---
title: What would happen if you left a chatbot app closed for a whole week? — How a language model learns: guessing… · tree and pragmatics
description: What would happen if you left a chatbot app closed for a whole week? Test 2 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/t2/)

<!-- 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/) / t2

# Test 2 · How a language model learns: guessing the next word

<!-- .ven lang=en -->
What would happen if you left a chatbot app closed for a whole week?

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 1 · right ✓ · **Who acts:** you · **What happens:** happen, leave, close · **To what, where:** chatbot app

<!-- .vabout -->
This is test 2 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/#t2).

## The question {#question}

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t2:1
# text = What would happen if you left a chatbot app closed for a whole week?
1	What	what	PRON	WP	PronType=Int	3	nsubj	_	_
2	would	would	AUX	MD	VerbForm=Fin	3	aux	_	_
3	happen	happen	VERB	VB	VerbForm=Inf	0	root	_	_
4	if	if	SCONJ	IN	_	6	mark	_	_
5	you	you	PRON	PRP	Case=Nom|Person=2|PronType=Prs	6	nsubj	_	_
6	left	leave	VERB	VBD	Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin	3	advcl	_	_
7	a	a	DET	DT	Definite=Ind|PronType=Art	9	det	_	_
8	chatbot	chatbot	NOUN	NN	Number=Sing	9	compound	_	_
9	app	app	NOUN	NN	Number=Sing	6	obj	_	_
10	closed	close	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	9	acl	_	_
11	for	for	ADP	IN	_	14	case	_	_
12	a	a	DET	DT	Definite=Ind|PronType=Art	14	det	_	_
13	whole	whole	ADJ	JJ	Degree=Pos	14	amod	_	_
14	week	week	NOUN	NN	Number=Sing	10	obl	_	SpaceAfter=No
15	?	?	PUNCT	.	_	3	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **happen** | would |  |  |  |  |  |  | vn occur-48.3-1 «NP V»: agent=Theme |
| 2 | **leave** *a condition, not said to happen* | past | you | a chatbot app |  |  |  |  | vn keep-15.2 «NP V NP»: agent=Agent app=Theme |
| 3 | **close** | participle |  | a chatbot app *not said here* |  |  | week |  | vn other\_cos-45.4 «NP.patient V»: agent=Patient |

<!-- .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 · ✓ the right answer {#o1}

<!-- .ven lang=en -->
Nothing; it would not miss you or think about you

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t2:o1:1
# text = Nothing; it would not miss you or think about you
1	Nothing	nothing	PRON	NN	Number=Sing|PronType=Neg	0	root	_	SpaceAfter=No
2	;	;	PUNCT	:	_	6	punct	_	_
3	it	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	6	nsubj	_	_
4	would	would	AUX	MD	VerbForm=Fin	6	aux	_	_
5	not	not	PART	RB	Polarity=Neg	6	advmod	_	_
6	miss	miss	VERB	VB	VerbForm=Inf	1	parataxis	_	_
7	you	you	PRON	PRP	Case=Acc|Person=2|PronType=Prs	6	obj	_	_
8	or	or	CCONJ	CC	_	9	cc	_	_
9	think	think	VERB	VB	VerbForm=Inf	6	conj	_	_
10	about	about	ADP	IN	_	11	case	_	_
11	you	you	PRON	PRP	Case=Acc|Person=2|PronType=Prs	9	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **not** **miss** | would | it | you |  |  |  |  | vn admire-31.2 «NP V NP»: agent=Experiencer you=Stimulus |
| 2 | **think** *speech: other* | infinitive |  |  |  |  |  | about you | vn focus-87.1-1 «NP V PP.topic»: agent=Agent about you=Topic |

### Option 2 {#o2}

<!-- .ven lang=en -->
It would dream about your last chat

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t2:o2:1
# text = It would dream about your last chat
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	3	nsubj	_	_
2	would	would	AUX	MD	VerbForm=Fin	3	aux	_	_
3	dream	dream	VERB	VB	VerbForm=Inf	0	root	_	_
4	about	about	ADP	IN	_	7	case	_	_
5	your	your	PRON	PRP$	Case=Gen|Person=2|Poss=Yes|PronType=Prs	7	nmod:poss	_	_
6	last	last	ADJ	JJ	Degree=Pos	7	amod	_	_
7	chat	chat	NOUN	NN	Number=Sing	3	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **dream** | would | It |  |  |  |  | about your last chat | vn cognize-85 «NP V PP.topic»: agent=Agent about chat=Topic |
| 2 | **chat** |  | your |  |  |  |  |  | nom chat «communication intransitive»: poss=agent |

### Option 3 {#o3}

<!-- .ven lang=en -->
It would plan what to say next time

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t2:o3:1
# text = It would plan what to say next time
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	3	nsubj	_	_
2	would	would	AUX	MD	VerbForm=Fin	3	aux	_	_
3	plan	plan	VERB	VB	VerbForm=Inf	0	root	_	_
4	what	what	PRON	WP	PronType=Int	6	obj	_	_
5	to	to	PART	TO	_	6	mark	_	_
6	say	say	VERB	VB	VerbForm=Inf	3	ccomp	_	_
7	next	next	ADJ	JJ	Degree=Pos	8	amod	_	_
8	time	time	NOUN	NN	Number=Sing	6	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **plan** | would | It |  |  |  |  |  | vn intend-61.2-1-1 «NP V S\_INF»: agent=Agent clause=Topic |
| 2 | **say** *speech: assert* *not said to happen* | to-infinitive |  |  |  |  | time |  | vn say-37.7-1-1 «NP V NP.topic»: agent=Agent what=Topic |

### Option 4 {#o4}

<!-- .ven lang=en -->
It would feel lonely and sad, waiting for you to come back

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t2:o4:1
# text = It would feel lonely and sad, waiting for you to come back
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	3	nsubj	_	_
2	would	would	AUX	MD	VerbForm=Fin	3	aux	_	_
3	feel	feel	VERB	VB	VerbForm=Inf	0	root	_	_
4	lonely	lonely	ADJ	JJ	Degree=Pos	3	xcomp	_	_
5	and	and	CCONJ	CC	_	6	cc	_	_
6	sad	sad	ADJ	JJ	Degree=Pos	4	conj	_	SpaceAfter=No
7	,	,	PUNCT	,	_	8	punct	_	_
8	waiting	wait	VERB	VBG	Tense=Pres|VerbForm=Part	3	advcl	_	_
9	for	for	SCONJ	IN	_	12	mark	_	_
10	you	you	PRON	PRP	Case=Nom|Person=2|PronType=Prs	12	nsubj	_	_
11	to	to	PART	TO	_	12	mark	_	_
12	come	come	VERB	VB	VerbForm=Inf	8	advcl	_	_
13	back	back	ADV	RB	_	12	advmod	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **feel** | would | It |  |  |  |  | lonely *property* | vn stimulus\_subject-30.4 «NP V ADJ»: agent=Stimulus |
| 2 | **wait** | gerund |  |  |  |  |  |  | vn exist-47.1 «NP V»: agent=Theme |
| 3 | **come back** | to-infinitive | you |  |  |  |  |  | vn escape-51.1-1 «NP V»: agent=Theme |

<!-- 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 1](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t1/)
- next →: [How a language model learns: guessing…, test 3](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t3/)
- ↑ 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/)