---
title: Ask ten bots for a number from 1 to 10. Which is most likely? — How a language model learns: guessing… · tree and pragmatics
description: Ask ten bots for a number from 1 to 10. Which is most likely? Test 6 of lesson 2 «How a language model learns: guessing the next word» of the AI course of Mova's primary school, with the dependency tree and pragmatics of the question and of each option; Mova's choice was right.
---

<!-- md -->
[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t6/)

<!-- 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/) / [How a language model learns: guessing…](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/) / t6

# Test 6 · How a language model learns: guessing the next word

<!-- .ven lang=en -->
Ask ten bots for a number from 1 to 10. Which is most likely?

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 1 · right ✓ · **Who acts:** you · **What happens:** ask, be · **To what, where:** ten bots

<!-- .vabout -->
This is test 6 of lesson 2 «How a language model learns: guessing the next word» 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](https://md.mova.elamur.ai/free/en/school-run/ai/2-guessing-the-next-word/#t6).

## The question {#question}

<!-- .note -->
*Sentence 1:* Ask ten bots for a number from 1 to 10.

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:1
# text = Ask ten bots for a number from 1 to 10.
1	Ask	ask	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
2	ten	ten	NUM	CD	NumForm=Word|NumType=Card	3	nummod	_	_
3	bots	bot	NOUN	NNS	Number=Plur	1	obj	_	_
4	for	for	ADP	IN	_	6	case	_	_
5	a	a	DET	DT	Definite=Ind|PronType=Art	6	det	_	_
6	number	number	NOUN	NN	Number=Sing	1	obl	_	_
7	from	from	ADP	IN	_	8	case	_	_
8	1	1	NUM	CD	NumForm=Digit|NumType=Card	6	nmod	_	_
9	to	to	ADP	IN	_	10	case	_	_
10	10	10	NUM	CD	NumForm=Digit|NumType=Card	8	nmod	_	SpaceAfter=No
11	.	.	PUNCT	.	_	1	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **ask** *speech: ask* | imperative | you *not said here* | ten bots |  |  |  | for a number from 1 to 10 | vn inquire-37.1.2 «NP V NP.recipient»: agent=Agent bot=Recipient |

<!-- .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.

<!-- .note -->
*Sentence 2:* Which is most likely?

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:2
# text = Which is most likely?
1	Which	which	PRON	WDT	PronType=Rel	4	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
3	most	most	ADV	RBS	Degree=Sup	4	advmod	_	_
4	likely	likely	ADV	RB	_	0	root	_	SpaceAfter=No
5	?	?	PUNCT	.	_	4	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is** | present |  |  |  |  |  | likely *property* | tree rules |

## The options {#options}

### Option 1 · ← Mova's choice · ✓ the right answer {#o1}

<!-- .ven lang=en -->
Many of them give 7, like many people do

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:o1:1
# text = Many of them give 7, like many people do
1	Many	many	ADJ	JJ	Degree=Pos	4	nsubj	_	_
2	of	of	ADP	IN	_	3	case	_	_
3	them	they	PRON	PRP	Case=Acc|Number=Plur|Person=3|PronType=Prs	1	nmod	_	_
4	give	give	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
5	7	7	NUM	CD	NumForm=Digit|NumType=Card	4	obj	_	SpaceAfter=No
6	,	,	PUNCT	,	_	10	punct	_	_
7	like	like	SCONJ	IN	_	10	mark	_	_
8	many	many	ADJ	JJ	Degree=Pos	9	amod	_	_
9	people	people	NOUN	NNS	Number=Plur	10	nsubj	_	_
10	do	do	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	4	advcl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **give** | present | Many of them | 7 |  |  |  |  | vn give-13.1-1 «NP V NP»: agent=Agent 7=Theme |
| 2 | **do** | present | many people |  |  |  |  |  | vn act-114-1 «NP V»: agent=Agent |

### Option 2 {#o2}

<!-- .ven lang=en -->
Each gives a different number, fairly spread out

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:o2:1
# text = Each gives a different number, fairly spread out
1	Each	each	DET	DT	PronType=Tot	2	nsubj	_	_
2	gives	give	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
3	a	a	DET	DT	Definite=Ind|PronType=Art	5	det	_	_
4	different	different	ADJ	JJ	Degree=Pos	5	amod	_	_
5	number	number	NOUN	NN	Number=Sing	2	obj	_	SpaceAfter=No
6	,	,	PUNCT	,	_	8	punct	_	_
7	fairly	fairly	ADV	RB	_	8	advmod	_	_
8	spread	spread	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	2	conj	_	_
9	out	out	ADP	RP	_	8	compound:prt	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **give** | present | Each | a different number |  |  |  |  | vn give-13.1-1 «NP V NP»: agent=Agent number=Theme |
| 2 | **spread out** | participle | Each *not said here* |  |  |  |  | fairly *property* | vn appear-48.1.1 «NP V»: agent=Theme |

### Option 3 {#o3}

<!-- .ven lang=en -->
They all say 10, because it is the biggest one

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:o3:1
# text = They all say 10, because it is the biggest one
1	They	they	PRON	PRP	Case=Nom|Number=Plur|Person=3|PronType=Prs	3	nsubj	_	_
2	all	all	DET	DT	PronType=Tot	3	advmod	_	_
3	say	say	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
4	10	10	NUM	CD	NumForm=Digit|NumType=Card	3	obj	_	SpaceAfter=No
5	,	,	PUNCT	,	_	11	punct	_	_
6	because	because	SCONJ	IN	_	11	mark	_	_
7	it	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	11	nsubj	_	_
8	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	11	cop	_	_
9	the	the	DET	DT	Definite=Def|PronType=Art	11	det	_	_
10	biggest	big	ADJ	JJS	Degree=Sup	11	amod	_	_
11	one	one	NOUN	NN	Number=Sing	3	conj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **say** *speech: assert* | present | They | 10 |  |  |  |  | vn say-37.7-1-1 «NP V NP.topic»: agent=Agent 10=Topic |
| 2 | **is a** | present | it | the biggest one |  |  |  |  | tree rules |

### Option 4 {#o4}

<!-- .ven lang=en -->
They all politely refuse to pick any number

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t6:o4:1
# text = They all politely refuse to pick any number
1	They	they	PRON	PRP	Case=Nom|Number=Plur|Person=3|PronType=Prs	4	nsubj	_	_
2	all	all	DET	DT	PronType=Tot	1	det	_	_
3	politely	politely	ADV	RB	_	4	advmod	_	_
4	refuse	refuse	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
5	to	to	PART	TO	_	6	mark	_	_
6	pick	pick	VERB	VB	VerbForm=Inf	4	xcomp	_	_
7	any	any	DET	DT	PronType=Ind	8	det	_	_
8	number	number	NOUN	NN	Number=Sing	6	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **refuse** | present | They |  |  |  |  | politely *property* | vn reject-77.2 «NP V S\_ING»: agent=Agent clause=Theme |
| 2 | **not** **pick** | to-infinitive | They *not said here* | any number |  |  |  |  | vn chew-39.2 «NP V NP»: agent=Agent number=Patient |

<!-- 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: [How a language model learns: guessing…, test 5](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t5/)
- next →: [How a language model learns: guessing…, test 7](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t7/)
- ↑ back to [How a language model learns: guessing the next word](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/)