How a language model learns: guessing the next word, sentence 9
Its training text stops at a certain date, so a bot without a clock or web search may not know today's time or news.
Who acts: training text, bot · What happens: stop, not know · To what, where: certain date
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 (training text, bot), 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 | Its | its | PRON | Case=Gen Gender=Neut Number=Sing Person=3 Poss=Yes PronType=Prs | 3 text | nmod:poss |
| 2 | training | training | NOUN | Number=Sing | 3 text | compound |
| 3 | text | text | NOUN | Number=Sing | 4 stops | nsubj |
| 4 | stops | stop | VERB | Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin | root | root |
| 5 | at | at | ADP | _ | 8 date | case |
| 6 | a | a | DET | Definite=Ind PronType=Art | 8 date | det |
| 7 | certain | certain | ADJ | Degree=Pos | 8 date | amod |
| 8 | date | date | NOUN | Number=Sing | 4 stops | obl |
| 9 | , | , | PUNCT | _ | 4 stops | punct |
| 10 | so | so | ADV | _ | 21 know | advmod |
| 11 | a | a | DET | Definite=Ind PronType=Art | 12 bot | det |
| 12 | bot | bot | NOUN | Number=Sing | 21 know | nsubj |
| 13 | without | without | ADP | _ | 15 clock | case |
| 14 | a | a | DET | Definite=Ind PronType=Art | 15 clock | det |
| 15 | clock | clock | NOUN | Number=Sing | 12 bot | nmod |
| 16 | or | or | CCONJ | _ | 18 search | cc |
| 17 | web | web | NOUN | Number=Sing | 18 search | compound |
| 18 | search | search | NOUN | Number=Sing | 15 clock | conj |
| 19 | may | may | AUX | VerbForm=Fin | 21 know | aux |
| 20 | not | not | PART | Polarity=Neg | 21 know | advmod |
| 21 | know | know | VERB | VerbForm=Inf | 4 stops | advcl |
| 22 | today | today | NOUN | Number=Sing | 24 time | nmod:poss |
| 23 | 's | 's | PART | _ | 22 today | case |
| 24 | time | time | NOUN | Number=Sing | 21 know | obj |
| 25 | or | or | CCONJ | _ | 26 news | cc |
| 26 | news | news | NOUN | Number=Sing | 24 time | conj |
| 27 | . | . | PUNCT | _ | 4 stops | punct |
Pragmatics
No stored speech act for this sentence.
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
|---|---|---|---|---|---|---|---|---|---|
| 1 | stop | present | model's training text | a certain date | vn lodge-46 «NP V PP.location»: agent=Theme at date=Location | ||||
| 2 | not know | may | a bot without a clock or web search | time | vn comprehend-87.2-1-1-1 «NP V»: agent=Experiencer |
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:9.
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/9/