Mova0.5 pre-release⌕
☰
home / corpora / questions / AI / In the news: tricked bots, real discov… / e1

Exam question 1 · In the news: tricked bots, real discoveries, careful words

Which of the following statements most accurately characterises the reported contribution of artificial intelligence to the study of carbonised ancient scrolls?

Mova's choice: option 1 · The right answer: option 3 · wrong ✗ · What happens: follow, characteris, report, carbonis, contribute, study · To what, where: reported contribution, artificial intelligence, carbonised ancient scrolls

This is exam question 1 of lesson 23 «In the news: tricked bots, real discoveries, careful words» 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.

The question

nsubjcasedetamodobladvmodadvmoddetamodobjcaseamodnmodcasedetoblcaseamodamodnmodpunctrootWhichPRONofADPtheDETfollowingVERBstatementsNOUNmostADVaccuratelyADVcharacterisesVERBtheDETreportedVERBcontributionNOUNofADPartificialADJintelligenceNOUNtoADPtheDETstudyNOUNofADPcarbonisedVERBancientADJscrollsNOUN?PUNCT
The words, one row each (CoNLL-U)
#wordlemmaUPOSfeaturesheadrelation
1WhichwhichPRONPronType=Rel8 characterisesnsubj
2ofofADP_5 statementscase
3thetheDETDefinite=Def PronType=Art5 statementsdet
4followingfollowVERBVerbForm=Ger5 statementsamod
5statementsstatementNOUNNumber=Plur8 characterisesobl
6mostmostADVDegree=Sup7 accuratelyadvmod
7accuratelyaccuratelyADV_8 characterisesadvmod
8characterisescharacterisVERBMood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Finrootroot
9thetheDETDefinite=Def PronType=Art11 contributiondet
10reportedreportVERBTense=Past VerbForm=Part Voice=Pass11 contributionamod
11contributioncontributionNOUNNumber=Sing8 characterisesobj
12ofofADP_14 intelligencecase
13artificialartificialADJDegree=Pos14 intelligenceamod
14intelligenceintelligenceNOUNNumber=Sing11 contributionnmod
15totoADP_17 studycase
16thetheDETDefinite=Def PronType=Art17 studydet
17studystudyNOUNNumber=Sing8 characterisesobl
18ofofADP_21 scrollscase
19carbonisedcarbonisVERBTense=Past VerbForm=Part Voice=Pass21 scrollsamod
20ancientancientADJDegree=Pos21 scrollsamod
21scrollsscrollNOUNNumber=Plur17 studynmod
22??PUNCT_8 characterisespunct
#verbtense, moodwhowhat, whomto whomwherewhenotherroles by
1followgerundvn occur-48.3-1 «NP V»: agent=Theme
2characterispresentthe reported contribution of artificial intelligenceof the following statements; to the study of carbonised ancient scrolls; accurately propertytree rules
3reportparticiplevn characterize-29.2-1-2 «NP V NP»: agent=Agent
4carbonisparticipletree rules
5contributeartificial intelligencenom contribution «act transitive»: of=patient
6studycarbonised ancient scrollsnom study «act transitive»: of=patient

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.

The options

Option 1 · ← Mova's choice

It reconstructed the scrolls physically from their ashes by means of robotic instruments

nsubjdetobjadvmodcasenmod:possoblcaseparataxiscaseamodoblrootItPRONreconstructedVERBtheDETscrollsNOUNphysicallyADVfromADPtheirPRONashesNOUNbyADPmeansVERBofADProboticADJinstrumentsNOUN
The words, one row each (CoNLL-U)
#wordlemmaUPOSfeaturesheadrelation
1ItitPRONCase=Nom Gender=Neut Number=Sing Person=3 PronType=Prs2 reconstructednsubj
2reconstructedreconstructVERBMood=Ind Number=Sing Person=3 Tense=Past VerbForm=Finrootroot
3thetheDETDefinite=Def PronType=Art4 scrollsdet
4scrollsscrollNOUNNumber=Plur2 reconstructedobj
5physicallyphysicallyADV_2 reconstructedadvmod
6fromfromADP_8 ashescase
7theirtheirPRONCase=Gen Number=Plur Person=3 Poss=Yes PronType=Prs8 ashesnmod:poss
8ashesashNOUNNumber=Plur2 reconstructedobl
9bybyADP_10 meanscase
10meansmeanVERBMood=Ind Number=Sing Person=3 Tense=Pres VerbForm=Fin2 reconstructedparataxis
11ofofADP_13 instrumentscase
12roboticroboticADJDegree=Pos13 instrumentsamod
13instrumentsinstrumentNOUNNumber=Plur10 meansobl
#verbtense, moodwhowhat, whomto whomwherewhenotherroles by
1reconstructpastItthe scrollsscrolls's ashesphysically propertytree rules
2meanpresentof robotic instrumentsvn intend-61.2-1 «NP V S»: agent=Agent

Option 2

It composed new texts in place of those destroyed

nsubjamodobjcaseoblcasenmodaclrootItPRONcomposedVERBnewADJtextsNOUNinADPplaceNOUNofADPthosePRONdestroyedVERB
The words, one row each (CoNLL-U)
#wordlemmaUPOSfeaturesheadrelation
1ItitPRONCase=Nom Gender=Neut Number=Sing Person=3 PronType=Prs2 composednsubj
2composedcomposeVERBMood=Ind Number=Sing Person=3 Tense=Past VerbForm=Finrootroot
3newnewADJDegree=Pos4 textsamod
4textstextNOUNNumber=Plur2 composedobj
5ininADP_6 placecase
6placeplaceNOUNNumber=Sing2 composedobl
7ofofADP_8 thosecase
8thosethatPRONNumber=Plur PronType=Dem6 placenmod
9destroyeddestroyVERBTense=Past VerbForm=Part Voice=Pass8 thoseacl
#verbtense, moodwhowhat, whomto whomwherewhenotherroles by
1composepastItnew textsplace of thosevn create-26.4-1 «NP V NP»: agent=Agent text=Result
2destroyparticiplevn destroy-44 «NP V NP»: agent=Agent

Option 3 · ✓ the right answer

It assisted in the detection of ink within scans, enabling the text to be read

The tree, 15 words
nsubjcasedetoblcasenmodcaseoblpunctadvcldetobjmarkaux:passadvclrootItPRONassistedVERBinADPtheDETdetectionNOUNofADPinkNOUNwithinADPscansNOUN,PUNCTenablingVERBtheDETtextNOUNtoPARTbeAUXreadVERB
The words, one row each (CoNLL-U)
#wordlemmaUPOSfeaturesheadrelation
1ItitPRONCase=Nom Gender=Neut Number=Sing Person=3 PronType=Prs2 assistednsubj
2assistedassistVERBMood=Ind Number=Sing Person=3 Tense=Past VerbForm=Finrootroot
3ininADP_5 detectioncase
4thetheDETDefinite=Def PronType=Art5 detectiondet
5detectiondetectionNOUNNumber=Sing2 assistedobl
6ofofADP_7 inkcase
7inkinkNOUNNumber=Sing5 detectionnmod
8withinwithinADP_9 scanscase
9scansscanNOUNNumber=Plur2 assistedobl
10,,PUNCT_11 enablingpunct
11enablingenableVERBTense=Pres VerbForm=Part2 assistedadvcl
12thetheDETDefinite=Def PronType=Art13 textdet
13texttextNOUNNumber=Sing11 enablingobj
14totoPART_16 readmark
15bebeAUXVerbForm=Inf16 readaux:pass
16readreadVERBTense=Past VerbForm=Part Voice=Pass11 enablingadvcl
#verbtense, moodwhowhat, whomto whomwherewhenotherroles by
1assistpastItthe detection of inkwithin scansvn help-72.1-1-1 «NP V PP.theme»: agent=Agent
2enablegerundthe texttree rules
3readto-infinitive · passivevn transfer_mesg-37.1.1-1 «NP V»
4detectinknom detection «cognition transitive»: of=patient

Option 4

It established that the scrolls contained no writing

nsubjmarkdetnsubjadvcldetobjrootItPRONestablishedVERBthatSCONJtheDETscrollsNOUNcontainedVERBnoDETwritingNOUN
The words, one row each (CoNLL-U)
#wordlemmaUPOSfeaturesheadrelation
1ItitPRONCase=Nom Gender=Neut Number=Sing Person=3 PronType=Prs2 establishednsubj
2establishedestablishVERBMood=Ind Number=Sing Person=3 Tense=Past VerbForm=Finrootroot
3thatthatSCONJ_6 containedmark
4thetheDETDefinite=Def PronType=Art5 scrollsdet
5scrollsscrollNOUNNumber=Plur6 containednsubj
6containedcontainVERBMood=Ind Number=Plur Person=3 Tense=Past VerbForm=Fin2 establishedadvcl
7nonoDETPronType=Neg8 writingdet
8writingwritingNOUNNumber=Sing6 containedobj
#verbtense, moodwhowhat, whomto whomwherewhenotherroles by
1establishpastItvn indicate-78-1-1 «NP V NP to be NP»: agent=Pivot
2containpastthe scrollsno writingvn comprise-107.2-2 «NP V NP»: agent=Pivot writing=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.

This page in Markdown → https://md.mova.elamur.ai/free/en/corpora/questions/ai/23-news-tricked-bots-discoveries/e1/