--- title: A next-word guesser is a counting machine: if after "the" it saw "ca… — Olympiad: thinking like a machine, Bebras puzzle… · tree and pragmatics description: A next-word guesser is a counting machine: if after "the" it saw "cat" five times and "dog" twice, it picks "cat", without knowing what a cat is. Who acts: word guesser, guesser. A sentence of the lesson «Olympiad: thinking like a machine, Bebras puzzles ★★★» of the ai course of Mova's primary schoo --- [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/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/) / [Olympiad: thinking like a machine, Beb…](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/) / 2 # Olympiad: thinking like a machine, Bebras puzzles ★★★, sentence 2 A next-word guesser is a counting machine: if after "the" it saw "cat" five times and "dog" twice, it picks "cat", without knowing what a cat is. **Who acts:** word guesser, guesser · **What happens:** be, see, pick, know · **To what, where:** counting machine, cat This is a sentence of the lesson «Olympiad: thinking like a machine, Bebras puzzles ★★★» 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 (word guesser, guesser), what happens, when and where, as Mova's frames read it from the tree. ## The tree {#tree} ```conllu # sent_id = school:ai:031-olympiad-thinking-like-a-machine.lesson:2 # text = A next-word guesser is a counting machine: if after "the" it saw "cat" five times and "dog" twice, it picks "cat", without knowing what a cat is. # source = school lesson (ours) # course = ai # lesson = 031-olympiad-thinking-like-a-machine.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): R7-rel-agree ×1 1 A a DET DT Definite=Ind|PronType=Art 5 det _ _ 2 next next ADJ JJ Degree=Pos 4 amod _ _ 3 - - PUNCT HYPH _ 2 punct _ _ 4 word word NOUN NN Number=Sing 5 compound _ _ 5 guesser guesser NOUN NN Number=Sing 9 nsubj _ _ 6 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 9 cop _ _ 7 a a DET DT Definite=Ind|PronType=Art 9 det _ _ 8 counting count NOUN NN Number=Sing 9 compound _ Agree=R7-rel-agree|Haiku=9:amod|HaikuPos=VERB:VBG:VerbForm=Ger 9 machine machine NOUN NN Number=Sing 0 root _ _ 10 : : PUNCT : _ 9 punct _ _ 11 if if SCONJ IN _ 17 mark _ _ 12 after after SCONJ IN _ 17 mark _ _ 13 " " PUNCT `` _ 17 punct _ _ 14 the the DET DT Definite=Def|PronType=Art 17 det _ _ 15 " " PUNCT `` _ 17 punct _ _ 16 it it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 17 nsubj _ _ 17 saw see VERB VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 9 advcl _ _ 18 " " PUNCT `` _ 19 punct _ _ 19 cat cat NOUN NN Number=Sing 17 obj _ _ 20 " " PUNCT '' _ 19 punct _ _ 21 five five NUM CD NumForm=Word|NumType=Card 22 nummod _ _ 22 times time NOUN NNS Number=Plur 17 obl:unmarked _ _ 23 and and CCONJ CC _ 25 cc _ _ 24 " " PUNCT `` _ 25 punct _ _ 25 dog dog NOUN NN Number=Sing 22 conj _ _ 26 " " PUNCT '' _ 25 punct _ _ 27 twice twice ADV RB NumForm=Word|NumType=Mult 25 advmod _ _ 28 , , PUNCT , _ 30 punct _ _ 29 it it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 30 nsubj _ _ 30 picks pick VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 9 conj _ _ 31 " " PUNCT `` _ 32 punct _ _ 32 cat cat NOUN NN Number=Sing 30 obj _ _ 33 " " PUNCT '' _ 32 punct _ _ 34 , , PUNCT , _ 36 punct _ _ 35 without without SCONJ IN _ 36 mark _ _ 36 knowing know VERB VBG Tense=Pres|VerbForm=Part 30 advcl _ _ 37 what what DET WDT PronType=Int 39 det _ _ 38 a a DET DT Definite=Ind|PronType=Art 39 det _ _ 39 cat cat NOUN NN Number=Sing 36 obj _ _ 40 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 36 aux _ _ 41 . . PUNCT . _ 9 punct _ _ ``` ## Pragmatics {#pragmatics} - form: statement - act: assert - voice: narrator - polarity: none - teacher: changed act=assert | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **is a** | present | a word guesser | a counting machine | | | | | tree rules | | 2 | **see** *a condition, not said to happen* | past | guesser | cat | | | time | | vn comprehend-87.2-1-1 «NP V NP»: agent=Experiencer cat=Stimulus | | 3 | **pick** | present | guesser | cat | | | | | vn chew-39.2 «NP V NP»: agent=Agent cat=Patient | | 4 | **know** | present · progressive | guesser *not said here* | what cat | | | | | vn comprehend-87.2-1-1-1 «NP V NP PP.attribute»: agent=Experiencer cat=Stimulus | 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:031-olympiad-thinking-like-a-machine.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): 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/). - ← previous: [Olympiad: thinking like a machine, Beb…, 1](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/1/) - next →: [Olympiad: thinking like a machine, Beb…, 4](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/4/) - ↑ back to [the lesson](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/)