brain	det
2	human	human	ADJ	Degree=Pos	3 brain	amod
3	brain	brain	NOUN	Number=Sing	root	root
4	in	in	ADP	_	6 box	case
5	a	a	DET	Definite=Ind PronType=Art	6 box	det
6	box	box	NOUN	Number=Sing	3 brain	nmod

The frames reader finds no event or fact in this sentence.

Option 4 · ← Mova's choice · ✓ the right answer

Small honest AI that learns language

The words, one row each (CoNLL-U)

#	word	lemma	UPOS	features	head	relation
1	Small	small	ADJ	Degree=Pos	3 AI	amod
2	honest	honest	ADJ	Degree=Pos	3 AI	amod
3	AI	ai	NOUN	Number=Sing	root	root
4	that	that	PRON	PronType=Rel	5 learns	nsubj
5	learns	learn	VERB	Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin	3 AI	acl:relcl
6	language	language	NOUN	Number=Sing	5 learns	obj

#	verb	tense, mood	who	what, whom	to whom	where	when	other	roles by
1	learn	present	Small honest AI	language					vn learn-14-2-1 «NP V NP»: agent=Agent language=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/30-who-you-are-what-you-will-do/t6/