How a language model learns: guessing the next word, sentence 3
This is why it can say "I understand how you feel" in a kind voice: kind people often write that.
Who acts: This, chatbot, you, kind people · What happens: be, say, understand, feel, write · To what, where: that · Speech: someone speaks here
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 (This, chatbot, you, kind people), 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 | This | this | PRON | Number=Sing PronType=Dem | 3 why | nsubj |
| 2 | is | be | AUX | Mood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin | 3 why | cop |
| 3 | why | why | ADV | PronType=Rel | root | root |
| 4 | it | it | PRON | Case=Nom Gender=Neut Number=Sing Person=3 PronType=Prs | 6 say | nsubj |
| 5 | can | can | AUX | VerbForm=Fin | 6 say | aux |
| 6 | say | say | VERB | VerbForm=Inf | 3 why | advcl:relcl |
| 7 | " | " | PUNCT | _ | 9 understand | punct |
| 8 | I | I | PRON | Case=Nom Number=Sing Person=1 PronType=Prs | 9 understand | nsubj |
| 9 | understand | understand | VERB | Mood=Ind Number=Sing Person=1 Tense=Pres VerbForm=Fin | 6 say | ccomp |
| 10 | how | how | ADV | PronType=Int | 12 feel | advmod |
| 11 | you | you | PRON | Case=Nom Person=2 PronType=Prs | 12 feel | nsubj |
| 12 | feel | feel | VERB | Mood=Ind Number=Sing Person=2 Tense=Pres VerbForm=Fin | 9 understand | ccomp |
| 13 | " | " | PUNCT | _ | 12 feel | punct |
| 14 | in | in | ADP | _ | 17 voice | case |
| 15 | a | a | DET | Definite=Ind PronType=Art | 17 voice | det |
| 16 | kind | kind | NOUN | Number=Sing | 17 voice | compound |
| 17 | voice | voice | NOUN | Number=Sing | 12 feel | obl |
| 18 | : | : | PUNCT | _ | 22 write | punct |
| 19 | kind | kind | ADJ | Degree=Pos | 20 people | amod |
| 20 | people | people | NOUN | Number=Plur | 22 write | nsubj |
| 21 | often | often | ADV | _ | 22 write | advmod |
| 22 | write | write | VERB | Mood=Ind Number=Plur Person=3 Tense=Pres VerbForm=Fin | 3 why | parataxis |
| 23 | that | that | PRON | Number=Sing PronType=Dem | 22 write | obj |
| 24 | . | . | PUNCT | _ | 3 why | punct |
Pragmatics
No stored speech act for this sentence.
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
|---|---|---|---|---|---|---|---|---|---|
| 1 | is | present | This | why property | tree rules | ||||
| 2 | say speech: assert | can | chatbot | vn say-37.7-1-1 «NP V that S»: agent=Agent clause=Topic | |||||
| 3 | understand in a quote | present | chatbot | vn comprehend-87.2-1-1-1 «NP V how S_INF»: agent=Experiencer clause=Stimulus | |||||
| 4 | feel in a quote | present | you | in a kind voice | vn seem-109-1-1 «NP V PP.attribute»: agent=Theme in voice=Attribute | ||||
| 5 | write | present | kind people | that | often property | vn scribble-25.2-1 «NP V NP»: agent=Agent that=Theme |
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:3.
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/3/