---
title: It writes an answer piece by piece, each time choosing a likely next… — How a language model learns: guessing the next w… · tree and pragmatics
description: It writes an answer piece by piece, each time choosing a likely next word. Who acts: model. A sentence of the lesson «How a language model learns: guessing the next word» of the ai course of Mova's primary school with its dependency tree and the pragmatics of every clause.
---

<!-- md -->
[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/8/)

<!-- crumbs -->
[home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [school](https://md.mova.elamur.ai/free/en/corpora/school/) / [AI](https://md.mova.elamur.ai/free/en/corpora/school/ai/) / [How a language model learns: guessing…](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/) / 8

# How a language model learns: guessing the next word, sentence 8

<!-- .ven lang=en -->
It writes an answer piece by piece, each time choosing a likely next word.

<!-- .vintro -->
**Who acts:** model · **What happens:** write, choose · **To what, where:** answer piece, likely next word

<!-- .vabout -->
This is a sentence of the lesson «How a language model learns: guessing the next word» of the ai course of Mova's primary school. The page gives its syntax tree — a dependency tree in the style of Universal Dependencies — and its pragmatics clause by clause: who acts (model), what happens, when and where, as Mova's frames read it from the tree.

## The tree {#tree}

```conllu
# sent_id = school:ai:002-guessing-the-next-word.lesson:8
# text = It writes an answer piece by piece, each time choosing a likely next word.
# source = school lesson (ours)
# course = ai
# lesson = 002-guessing-the-next-word.lesson
# annotation = Mova annot: Rust (en) → Haiku 5.5 (medium, Batches API) patches; gates UD 2.18; agreed by treeagree rules (Stanza, Trankit, spaCy trf): R5-strong ×2, R7-rel-agree ×1
1	It	it	PRON	PRP	Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs	2	nsubj	_	_
2	writes	write	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
3	an	a	DET	DT	Definite=Ind|PronType=Art	5	det	_	_
4	answer	answer	NOUN	NN	Number=Sing	5	compound	_	_
5	piece	piece	NOUN	NN	Number=Sing	2	obj	_	_
6	by	by	ADP	IN	_	7	case	_	_
7	piece	piece	NOUN	NN	Number=Sing	5	nmod	_	Agree=R5-strong|Haiku=2:obl
8	,	,	PUNCT	,	_	11	punct	_	_
9	each	each	DET	DT	PronType=Tot	10	det	_	_
10	time	time	NOUN	NN	Number=Sing	11	obl:unmarked	_	_
11	choosing	choose	VERB	VBG	Tense=Pres|VerbForm=Part	2	advcl	_	Agree=R7-rel-agree|Haiku=2:conj
12	a	a	DET	DT	Definite=Ind|PronType=Art	15	det	_	_
13	likely	likely	ADJ	JJ	Degree=Pos	15	amod	_	Agree=R5-strong|Haiku=14:advmod|HaikuPos=ADV:RB:_
14	next	next	ADJ	JJ	Degree=Pos	15	amod	_	_
15	word	word	NOUN	NN	Number=Sing	11	obj	_	_
16	.	.	PUNCT	.	_	2	punct	_	_
```

## Pragmatics {#pragmatics}

<!-- .note -->
No stored speech act for this sentence.

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **write** | present | model | a answer piece |  |  |  | by piece | vn scribble-25.2-1 «NP V NP»: agent=Agent piece=Theme |
| 2 | **choose** | gerund | model *not said here* | a likely next word |  |  | time |  | vn get-13.5.1 «NP V NP»: agent=Agent word=Theme |

<!-- .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.

<!-- div src -->

**Licence: [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)**, as the whole of Mova corpus 0.4, of which this treebank (the agreed school, `mova-school-agreed-en.conllu`) is part. The lessons were written for Mova's primary school. Sentence `school:ai:002-guessing-the-next-word.lesson:8`.

**The tree:** Mova annot: Rust (en) → Haiku 5.5 (medium, Batches API) patches; gates UD 2.18; agreed by treeagree rules (Stanza, Trankit, spaCy trf): R5-strong ×2, R7-rel-agree ×1. **The frames** are read from the tree by Mova's frames reader (`prag`) when this page is built, the lesson read in order, so a pronoun may be resolved from an earlier sentence.

See the [release 0.4](https://md.mova.elamur.ai/free/en/releases/0.4/).

<!-- /div -->

<!-- pn -->
- ← previous: [How a language model learns: guessing…, 7](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/7/)
- next →: [How a language model learns: guessing…, 9](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/9/)
- ↑ back to [the lesson](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/)