---
title: Your friend says the bot is "a she, called Alexa or whatever". What… — How a language model learns: guessing… · tree and pragmatics
description: Your friend says the bot is "a she, called Alexa or whatever". What is closer to the truth? Test 8 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 wa
---

<!-- 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/t8/)

<!-- 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/) / t8

# Test 8 · How a language model learns: guessing the next word

<!-- .ven lang=en -->
Your friend says the bot is "a she, called Alexa or whatever". What is closer to the truth?

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 1 · right ✓ · **Who acts:** friend · **What happens:** say, call, be · **To what, where:** bot · **Speech:** someone speaks here

<!-- .vabout -->
This is test 8 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/#t8).

## The question {#question}

<!-- .note -->
*Sentence 1:* Your friend says the bot is "a she, called Alexa or whatever".

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:1
# text = Your friend says the bot is "a she, called Alexa or whatever".
1	Your	your	PRON	PRP$	Case=Gen|Person=2|Poss=Yes|PronType=Prs	2	nmod:poss	_	_
2	friend	friend	NOUN	NN	Number=Sing	3	nsubj	_	_
3	says	say	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
4	the	the	DET	DT	Definite=Def|PronType=Art	5	det	_	_
5	bot	bot	NOUN	NN	Number=Sing	11	nsubj:pass	_	_
6	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	11	aux:pass	_	_
7	"	"	PUNCT	``	_	11	punct	_	SpaceAfter=No
8	a	a	DET	DT	Definite=Ind|PronType=Art	11	nsubj:pass	_	_
9	she	she	PRON	PRP	Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs	11	nsubj:pass	_	SpaceAfter=No
10	,	,	PUNCT	,	_	11	punct	_	_
11	called	call	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	3	ccomp	_	_
12	Alexa	Alexa	PROPN	NNP	Number=Sing	11	xcomp	_	_
13	or	or	CCONJ	CC	_	14	cc	_	_
14	whatever	whatever	PRON	WP	PronType=Rel	11	xcomp	_	SpaceAfter=No
15	"	"	PUNCT	''	_	14	punct	_	SpaceAfter=No
16	.	.	PUNCT	.	_	3	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **say** *speech: assert* | present | Your friend |  |  |  |  |  | vn say-37.7-1-1 «NP V that S»: agent=Agent clause=Topic |
| 2 | **call** *in a quote* | present · passive |  | the bot |  |  |  |  | vn initiate\_communication-37.4.2-1 «NP V NP.recipient»: subject=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:* What is closer to the truth?

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:2
# text = What is closer to the truth?
1	What	what	PRON	WP	PronType=Int	3	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	3	cop	_	_
3	closer	close	ADJ	JJR	Degree=Cmp	0	root	_	_
4	to	to	ADP	IN	_	6	case	_	_
5	the	the	DET	DT	Definite=Def|PronType=Art	6	det	_	_
6	truth	truth	NOUN	NN	Number=Sing	3	obl	_	SpaceAfter=No
7	?	?	PUNCT	.	_	3	punct	_	_
```

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

## The options {#options}

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

<!-- .ven lang=en -->
A name and voice are labels chosen by its makers

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:o1:1
# text = A name and voice are labels chosen by its makers
1	A	a	DET	DT	Definite=Ind|PronType=Art	2	det	_	_
2	name	name	NOUN	NN	Number=Sing	6	nsubj	_	_
3	and	and	CCONJ	CC	_	4	cc	_	_
4	voice	voice	NOUN	NN	Number=Sing	2	conj	_	_
5	are	be	AUX	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	6	cop	_	_
6	labels	label	NOUN	NNS	Number=Plur	0	root	_	_
7	chosen	choose	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	6	acl	_	_
8	by	by	ADP	IN	_	10	case	_	_
9	its	its	PRON	PRP$	Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs	10	nmod:poss	_	_
10	makers	maker	NOUN	NNS	Number=Plur	7	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | a name and voice | labels |  |  |  |  | tree rules |
| 2 | **choose** | participle |  | labels *not said here* |  |  |  | by voice's makers | vn get-13.5.1 «NP V NP»: agent=Agent |

### Option 2 {#o2}

<!-- .ven lang=en -->
It is a woman who works from home and answers questions all day

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:o2:1
# text = It is a woman who works from home and answers questions all day
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	4	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
3	a	a	DET	DT	Definite=Ind|PronType=Art	4	det	_	_
4	woman	woman	NOUN	NN	Number=Sing	0	root	_	_
5	who	who	PRON	WP	PronType=Rel	6	nsubj	_	_
6	works	work	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	acl:relcl	_	_
7	from	from	ADP	IN	_	8	case	_	_
8	home	home	NOUN	NN	Number=Sing	6	obl	_	_
9	and	and	CCONJ	CC	_	10	cc	_	_
10	answers	answer	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	6	conj	_	_
11	questions	question	NOUN	NNS	Number=Plur	10	obj	_	_
12	all	all	DET	DT	PronType=Tot	13	det	_	_
13	day	day	NOUN	NN	Number=Sing	10	obl:unmarked	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | It | a woman |  |  |  |  | tree rules |
| 2 | **work** | present | a woman |  |  | home |  |  | vn employment-95.3 «NP V»: agent=Agent |
| 3 | **answer** *speech: assert* | present | a woman *not said here* | questions |  |  | day |  | vn reciprocate-112-1 «NP V PP»: agent=Agent question=Eventuality |

### Option 3 {#o3}

<!-- .ven lang=en -->
It chose its own name when it was born

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:o3:1
# text = It chose its own name when it was born
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	2	nsubj	_	_
2	chose	choose	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	0	root	_	_
3	its	its	PRON	PRP$	Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs	5	nmod:poss	_	_
4	own	own	ADJ	JJ	Degree=Pos	5	amod	_	_
5	name	name	NOUN	NN	Number=Sing	2	obj	_	_
6	when	when	ADV	WRB	PronType=Int	9	advmod	_	_
7	it	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	9	nsubj:pass	_	_
8	was	be	AUX	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	9	aux:pass	_	_
9	born	bear	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	2	advcl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **choose** | past | It | its own name |  |  |  |  | vn get-13.5.1 «NP V NP»: agent=Agent name=Theme |
| 2 | **bear** | past · passive |  | name |  |  |  |  | vn birth-28.2-1-1 «NP V NP»: subject=Patient |
| 3 | **name** |  | its *= it* |  |  |  |  |  | nom name «communication transitive»: poss=agent |

### Option 4 {#o4}

<!-- .ven lang=en -->
It is a girl robot hidden in a cupboard

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t8:o4:1
# text = It is a girl robot hidden in a cupboard
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	5	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	5	cop	_	_
3	a	a	DET	DT	Definite=Ind|PronType=Art	5	det	_	_
4	girl	girl	NOUN	NN	Number=Sing	5	compound	_	_
5	robot	robot	NOUN	NN	Number=Sing	0	root	_	_
6	hidden	hide	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	5	acl	_	_
7	in	in	ADP	IN	_	9	case	_	_
8	a	a	DET	DT	Definite=Ind|PronType=Art	9	det	_	_
9	cupboard	cupboard	NOUN	NN	Number=Sing	6	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | It | a girl robot |  |  |  |  | tree rules |
| 2 | **hide** | participle |  | a girl robot *not said here* |  | a cupboard |  |  | vn concealment-16-1 «NP V PP.location»: agent=Agent in cupboard=Location |

<!-- 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 7](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t7/)
- next →: [How a language model learns: guessing…, test 9](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t9/)
- ↑ 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/)

