--- title: Chatbots are trained to be pleasant: "Great question!" they say, eve… — Why the bot agrees too easily · tree and pragmatics description: Chatbots are trained to be pleasant: "Great question!" they say, even when you asked something quite ordinary. Who acts: Chatbots, you. A sentence of the lesson «Why the bot agrees too easily» of the ai course of Mova's primary school with its dependency tree and the pragmatics of every clause. --- [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/0/) [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/) / [Why the bot agrees too easily](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/) / 0 # Why the bot agrees too easily, sentence 0 Chatbots are trained to be pleasant: "Great question!" they say, even when you asked something quite ordinary. **Who acts:** Chatbots, you · **What happens:** train, be, say, ask · **To what, where:** Chatbots, something · **Speech:** someone speaks here This is a sentence of the lesson «Why the bot agrees too easily» 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 (Chatbots, you), what happens, when and where, as Mova's frames read it from the tree. ## The tree {#tree} ```conllu # sent_id = school:ai:006-why-the-bot-agrees-too-easily.lesson:0 # text = Chatbots are trained to be pleasant: "Great question!" they say, even when you asked something quite ordinary. # source = school lesson (ours) # course = ai # lesson = 006-why-the-bot-agrees-too-easily.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): R6-punct-agree ×1, R7-rel-agree ×2 1 Chatbots chatbot NOUN NNS Number=Plur 3 nsubj:pass _ _ 2 are be AUX VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 3 aux:pass _ _ 3 trained train VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 0 root _ _ 4 to to PART TO _ 6 mark _ _ 5 be be AUX VB VerbForm=Inf 6 cop _ _ 6 pleasant pleasant ADJ JJ Degree=Pos 3 xcomp _ Agree=R7-rel-agree|Haiku=3:conj 7 : : PUNCT : _ 10 punct _ _ 8 " " PUNCT `` _ 10 punct _ _ 9 Great great ADJ JJ Degree=Pos 10 amod _ _ 10 question question NOUN NN Number=Sing 6 conj _ _ 11 ! ! PUNCT . _ 10 punct _ Agree=R6-punct-agree|Haiku=6:punct 12 " " PUNCT '' _ 6 punct _ _ 13 they they PRON PRP Case=Nom|Number=Plur|Person=3|PronType=Prs 14 nsubj _ _ 14 say say VERB VBP Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin 3 parataxis _ Agree=R7-rel-agree|Haiku=3:conj 15 , , PUNCT , _ 19 punct _ _ 16 even even ADV RB _ 19 advmod _ _ 17 when when SCONJ WRB _ 19 mark _ _ 18 you you PRON PRP Case=Nom|Person=2|PronType=Prs 19 nsubj _ _ 19 asked ask VERB VBD Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin 14 advcl _ _ 20 something something PRON NN Number=Sing|PronType=Ind 19 obj _ _ 21 quite quite ADV RB _ 22 advmod _ _ 22 ordinary ordinary ADJ JJ Degree=Pos 20 amod _ _ 23 . . PUNCT . _ 3 punct _ _ ``` ## Pragmatics {#pragmatics} - form: statement - act: assert - voice: narrator - polarity: pos - teacher: changed form=decl, act=assert, voice=narrator | # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **train** | present · passive | | Chatbots | | | | | vn hire-13.5.3 «NP V NP»: subject=Theme | | 2 | **is** | to-infinitive | Chatbots *not said here* | | | | | pleasant *property* | tree rules | | 3 | **say** *speech: assert* | present | Chatbots *= chatbot* | | | | | | vn say-37.7-1-1 «NP V that S»: agent=Agent | | 4 | **ask** *speech: ask* | past | you | something | | | | | vn inquire-37.1.2 «NP V NP.recipient»: agent=Agent something=Recipient | 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:006-why-the-bot-agrees-too-easily.lesson:0`. **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): R6-punct-agree ×1, R7-rel-agree ×2. **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: [Hallucinations: confident made-up answ…, 20](https://md.mova.elamur.ai/free/en/corpora/school/ai/5-hallucinations-confident-made-up-answers/20/) - next →: [Why the bot agrees too easily, 1](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/1/) - ↑ back to [the lesson](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/)