---
title: Which of these did a language model NOT need to learn? — How a language model learns: guessing… · tree and pragmatics
description: Which of these did a language model NOT need to learn? Test 10 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/t10/)

<!-- 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/) / t10

# Test 10 · How a language model learns: guessing the next word

<!-- .ven lang=en -->
Which of these did a language model NOT need to learn?

<!-- .vintro -->
**Mova's choice:** option 4 · **The right answer:** option 1 · wrong ✗ · **What happens:** not need, learn

<!-- .vabout -->
This is test 10 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/#t10).

## The question {#question}

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t10:1
# text = Which of these did a language model NOT need to learn?
1	Which	which	PRON	WDT	PronType=Rel	4	obj	_	_
2	of	of	ADP	IN	_	3	case	_	_
3	these	this	PRON	DT	Number=Plur|PronType=Dem	4	obl	_	_
4	did	do	AUX	VBD	Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin	9	aux	_	_
5	a	a	DET	DT	Definite=Ind|PronType=Art	7	det	_	_
6	language	language	NOUN	NN	Number=Sing	7	compound	_	_
7	model	model	NOUN	NN	Number=Sing	4	obj	_	_
8	NOT	not	PART	RB	Polarity=Neg	9	advmod	_	_
9	need	need	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
10	to	to	PART	TO	_	11	mark	_	_
11	learn	learn	VERB	VB	VerbForm=Inf	9	xcomp	_	SpaceAfter=No
12	?	?	PUNCT	.	_	9	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **not** **need** | past · do-support |  |  |  |  |  |  | vn want-32.1-1-1 «NP V NP S\_INF»: agent=Pivot clause=Theme |
| 2 | **learn** *not said to happen* | to-infinitive |  |  |  |  |  |  | vn learn-14-1 «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 · ✓ the right answer {#o1}

<!-- .ven lang=en -->
A body to feel things with

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t10:o1:1
# text = A body to feel things with
1	A	a	DET	DT	Definite=Ind|PronType=Art	2	det	_	_
2	body	body	NOUN	NN	Number=Sing	4	nsubj	_	_
3	to	to	PART	TO	_	4	mark	_	_
4	feel	feel	VERB	VB	VerbForm=Inf	0	root	_	_
5	things	thing	NOUN	NNS	Number=Plur	4	obj	_	_
6	with	with	ADP	IN	_	4	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **feel** | to-infinitive | a body | things |  |  |  |  | vn hunt-35.1 «NP V NP»: agent=Agent thing=Theme |

### Option 2 {#o2}

<!-- .ven lang=en -->
People to build and train it

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t10:o2:1
# text = People to build and train it
1	People	people	NOUN	NNS	Number=Plur	3	nsubj	_	_
2	to	to	PART	TO	_	3	mark	_	_
3	build	build	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
4	and	and	CCONJ	CC	_	5	cc	_	_
5	train	train	VERB	VB	Mood=Imp|VerbForm=Fin	3	conj	_	_
6	it	it	PRON	PRP	Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs	5	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **build** | to-infinitive | People |  |  |  |  |  | vn calibratable\_cos-45.6.1 «NP.attribute V»: agent=Attribute |
| 2 | **train** | infinitive | People *not said here* | it |  |  |  |  | vn hire-13.5.3 «NP V NP»: agent=Agent it=Theme |

### Option 3 {#o3}

<!-- .ven lang=en -->
Powerful computers to run on

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t10:o3:1
# text = Powerful computers to run on
1	Powerful	powerful	ADJ	JJ	Degree=Pos	2	amod	_	_
2	computers	computer	NOUN	NNS	Number=Plur	0	root	_	_
3	to	to	PART	TO	_	4	mark	_	_
4	run	run	VERB	VB	VerbForm=Inf	2	acl	_	_
5	on	on	ADP	RP	_	4	compound:prt	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **run on** | to-infinitive |  |  |  |  |  |  | vn run-51.3.2-2-1 «NP V»: agent=Theme |

### Option 4 · ← Mova's choice {#o4}

<!-- .ven lang=en -->
Huge amounts of text to learn from

```conllu
# sent_id = question:ai:2-guessing-the-next-word:t10:o4:1
# text = Huge amounts of text to learn from
1	Huge	huge	ADJ	JJ	Degree=Pos	2	amod	_	_
2	amounts	amount	NOUN	NNS	Number=Plur	0	root	_	_
3	of	of	ADP	IN	_	4	case	_	_
4	text	text	NOUN	NN	Number=Sing	2	nmod	_	_
5	to	to	PART	TO	_	6	mark	_	_
6	learn	learn	VERB	VB	VerbForm=Inf	2	acl	_	_
7	from	from	ADP	IN	_	6	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **learn** | to-infinitive |  |  |  |  |  |  | vn learn-14-1 «NP V»: agent=Agent |
| 2 | **amount** |  |  | text |  |  |  |  | nom amount «possession transitive»: of=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 9](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t9/)
- next →: [How a language model learns: guessing…, exam 1](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/e1/)
- ↑ 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/)