--- title: Now, when you ask something, it builds an answer a little piece at a… — How a language model learns: guessing the next w… · tree and pragmatics description: Now, when you ask something, it builds an answer a little piece at a time, each time picking a word that fits well after the words before it. Who acts: you, chatbot, word. A sentence of the lesson «How a language model learns: guessing the next word» of the ai course of Mova's primary school with it --- [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/2/) [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/) / 2 # How a language model learns: guessing the next word, sentence 2 Now, when you ask something, it builds an answer a little piece at a time, each time picking a word that fits well after the words before it. **Who acts:** you, chatbot, word · **What happens:** ask, build, pick, fit · **To what, where:** something, answer, word, chatbot 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 (you, chatbot, word), 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:2 # text = Now, when you ask something, it builds an answer a little piece at a time, each time picking a word that fits well after the words before it. # 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 ×1 1 Now now ADV RB _ 9 advmod _ _ 2 , , PUNCT , _ 1 punct _ _ 3 when when ADV WRB _ 5 advmod _ _ 4 you you PRON PRP Case=Nom|Person=2|PronType=Prs 5 nsubj _ _ 5 ask ask VERB VBP Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin 9 advcl _ _ 6 something something PRON NN Number=Sing|PronType=Ind 5 obj _ _ 7 , , PUNCT , _ 5 punct _ _ 8 it it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 9 nsubj _ _ 9 builds build VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 10 an a DET DT Definite=Ind|PronType=Art 11 det _ _ 11 answer answer NOUN NN Number=Sing 9 obj _ _ 12 a a DET DT Definite=Ind|PronType=Art 14 det _ _ 13 little little ADJ JJ Degree=Pos 14 amod _ _ 14 piece piece NOUN NN Number=Sing 9 obj _ _ 15 at at ADP IN _ 17 case _ _ 16 a a DET DT Definite=Ind|PronType=Art 17 det _ _ 17 time time NOUN NN Number=Sing 14 nmod _ _ 18 , , PUNCT , _ 17 punct _ _ 19 each each DET DT PronType=Tot 20 det _ _ 20 time time NOUN NN Number=Sing 17 conj _ _ 21 picking pick VERB VBG VerbForm=Ger 9 advcl _ Agree=R5-strong|Haiku=20:acl 22 a a DET DT Definite=Ind|PronType=Art 23 det _ _ 23 word word NOUN NN Number=Sing 21 obj _ _ 24 that that PRON WDT PronType=Rel 25 nsubj _ _ 25 fits fit VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 23 acl:relcl _ _ 26 well well ADV RB Degree=Pos 25 advmod _ _ 27 after after ADP IN _ 29 case _ _ 28 the the DET DT Definite=Def|PronType=Art 29 det _ _ 29 words word NOUN NNS Number=Plur 25 obl _ _ 30 before before ADP IN _ 31 case _ _ 31 it it PRON PRP Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs 25 obl _ _ 32 . . PUNCT . _ 9 punct _ _ ``` ## Pragmatics {#pragmatics} - form: statement - act: assert - voice: narrator - polarity: none - teacher: kept the draft | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **ask** *speech: ask* | present | you | something | | | | | vn inquire-37.1.2 «NP V NP.recipient»: agent=Agent something=Recipient | | 2 | **build** | present | chatbot | a answer | | | now | | vn build-26.1-1 «NP.asset V NP NP»: agent=Asset answer=Beneficiary piece=Product | | 3 | **pick** | gerund | chatbot *not said here* | a word | | | | | vn chew-39.2 «NP V NP»: agent=Agent word=Patient | | 4 | **fit** | present | a word | | | chatbot | after the words | well *property* | vn funnel-9.3-1 «NP V NP PP.trajectory»: agent=Agent before it=Trajectory | 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. **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:2`. **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 ×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/). - ← previous: [How a language model learns: guessing…, 1](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/1/) - next →: [How a language model learns: guessing…, 3](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/3/) - ↑ back to [the lesson](https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/)