How a language model learns: guessing the next word, sentence 6
"Large language model" means a huge program that has learned the patterns of how words are used.
Who acts: Large language model, huge program · What happens: mean, learn, use · To what, where: huge program, patterns, words
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 (Large language model, huge program), what happens, when and where, as Mova's frames read it from the tree.
The tree
The words, one row each (CoNLL-U)
| # | word | lemma | UPOS | features | head | relation |
|---|---|---|---|---|---|---|
| 1 | " | " | PUNCT | _ | 4 model | punct |
| 2 | Large | large | ADJ | Degree=Pos | 4 model | amod |
| 3 | language | language | NOUN | Number=Sing | 4 model | compound |
| 4 | model | model | NOUN | Number=Sing | 6 means | nsubj |
| 5 | " | " | PUNCT | _ | 4 model | punct |
| 6 | means | mean | VERB | Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin | root | root |
| 7 | a | a | DET | Definite=Ind PronType=Art | 9 program | det |
| 8 | huge | huge | ADJ | Degree=Pos | 9 program | amod |
| 9 | program | program | NOUN | Number=Sing | 6 means | obj |
| 10 | that | that | PRON | PronType=Rel | 12 learned | nsubj |
| 11 | has | have | AUX | Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin | 12 learned | aux |
| 12 | learned | learn | VERB | Tense=Past VerbForm=Part | 9 program | acl:relcl |
| 13 | the | the | DET | Definite=Def PronType=Art | 14 patterns | det |
| 14 | patterns | pattern | NOUN | Number=Plur | 12 learned | obj |
| 15 | of | of | SCONJ | _ | 19 used | mark |
| 16 | how | how | ADV | PronType=Int | 19 used | advmod |
| 17 | words | word | NOUN | Number=Plur | 19 used | nsubj:pass |
| 18 | are | be | AUX | Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin | 19 used | aux:pass |
| 19 | used | use | VERB | Tense=Past VerbForm=Part Voice=Pass | 14 patterns | acl |
| 20 | . | . | PUNCT | _ | 6 means | punct |
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 | mean | present | Large language model | a huge program | vn intend-61.2-1 «NP V NP»: agent=Agent program=Topic | ||||
| 2 | learn | present · perfect | a huge program | the patterns | vn learn-14-2-1 «NP V NP»: agent=Agent pattern=Topic | ||||
| 3 | use | present · passive | words | vn eat-39.1 «NP V NP»: subject=Patient |
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, 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:6.
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): no change. 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.
This page in Markdown → https://md.mova.elamur.ai/free/en/corpora/school/ai/2-guessing-the-next-word/6/