--- title: It is given that numerous distinct programs, when requested to selec… — How a language model learns: guessing… · tree and pragmatics description: It is given that numerous distinct programs, when requested to select a number between one and ten, select seven. Ascertain the most probable explanation. Exam question 4 of lesson 2 «How a language model learns: guessing the next word» of the AI course of Mova's primary school, with the dependency --- [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/e4/) [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/) / e4 # Exam question 4 · How a language model learns: guessing the next word It is given that numerous distinct programs, when requested to select a number between one and ten, select seven. Ascertain the most probable explanation. **Mova's choice:** option 1 · **The right answer:** option 1 · right ✓ · **Who acts:** numerous distinct programs, you · **What happens:** give, request, select, ascertain · **To what, where:** It, number, seven, probable explanation This is exam question 4 of lesson 2 «How a language model learns: guessing the next word» of the AI course of Mova's primary school, asked in stiff, formal language. 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/#e4). ## The question {#question} *Sentence 1:* It is given that numerous distinct programs, when requested to select a number between one and ten, select seven. ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:1 # text = It is given that numerous distinct programs, when requested to select a number between one and ten, select seven. 1 It it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 3 nsubj:pass _ _ 2 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 aux:pass _ _ 3 given give VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 0 root _ _ 4 that that SCONJ IN _ 20 mark _ _ 5 numerous numerous ADJ JJ Degree=Pos 7 amod _ _ 6 distinct distinct ADJ JJ Degree=Pos 7 amod _ _ 7 programs program NOUN NNS Number=Plur 20 nsubj _ SpaceAfter=No 8 , , PUNCT , _ 10 punct _ _ 9 when when ADV WRB PronType=Int 10 advmod _ _ 10 requested request VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 7 acl:relcl _ _ 11 to to PART TO _ 12 mark _ _ 12 select select VERB VB VerbForm=Inf 10 xcomp _ _ 13 a a DET DT Definite=Ind|PronType=Art 14 det _ _ 14 number number NOUN NN Number=Sing 12 obj _ _ 15 between between ADP IN _ 16 case _ _ 16 one one NUM CD NumForm=Word|NumType=Card 14 nmod _ _ 17 and and CCONJ CC _ 18 cc _ _ 18 ten ten NUM CD NumForm=Word|NumType=Card 16 conj _ SpaceAfter=No 19 , , PUNCT , _ 7 punct _ _ 20 select select VERB VB VerbForm=Inf 3 advcl _ _ 21 seven seven NUM CD NumForm=Word|NumType=Card 20 obj _ SpaceAfter=No 22 . . PUNCT . _ 3 punct _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **give** | present · passive | | It | | | | | vn give-13.1-1 «NP V NP»: subject=Theme | | 2 | **request** | participle | | | | | | | vn beg-58.2 «NP V S\_INF»: agent=Agent clause=Topic | | 3 | **select** | to-infinitive | | a number | | | | between one | vn obtain-13.5.2 «NP V NP»: agent=Agent number=Theme | | 4 | **select** | infinitive | numerous distinct programs | seven | | | | | vn obtain-13.5.2 «NP V NP»: agent=Agent seven=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:* Ascertain the most probable explanation. ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:2 # text = Ascertain the most probable explanation. 1 Ascertain ascertain VERB VB Mood=Imp|VerbForm=Fin 0 root _ _ 2 the the DET DT Definite=Def|PronType=Art 5 det _ _ 3 most most ADV RBS Degree=Sup 4 advmod _ _ 4 probable probable ADJ JJ Degree=Pos 5 amod _ _ 5 explanation explanation NOUN NN Number=Sing 1 obj _ SpaceAfter=No 6 . . PUNCT . _ 1 punct _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **ascertain** | imperative | you *not said here* | the probable explanation | | | | | vn discover-84 «NP V NP»: agent=Agent explanation=Topic | ## The options {#options} ### Option 1 · ← Mova's choice · ✓ the right answer {#o1} Such programs tend to reproduce the most frequent human preference ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:o1:1 # text = Such programs tend to reproduce the most frequent human preference 1 Such such ADJ JJ Degree=Pos 2 amod _ _ 2 programs program NOUN NNS Number=Plur 3 nsubj _ _ 3 tend tend VERB VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 4 to to PART TO _ 5 mark _ _ 5 reproduce reproduce VERB VB VerbForm=Inf 3 xcomp _ _ 6 the the DET DT Definite=Def|PronType=Art 10 det _ _ 7 most most ADV RBS Degree=Sup 8 advmod _ _ 8 frequent frequent ADJ JJ Degree=Pos 10 amod _ _ 9 human human ADJ JJ Degree=Pos 10 amod _ _ 10 preference preference NOUN NN Number=Sing 5 obj _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **tend** | present | Such programs | | | | | | tree rules | | 2 | **reproduce** | to-infinitive | Such programs *not said here* | the frequent human preference | | | | | vn other\_cos-45.4 «NP V NP.patient»: agent=Agent preference=Patient | ### Option 2 {#o2} The programs have conferred with one another in advance of the request ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:o2:1 # text = The programs have conferred with one another in advance of the request 1 The the DET DT Definite=Def|PronType=Art 2 det _ _ 2 programs program NOUN NNS Number=Plur 4 nsubj:pass _ _ 3 have have AUX VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 4 aux _ _ 4 conferred confer VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 0 root _ _ 5 with with ADP IN _ 6 case _ _ 6 one one NUM CD NumForm=Word|NumType=Card 4 obl _ _ 7 another another DET DT PronType=Ind 6 fixed _ _ 8 in in ADP IN _ 9 case _ _ 9 advance advance NOUN NN Number=Sing 4 obl _ _ 10 of of ADP IN _ 12 case _ _ 11 the the DET DT Definite=Def|PronType=Art 12 det _ _ 12 request request NOUN NN Number=Sing 9 nmod _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **confer** | present · perfect · passive | | the programs | | advance of the request | | with one | tree rules | | 2 | **advance** | | the request | | | | | | nom advance «event intransitive»: of=agent | ### Option 3 {#o3} Seven is the only integer such programs are able to produce ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:o3:1 # text = Seven is the only integer such programs are able to produce 1 Seven seven NUM CD NumForm=Word|NumType=Card 9 nsubj _ _ 2 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 9 cop _ _ 3 the the DET DT Definite=Def|PronType=Art 5 det _ _ 4 only only ADJ JJ Degree=Pos 5 amod _ _ 5 integer integer NOUN NN Number=Sing 9 nsubj _ _ 6 such such ADJ JJ Degree=Pos 7 amod _ _ 7 programs program NOUN NNS Number=Plur 9 nsubj _ _ 8 are be AUX VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 9 cop _ _ 9 able able ADJ JJ Degree=Pos 0 root _ _ 10 to to PART TO _ 11 mark _ _ 11 produce produce VERB VB VerbForm=Inf 9 xcomp _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **is** | present | Seven | | | | | able *property* | tree rules | | 2 | **produce** | to-infinitive | Seven *not said here* | | | | | | vn create-26.4 «NP V NP»: agent=Agent | ### Option 4 {#o4} The selection is governed by the date of the request ```conllu # sent_id = question:ai:2-guessing-the-next-word:e4:o4:1 # text = The selection is governed by the date of the request 1 The the DET DT Definite=Def|PronType=Art 2 det _ _ 2 selection selection NOUN NN Number=Sing 4 nsubj:pass _ _ 3 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 4 aux:pass _ _ 4 governed govern VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 0 root _ _ 5 by by ADP IN _ 7 case _ _ 6 the the DET DT Definite=Def|PronType=Art 7 det _ _ 7 date date NOUN NN Number=Sing 4 obl _ _ 8 of of ADP IN _ 10 case _ _ 9 the the DET DT Definite=Def|PronType=Art 10 det _ _ 10 request request NOUN NN Number=Sing 7 nmod _ _ ``` | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **govern** | present · passive | the date of the request | the selection | | | | | vn supervision-95.2.2 «NP V NP.theme»: agent=Agent subject=Theme | **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…, exam 3](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/e3/) - next →: [Sounding right and being right, test 1](https://md.mova.elamur.ai/free/en/corpora/questions/ai/3-sounding-right-and-being-right/t1/) - ↑ 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/)