--- title: A machine can only learn patterns that are in its examples; if a kin… — Olympiad: thinking like a machine, Bebras puzzle… · tree and pragmatics description: A machine can only learn patterns that are in its examples; if a kind of example is missing, it may get that kind wrong. Who acts: machine, patterns, kind. A sentence of the lesson «Olympiad: thinking like a machine, Bebras puzzles ★★★» of the ai course of Mova's primary school with its dependency t --- [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/9/) [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/) / 9 # Olympiad: thinking like a machine, Bebras puzzles ★★★, sentence 9 A machine can only learn patterns that are in its examples; if a kind of example is missing, it may get that kind wrong. **Who acts:** machine, patterns, kind · **What happens:** learn, be, get · **To what, where:** patterns, examples, kind 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 (machine, patterns, kind), 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:9 # text = A machine can only learn patterns that are in its examples; if a kind of example is missing, it may get that kind wrong. # 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): R2-punct-next ×1, R7-rel-agree ×1 1 A a DET DT Definite=Ind|PronType=Art 2 det _ _ 2 machine machine NOUN NN Number=Sing 5 nsubj _ _ 3 can can AUX MD VerbForm=Fin 5 aux _ _ 4 only only ADV RB _ 5 advmod _ _ 5 learn learn VERB VB VerbForm=Inf 0 root _ _ 6 patterns pattern NOUN NNS Number=Plur 5 obj _ _ 7 that that PRON WDT PronType=Rel 11 nsubj _ _ 8 are be AUX VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 11 cop _ _ 9 in in ADP IN _ 11 case _ _ 10 its its PRON PRP$ Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs 11 nmod:poss _ _ 11 examples example NOUN NNS Number=Plur 6 acl:relcl _ _ 12 ; ; PUNCT , _ 23 punct _ Agree=R2-punct-next|Haiku=5:punct 13 if if SCONJ IN _ 19 mark _ _ 14 a a DET DT Definite=Ind|PronType=Art 15 det _ _ 15 kind kind NOUN NN Number=Sing 19 nsubj _ _ 16 of of ADP IN _ 17 case _ _ 17 example example NOUN NN Number=Sing 15 nmod _ _ 18 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 19 cop _ _ 19 missing missing ADJ JJ Degree=Pos 23 advcl _ _ 20 , , PUNCT , _ 19 punct _ _ 21 it it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 23 nsubj _ _ 22 may may AUX MD VerbForm=Fin 23 aux _ _ 23 get get VERB VB VerbForm=Inf 5 parataxis _ Agree=R7-rel-agree|Haiku=5:conj 24 that that DET DT Number=Sing|PronType=Dem 25 det _ _ 25 kind kind NOUN NN Number=Sing 23 obj _ _ 26 wrong wrong ADJ JJ Degree=Pos 23 xcomp _ _ 27 . . PUNCT . _ 5 punct _ _ ``` ## Pragmatics {#pragmatics} No stored speech act for this sentence. | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **learn** | can | a machine | patterns | | | | | vn learn-14-2-1 «NP V NP»: agent=Agent pattern=Topic | | 2 | **is** | present | patterns | | | machine's examples | | | tree rules | | 3 | **is** *a condition, not said to happen* | present | a kind of example | | | | | missing *property* | tree rules | | 4 | **get** | may | kind | that kind | | | | wrong *property* | vn comprehend-87.2-1 «NP V NP»: agent=Experiencer kind=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: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): R2-punct-next ×1, 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…, 8](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/8/) - next →: [Olympiad: thinking like a machine, Beb…, 10](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/10/) - ↑ back to [the lesson](https://md.mova.elamur.ai/free/en/corpora/school/ai/31-olympiad-thinking-like-a-machine/)