---
title: Which of the following statements most accurately characterises the… — Olympiad: thinking like a machine, Beb… · tree and pragmatics
description: Which of the following statements most accurately characterises the error of the picture sorter that classified a husky upon snow as a wolf? Exam question 3 of lesson 31 «Olympiad: thinking like a machine, Bebras puzzles ★★★» of the AI course of Mova's primary school, with the dependency tree and pr
---

<!-- md -->
[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/questions/ai/31-olympiad-thinking-like-a-machine/e3/)

<!-- crumbs -->
[home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [questions](https://md.mova.elamur.ai/free/en/corpora/questions/) / [AI](https://md.mova.elamur.ai/free/en/corpora/questions/ai/) / [Olympiad: thinking like a machine, Beb…](https://md.mova.elamur.ai/free/en/corpora/questions/ai/31-olympiad-thinking-like-a-machine/) / e3

# Exam question 3 · Olympiad: thinking like a machine, Bebras puzzles ★★★

<!-- .ven lang=en -->
Which of the following statements most accurately characterises the error of the picture sorter that classified a husky upon snow as a wolf?

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 2 · wrong ✗ · **Who acts:** picture sorter · **What happens:** follow, characteris, classify, err · **To what, where:** error, husky

<!-- .vabout -->
This is exam question 3 of lesson 31 «Olympiad: thinking like a machine, Bebras puzzles ★★★» 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](https://md.mova.elamur.ai/free/en/school-run/ai/31-olympiad-thinking-like-a-machine/#e3).

## The question {#question}

```conllu
# sent_id = question:ai:31-olympiad-thinking-like-a-machine:e3:1
# text = Which of the following statements most accurately characterises the error of the picture sorter that classified a husky upon snow as a wolf?
1	Which	which	PRON	WDT	PronType=Rel	8	nsubj	_	_
2	of	of	ADP	IN	_	5	case	_	_
3	the	the	DET	DT	Definite=Def|PronType=Art	5	det	_	_
4	following	follow	VERB	VBG	VerbForm=Ger	5	amod	_	_
5	statements	statement	NOUN	NNS	Number=Plur	8	obl	_	_
6	most	most	ADV	RBS	Degree=Sup	7	advmod	_	_
7	accurately	accurately	ADV	RB	_	8	advmod	_	_
8	characterises	characteris	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
9	the	the	DET	DT	Definite=Def|PronType=Art	10	det	_	_
10	error	error	NOUN	NN	Number=Sing	8	obj	_	_
11	of	of	ADP	IN	_	14	case	_	_
12	the	the	DET	DT	Definite=Def|PronType=Art	14	det	_	_
13	picture	picture	NOUN	NN	Number=Sing	14	compound	_	_
14	sorter	sorter	NOUN	NN	Number=Sing	10	nmod	_	_
15	that	that	PRON	WDT	PronType=Rel	16	nsubj	_	_
16	classified	classify	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	14	acl:relcl	_	_
17	a	a	DET	DT	Definite=Ind|PronType=Art	18	det	_	_
18	husky	husky	NOUN	NN	Number=Sing	16	obj	_	_
19	upon	upon	ADP	IN	_	20	case	_	_
20	snow	snow	NOUN	NN	Number=Sing	18	nmod	_	_
21	as	as	ADP	IN	_	23	case	_	_
22	a	a	DET	DT	Definite=Ind|PronType=Art	23	det	_	_
23	wolf	wolf	NOUN	NN	Number=Sing	16	obl	_	SpaceAfter=No
24	?	?	PUNCT	.	_	8	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **follow** | gerund |  |  |  |  |  |  | vn occur-48.3-1 «NP V»: agent=Theme |
| 2 | **characteris** | present |  | the error of the picture sorter |  |  |  | of the following statements; accurately *property* | tree rules |
| 3 | **classify** | past | the picture sorter | a husky |  |  |  | upon snow; as a wolf | vn characterize-29.2 «NP V NP S\_ING»: agent=Agent husky=Theme as wolf=Attribute |
| 4 | **err** |  | the picture sorter |  |  |  |  |  | nom error «act intransitive»: of=agent |

<!-- .note -->
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 {#options}

### Option 1 · ← Mova's choice {#o1}

<!-- .ven lang=en -->
It had been trained exclusively upon photographs of domestic cats

```conllu
# sent_id = question:ai:31-olympiad-thinking-like-a-machine:e3:o1:1
# text = It had been trained exclusively upon photographs of domestic cats
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	4	nsubj:pass	_	_
2	had	have	AUX	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	4	aux	_	_
3	been	be	AUX	VBN	Tense=Past|VerbForm=Part	4	aux:pass	_	_
4	trained	train	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
5	exclusively	exclusively	ADV	RB	_	4	advmod	_	_
6	upon	upon	ADP	IN	_	7	case	_	_
7	photographs	photograph	NOUN	NNS	Number=Plur	4	obl	_	_
8	of	of	ADP	IN	_	10	case	_	_
9	domestic	domestic	ADJ	JJ	Degree=Pos	10	amod	_	_
10	cats	cat	NOUN	NNS	Number=Plur	7	nmod	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **train** | past · perfect · passive |  | It |  |  |  | upon photographs of domestic cats; exclusively *property* | vn hire-13.5.3 «NP V NP»: subject=Theme |

### Option 2 · ✓ the right answer {#o2}

<!-- .ven lang=en -->
It had associated the snowy background, rather than the animal, with wolves

```conllu
# sent_id = question:ai:31-olympiad-thinking-like-a-machine:e3:o2:1
# text = It had associated the snowy background, rather than the animal, with wolves
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	3	nsubj:pass	_	_
2	had	have	AUX	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	3	aux	_	_
3	associated	associate	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
4	the	the	DET	DT	Definite=Def|PronType=Art	6	det	_	_
5	snowy	snowy	ADJ	JJ	Degree=Pos	6	amod	_	_
6	background	background	NOUN	NN	Number=Sing	3	obj	_	SpaceAfter=No
7	,	,	PUNCT	,	_	11	punct	_	_
8	rather	rather	ADV	RB	ExtPos=CCONJ	11	cc	_	_
9	than	than	ADP	IN	_	8	fixed	_	_
10	the	the	DET	DT	Definite=Def|PronType=Art	11	det	_	_
11	animal	animal	NOUN	NN	Number=Sing	3	conj	_	SpaceAfter=No
12	,	,	PUNCT	,	_	14	punct	_	_
13	with	with	ADP	IN	_	14	case	_	_
14	wolves	wolf	NOUN	NNS	Number=Plur	3	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **associate** | past · perfect · passive |  | It |  |  |  | with wolves | tree rules |

### Option 3 {#o3}

<!-- .ven lang=en -->
It had been instructed deliberately to confuse the two species

```conllu
# sent_id = question:ai:31-olympiad-thinking-like-a-machine:e3:o3:1
# text = It had been instructed deliberately to confuse the two species
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	4	nsubj:pass	_	_
2	had	have	AUX	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	4	aux	_	_
3	been	be	AUX	VBN	Tense=Past|VerbForm=Part	4	aux:pass	_	_
4	instructed	instruct	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
5	deliberately	deliberately	ADV	RB	_	4	advmod	_	_
6	to	to	PART	TO	_	7	mark	_	_
7	confuse	confuse	VERB	VB	VerbForm=Inf	4	advcl	_	_
8	the	the	DET	DT	Definite=Def|PronType=Art	10	det	_	_
9	two	two	NUM	CD	NumForm=Word|NumType=Card	10	nummod	_	_
10	species	species	NOUN	NNS	Number=Plur	7	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **instruct** *speech: other* | past · perfect · passive |  | It |  |  |  | deliberately *property* | vn advise-37.9-1 «NP V NP.recipient»: subject=Recipient |
| 2 | **confuse** | to-infinitive |  | the two species |  |  |  |  | vn amalgamate-22.2-2 «NP V NP»: agent=Agent species=Patient |

### Option 4 {#o4}

<!-- .ven lang=en -->
It had insufficient light by which to perceive the photograph

```conllu
# sent_id = question:ai:31-olympiad-thinking-like-a-machine:e3:o4:1
# text = It had insufficient light by which to perceive the photograph
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	2	nsubj	_	_
2	had	have	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	0	root	_	_
3	insufficient	insufficient	ADJ	JJ	Degree=Pos	4	amod	_	_
4	light	light	NOUN	NN	Number=Sing	2	obj	_	_
5	by	by	ADP	IN	_	6	case	_	_
6	which	which	PRON	WDT	PronType=Rel	2	obj	_	_
7	to	to	PART	TO	_	8	mark	_	_
8	perceive	perceive	VERB	VB	VerbForm=Inf	2	advcl	_	_
9	the	the	DET	DT	Definite=Def|PronType=Art	10	det	_	_
10	photograph	photograph	NOUN	NN	Number=Sing	8	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **have** | past | It | insufficient light |  |  |  |  | tree rules |
| 2 | **perceive** | to-infinitive |  | the photograph |  |  |  |  | vn see-30.1-1 «NP V S»: agent=Experiencer photograph=Stimulus |

<!-- div src -->

**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.

<!-- /div -->

<!-- pn -->
- ← previous: [Olympiad: thinking like a machine, Beb…, exam 2](https://md.mova.elamur.ai/free/en/corpora/questions/ai/31-olympiad-thinking-like-a-machine/e2/)
- next →: [Olympiad: thinking like a machine, Beb…, exam 4](https://md.mova.elamur.ai/free/en/corpora/questions/ai/31-olympiad-thinking-like-a-machine/e4/)
- ↑ back to [Olympiad: thinking like a machine, Bebras puzzles ★★★](https://md.mova.elamur.ai/free/en/corpora/questions/ai/31-olympiad-thinking-like-a-machine/)