---
title: Why do words appear one after another when a bot answers? — How a language model learns: guessing… · tree and pragmatics
description: Why do words appear one after another when a bot answers? Test 9 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 wrong.
---

<!-- 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/t9/)

<!-- 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/) / t9

# Test 9 · How a language model learns: guessing the next word

<!-- .ven lang=en -->
Why do words appear one after another when a bot answers?

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 3 · wrong ✗ · **Who acts:** words, bot · **What happens:** appear, answer · **To what, where:** one

<!-- .vabout -->
This is test 9 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/#t9).

## The question {#question}

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t9:1
# text = Why do words appear one after another when a bot answers?
1	Why	why	ADV	WRB	PronType=Int	4	advmod	_	_
2	do	do	AUX	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	4	aux	_	_
3	words	word	NOUN	NNS	Number=Plur	4	nsubj	_	_
4	appear	appear	VERB	VB	VerbForm=Inf	0	root	_	_
5	one	one	NUM	CD	NumForm=Word|NumType=Card	4	obj	_	_
6	after	after	ADP	IN	_	7	case	_	_
7	another	another	DET	DT	PronType=Ind	4	obl	_	_
8	when	when	ADV	WRB	PronType=Int	11	advmod	_	_
9	a	a	DET	DT	Definite=Ind|PronType=Art	10	det	_	_
10	bot	bot	NOUN	NN	Number=Sing	11	nsubj	_	_
11	answers	answer	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	parataxis	_	SpaceAfter=No
12	?	?	PUNCT	.	_	4	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **appear** | present · do-support | words | one |  |  | after another |  | vn appear-48.1.1 «PP.location V NP»: agent=Location one=Theme |
| 2 | **answer** *speech: assert* | present | a bot |  |  |  |  |  | vn reciprocate-112-1 «NP V»: agent=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 is waiting for you to read each word

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t9:o1:1
# text = It is waiting for you to read each word
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	3	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	3	aux	_	_
3	waiting	wait	VERB	VBG	Tense=Pres|VerbForm=Part	0	root	_	_
4	for	for	SCONJ	IN	_	7	mark	_	_
5	you	you	PRON	PRP	Case=Nom|Person=2|PronType=Prs	7	nsubj	_	_
6	to	to	PART	TO	_	7	mark	_	_
7	read	read	VERB	VB	VerbForm=Inf	3	advcl	_	_
8	each	each	DET	DT	PronType=Tot	9	det	_	_
9	word	word	NOUN	NN	Number=Sing	7	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **wait** | present · progressive | It |  |  |  |  |  | vn exist-47.1 «NP V»: agent=Theme |
| 2 | **read** | to-infinitive | you | each word |  |  |  |  | vn transfer\_mesg-37.1.1-1 «NP V NP»: agent=Agent word=Topic |

### Option 2 {#o2}

<!-- .ven lang=en -->
The internet is too slow to send a whole sentence at once

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t9:o2:1
# text = The internet is too slow to send a whole sentence at once
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	internet	internet	NOUN	NN	Number=Sing	5	nsubj	_	_
3	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	5	cop	_	_
4	too	too	ADV	RB	_	5	advmod	_	_
5	slow	slow	ADJ	JJ	Degree=Pos	0	root	_	_
6	to	to	PART	TO	_	7	mark	_	_
7	send	send	VERB	VB	VerbForm=Inf	5	xcomp	_	_
8	a	a	DET	DT	Definite=Ind|PronType=Art	10	det	_	_
9	whole	whole	ADJ	JJ	Degree=Pos	10	amod	_	_
10	sentence	sentence	NOUN	NN	Number=Sing	7	obj	_	_
11	at	at	ADP	IN	_	12	case	_	_
12	once	once	ADV	RB	NumForm=Word|NumType=Mult	7	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is** | present | the internet |  |  |  |  | slow *property* | tree rules |
| 2 | **send** | to-infinitive | the internet *not said here* | a whole sentence |  |  |  |  | vn confine-92-1 «NP V NP»: agent=Agent sentence=Theme |

### Option 3 · ✓ the right answer {#o3}

<!-- .ven lang=en -->
It works out the answer in pieces and shows them as they come

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t9:o3:1
# text = It works out the answer in pieces and shows them as they come
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	2	nsubj	_	_
2	works	work	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
3	out	out	ADP	RP	_	2	compound:prt	_	_
4	the	the	DET	DT	Definite=Def|PronType=Art	5	det	_	_
5	answer	answer	NOUN	NN	Number=Sing	2	obj	_	_
6	in	in	ADP	IN	_	7	case	_	_
7	pieces	piece	NOUN	NNS	Number=Plur	5	nmod	_	_
8	and	and	CCONJ	CC	_	9	cc	_	_
9	shows	show	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	2	conj	_	_
10	them	they	PRON	PRP	Case=Acc|Number=Plur|Person=3|PronType=Prs	9	obj	_	_
11	as	as	SCONJ	IN	_	13	mark	_	_
12	they	they	PRON	PRP	Case=Nom|Number=Plur|Person=3|PronType=Prs	13	nsubj	_	_
13	come	come	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	9	advcl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **work out** | present | It | the answer |  | pieces |  |  | vn discover-84 «NP V NP»: agent=Agent answer=Topic |
| 2 | **show** | present |  | pieces *= piece* |  |  |  |  | vn transfer\_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent they=Recipient |
| 3 | **come** | present | pieces *= piece* |  |  |  |  |  | vn escape-51.1-1 «NP V»: agent=Theme |

### Option 4 {#o4}

<!-- .ven lang=en -->
It is a real person somewhere typing as fast as they possibly can for you

<!-- fold The tree, 15 words -->
```conllu
# sent_id = question:ai:2-guessing-the-next-word:t9:o4:1
# text = It is a real person somewhere typing as fast as they possibly can for you
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	real	real	ADJ	JJ	Degree=Pos	5	amod	_	_
5	person	person	NOUN	NN	Number=Sing	0	root	_	_
6	somewhere	somewhere	ADV	RB	PronType=Ind	5	advmod	_	_
7	typing	type	VERB	VBG	VerbForm=Ger	5	acl	_	_
8	as	as	ADV	RB	_	9	advmod	_	_
9	fast	fast	ADV	RB	Degree=Pos	7	advmod	_	_
10	as	as	SCONJ	IN	_	13	mark	_	_
11	they	they	PRON	PRP	Case=Nom|Number=Plur|Person=3|PronType=Prs	13	nsubj	_	_
12	possibly	possibly	ADV	RB	_	13	advmod	_	_
13	can	can	AUX	MD	VerbForm=Fin	9	advcl	_	_
14	for	for	ADP	IN	_	15	case	_	_
15	you	you	PRON	PRP	Case=Acc|Person=2|PronType=Prs	7	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | It | a real person |  |  |  | somewhere *property* | tree rules |
| 2 | **type** | gerund | a real person *not said here* |  |  |  |  | for you; fast *property* | vn scribble-25.2-1 «NP V»: agent=Agent |

<!-- 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 8](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t8/)
- next →: [How a language model learns: guessing…, test 10](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t10/)
- ↑ 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/)