--- title: In a cartoon a chatbot snores in its box at night. What is wrong wit… — How a language model learns: guessing… · tree and pragmatics description: In a cartoon a chatbot snores in its box at night. What is wrong with that? Test 5 of lesson 2 «How a language model learns: guessing the next word» of the AI course of Mova's primary school, with the dependency tree and pragmatics of the question and of each option; Mova's choice was wrong. --- [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t5/) [home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [questions](https://md.mova.elamur.ai/free/en/corpora/questions/) / [AI](https://md.mova.elamur.ai/free/en/corpora/questions/ai/) / [How a language model learns: guessing…](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/) / t5 # Test 5 · How a language model learns: guessing the next word In a cartoon a chatbot snores in its box at night. What is wrong with that? **Mova's choice:** option 2 · **The right answer:** option 4 · wrong ✗ · **Who acts:** chatbot · **What happens:** snore, be This is test 5 of lesson 2 «How a language model learns: guessing the next word» of the AI course of Mova's primary school. The page gives the question's syntax tree — a dependency tree in the style of Universal Dependencies — and its pragmatics clause by clause, then the 4 options as the student saw them, each with its tree and pragmatics. Every text is parsed by Mova itself. How the student answered it, with the score of every option and why: [the test at school](https://md.mova.elamur.ai/free/en/school-run/ai/2-guessing-the-next-word/#t5). ## The question {#question} *Sentence 1:* In a cartoon a chatbot snores in its box at night. ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:1 # text = In a cartoon a chatbot snores in its box at night. 1 In in ADP IN _ 3 case _ _ 2 a a DET DT Definite=Ind|PronType=Art 3 det _ _ 3 cartoon cartoon NOUN NN Number=Sing 6 obl _ _ 4 a a DET DT Definite=Ind|PronType=Art 5 det _ _ 5 chatbot chatbot NOUN NN Number=Sing 6 nsubj _ _ 6 snores snore VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 7 in in ADP IN _ 9 case _ _ 8 its its PRON PRP$ Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs 9 nmod:poss _ _ 9 box box NOUN NN Number=Sing 6 obl _ _ 10 at at ADP IN _ 11 case _ _ 11 night night NOUN NN Number=Sing 6 obl _ SpaceAfter=No 12 . . PUNCT . _ 6 punct _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **snore** | present | a chatbot | | | | night | in chatbot's box; in a cartoon | vn nonverbal\_expression-40.2 «NP V PP.theme»: agent=Agent in cartoon=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. *Sentence 2:* What is wrong with that? ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:2 # text = What is wrong with that? 1 What what PRON WP PronType=Int 3 nsubj _ _ 2 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 cop _ _ 3 wrong wrong ADJ JJ Degree=Pos 0 root _ _ 4 with with ADP IN _ 5 case _ _ 5 that that PRON DT Number=Sing|PronType=Dem 3 obl _ SpaceAfter=No 6 ? ? PUNCT . _ 3 punct _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **is** | present | | | | | | with that; wrong *property* | tree rules | ## The options {#options} ### Option 1 {#o1} Nothing, bots sleep eight hours a night ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:o1:1 # text = Nothing, bots sleep eight hours a night 1 Nothing nothing PRON NN Number=Sing|PronType=Neg 4 vocative _ SpaceAfter=No 2 , , PUNCT , _ 1 punct _ _ 3 bots bot NOUN NNS Number=Plur 4 nsubj _ _ 4 sleep sleep VERB VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 5 eight eight NUM CD NumForm=Word|NumType=Card 6 nummod _ _ 6 hours hour NOUN NNS Number=Plur 4 obl _ _ 7 a a DET DT Definite=Ind|PronType=Art 8 det _ _ 8 night night NOUN NN Number=Sing 4 obl:unmarked _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **sleep** | present | bots | | | | hour; night | Nothing *vocative* | vn snooze-40.4-1 «NP V»: agent=Agent | ### Option 2 · ← Mova's choice {#o2} Chatbots only snore in the morning ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:o2:1 # text = Chatbots only snore in the morning 1 Chatbots chatbot NOUN NNS Number=Plur 3 nsubj _ _ 2 only only ADV RB _ 3 advmod _ _ 3 snore snore VERB VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 4 in in ADP IN _ 6 case _ _ 5 the the DET DT Definite=Def|PronType=Art 6 det _ _ 6 morning morning NOUN NN Number=Sing 3 obl _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **snore** | present | Chatbots | | | | morning | | vn nonverbal\_expression-40.2 «NP V»: agent=Agent | ### Option 3 {#o3} Bots dream but never snore ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:o3:1 # text = Bots dream but never snore 1 Bots bot NOUN NNS Number=Plur 2 nsubj _ _ 2 dream dream VERB VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 3 but but CCONJ CC _ 5 cc _ _ 4 never never ADV RB PronType=Neg 5 advmod _ _ 5 snore snore VERB VB VerbForm=Inf 2 conj _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **dream** | present | Bots | | | | | | vn cognize-85 «NP V PP.topic»: agent=Agent | | 2 | **not** **snore** | infinitive | Bots *not said here* | | | | | | vn nonverbal\_expression-40.2 «NP V»: agent=Agent | ### Option 4 · ✓ the right answer {#o4} A program that is not running does nothing at all ```conllu # sent_id = question:ai:2-guessing-the-next-word:t5:o4:1 # text = A program that is not running does nothing at all 1 A a DET DT Definite=Ind|PronType=Art 2 det _ _ 2 program program NOUN NN Number=Sing 7 nsubj _ _ 3 that that PRON WDT PronType=Rel 6 nsubj _ _ 4 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 6 aux _ _ 5 not not PART RB Polarity=Neg 6 advmod _ _ 6 running run VERB VBG Tense=Pres|VerbForm=Part 2 acl:relcl _ _ 7 does do VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 8 nothing nothing PRON NN Number=Sing|PronType=Neg 7 obj _ _ 9 at at ADP IN _ 10 case _ _ 10 all all DET DT PronType=Tot 8 nmod _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **not** **run** | present · progressive | a program | | | | | | vn run-51.3.2-2-1 «NP V»: agent=Theme | | 2 | **do** | present | a program | nothing | | all | | | vn act-114-1 «NP V NP»: agent=Agent nothing=Eventuality | **Text:** the tests of Mova's primary school, written for Mova (`world/data/school/`), as the course runner gave them to the student. **Trees:** Mova's own parse — the `en` model on the CPU, when the site is built — not checked by a teacher; they may be wrong. **Frames:** Mova's frames reader (`prag`), each text read on its own. Elamur Cosmic License. - ← previous: [How a language model learns: guessing…, test 4](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t4/) - next →: [How a language model learns: guessing…, test 6](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t6/) - ↑ back to [How a language model learns: guessing the next word](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/)