---
title: autoencoder — mysticism dictionary · trees and pragmatics
description: «autoencoder» in the mysticism dictionary: A kind of neural network that squeezes its input into a few numbers and then grows it back, and learns from how far the copy is from the original. Every meaning for a pupil with its dependency tree and pragmatics.
---

<!-- md -->
[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/)

<!-- crumbs -->
[home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [dictionaries](https://md.mova.elamur.ai/free/en/corpora/dictionaries/) / [mysticism dictionary](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/) / [A](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/) / autoencoder

# autoencoder

<!-- .vintro -->
**Who acts:** kind, One, That, you, seasons, network · **What happens:** squeeze, grow back, learn, be, tell, press · **To what, where:** input, few numbers, copy, original, Middle, world · **Speech:** someone speaks here

<!-- .vabout -->
«autoencoder» in the mysticism dictionary: its meaning for a pupil and its 5 examples, every sentence parsed by Mova itself — its syntax tree, a dependency tree in the style of Universal Dependencies, and its pragmatics clause by clause. The word in the dictionary, with its sense in the lessons: [autoencoder in the mysticism dictionary](https://md.mova.elamur.ai/free/en/dictionaries/mysticism/w/autoencoder.md).

## Meaning 1 {#m1}

<!-- .ven lang=en -->
A kind of neural network that squeezes its input into a few numbers and then grows it back, and learns from how far the copy is from the original.

<!-- fold The tree, 29 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:m1:1
# text = A kind of neural network that squeezes its input into a few numbers and then grows it back, and learns from how far the copy is from the original.
1	A	a	DET	DT	Definite=Ind|PronType=Art	2	det	_	_
2	kind	kind	NOUN	NN	Number=Sing	30	nsubj	_	_
3	of	of	ADP	IN	_	5	case	_	_
4	neural	neural	ADJ	JJ	Degree=Pos	5	amod	_	_
5	network	network	NOUN	NN	Number=Sing	2	nmod	_	_
6	that	that	PRON	WDT	PronType=Rel	7	nsubj	_	_
7	squeezes	squeeze	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	2	acl:relcl	_	_
8	its	its	PRON	PRP$	Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs	9	nmod:poss	_	_
9	input	input	NOUN	NN	Number=Sing	7	obj	_	_
10	into	into	ADP	IN	_	13	case	_	_
11	a	a	DET	DT	Definite=Ind|PronType=Art	13	det	_	_
12	few	few	ADJ	JJ	Degree=Pos	13	amod	_	_
13	numbers	number	NOUN	NNS	Number=Plur	7	obl	_	_
14	and	and	CCONJ	CC	_	16	cc	_	_
15	then	then	ADV	RB	PronType=Dem	16	advmod	_	_
16	grows	grow	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	7	conj	_	_
17	it	it	PRON	PRP	Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs	16	obj	_	_
18	back	back	ADV	RB	_	16	advmod	_	SpaceAfter=No
19	,	,	PUNCT	,	_	21	punct	_	_
20	and	and	CCONJ	CC	_	21	cc	_	_
21	learns	learn	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	7	conj	_	_
22	from	from	ADP	IN	_	26	case	_	_
23	how	how	ADV	WRB	PronType=Int	24	advmod	_	_
24	far	far	ADV	RB	Degree=Pos	26	advmod	_	_
25	the	the	DET	DT	Definite=Def|PronType=Art	26	det	_	_
26	copy	copy	NOUN	NN	Number=Sing	21	obl	_	_
27	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	30	cop	_	_
28	from	from	ADP	IN	_	30	case	_	_
29	the	the	DET	DT	Definite=Def|PronType=Art	30	det	_	_
30	original	original	NOUN	NN	Number=Sing	0	root	_	SpaceAfter=No
31	.	.	PUNCT	.	_	30	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **squeeze** | present | a kind of neural network | kind's input |  | a few numbers |  |  | vn knead-26.5 «NP V NP.material PP.product»: agent=Agent input=Material into number=Product |
| 2 | **grow back** | present | a kind of neural network *not said here* | input |  |  | then |  | vn appear-48.1.1 «PP.location V NP»: agent=Location it=Theme |
| 3 | **learn** | present | a kind of neural network *not said here* |  |  | the copy |  |  | vn learn-14-2-1 «NP V PP.source»: agent=Agent from copy=Source |
| 4 | **is** | present | a kind of neural network |  |  | the original |  |  | tree rules |

<!-- .note -->
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.

## Example 1 {#x1}

<!-- .ven lang=en -->
The One in the Middle told it as an autoencoder: a world pressed into a point, and unfolded again. (note 05)

<!-- .note -->
*Sentence 1:* The One in the Middle told it as an autoencoder: a world pressed into a point, and unfolded again.

<!-- fold The tree, 19 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:x1:1
# text = The One in the Middle told it as an autoencoder: a world pressed into a point, and unfolded again.
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	One	one	NUM	CD	NumForm=Word|NumType=Card	6	nsubj	_	_
3	in	in	ADP	IN	_	5	case	_	_
4	the	the	DET	DT	Definite=Def|PronType=Art	5	det	_	_
5	Middle	Middle	PROPN	NNP	Number=Sing	6	obl	_	_
6	told	tell	VERB	VBD	Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin	0	root	_	_
7	it	it	PRON	PRP	Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs	6	obj	_	_
8	as	as	ADP	IN	_	10	case	_	_
9	an	a	DET	DT	Definite=Ind|PronType=Art	10	det	_	_
10	autoencoder	autoencoder	NOUN	NN	Number=Sing	6	obl	_	SpaceAfter=No
11	:	:	PUNCT	:	_	13	punct	_	_
12	a	a	DET	DT	Definite=Ind|PronType=Art	13	det	_	_
13	world	world	NOUN	NN	Number=Sing	10	appos	_	_
14	pressed	press	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	13	acl	_	_
15	into	into	ADP	IN	_	17	case	_	_
16	a	a	DET	DT	Definite=Ind|PronType=Art	17	det	_	_
17	point	point	NOUN	NN	Number=Sing	14	obl	_	SpaceAfter=No
18	,	,	PUNCT	,	_	20	punct	_	_
19	and	and	CCONJ	CC	_	20	cc	_	_
20	unfolded	unfold	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	6	conj	_	_
21	again	again	ADV	RB	_	20	advmod	_	SpaceAfter=No
22	.	.	PUNCT	.	_	6	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **tell** *speech: assert* | past | the One |  | Middle | the Middle |  | as a autoencoder | vn transfer\_mesg-37.1.1-1-1 «NP V NP.recipient»: agent=Agent it=Recipient |
| 2 | **press** | participle |  | a world *not said here* |  | a point |  |  | vn push-12-1-1 «NP V PP.trajectory»: agent=Agent into point=Trajectory |
| 3 | **unfold** | participle | the One *not said here* |  |  |  | again |  | vn bend-45.2 «NP.patient V»: agent=Patient |

<!-- .note -->
*Sentence 2:* (note 05)

```conllu
# sent_id = dict:mysticism:autoencoder:x1:2
# text = (note 05)
1	(	(	PUNCT	-LRB-	_	2	punct	_	SpaceAfter=No
2	note	note	NOUN	NN	Number=Sing	0	root	_	_
3	05	05	NUM	CD	NumForm=Digit|NumType=Card	2	flat	_	SpaceAfter=No
4	)	)	PUNCT	-RRB-	_	2	punct	_	_
```

<!-- .note -->
The frames reader finds no event or fact in this sentence.

## Example 2 {#x2}

<!-- .ven lang=en -->
That is the shape of an autoencoder, read backwards: the seasons decode first and encode after, where a network encodes first. (note 08)

<!-- .note -->
*Sentence 1:* That is the shape of an autoencoder, read backwards: the seasons decode first and encode after, where a network encodes first.

<!-- fold The tree, 21 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:x2:1
# text = That is the shape of an autoencoder, read backwards: the seasons decode first and encode after, where a network encodes first.
1	That	that	PRON	DT	Number=Sing|PronType=Dem	4	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
3	the	the	DET	DT	Definite=Def|PronType=Art	4	det	_	_
4	shape	shape	NOUN	NN	Number=Sing	9	obj	_	_
5	of	of	ADP	IN	_	7	case	_	_
6	an	a	DET	DT	Definite=Ind|PronType=Art	7	det	_	_
7	autoencoder	autoencoder	NOUN	NN	Number=Sing	4	nmod	_	SpaceAfter=No
8	,	,	PUNCT	,	_	4	punct	_	_
9	read	read	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
10	backwards	backwards	ADV	RB	_	9	advmod	_	SpaceAfter=No
11	:	:	PUNCT	:	_	14	punct	_	_
12	the	the	DET	DT	Definite=Def|PronType=Art	13	det	_	_
13	seasons	season	NOUN	NNS	Number=Plur	14	nsubj	_	_
14	decode	decode	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	9	parataxis	_	_
15	first	first	ADV	RB	NumForm=Word|NumType=Ord	14	advmod	_	_
16	and	and	CCONJ	CC	_	17	cc	_	_
17	encode	encode	VERB	VB	VerbForm=Inf	14	conj	_	_
18	after	after	ADV	RB	_	17	advmod	_	SpaceAfter=No
19	,	,	PUNCT	,	_	23	punct	_	_
20	where	where	ADV	WRB	PronType=Rel	23	advmod	_	_
21	a	a	DET	DT	Definite=Ind|PronType=Art	22	det	_	_
22	network	network	NOUN	NN	Number=Sing	23	nsubj	_	_
23	encodes	encode	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	17	conj	_	_
24	first	first	ADV	RB	NumForm=Word|NumType=Ord	23	advmod	_	SpaceAfter=No
25	.	.	PUNCT	.	_	9	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | That | the shape |  |  |  | of a autoencoder | tree rules |
| 2 | **read** | imperative | you *not said here* |  |  |  |  | backwards *property* | vn transfer\_mesg-37.1.1-1 «NP V»: agent=Agent |
| 3 | **decode** | present | the seasons |  |  |  |  | first *property* | tree rules |
| 4 | **encode** | infinitive | the seasons *not said here* |  |  |  |  | after *property* | tree rules |
| 5 | **encode** | present | a network |  |  |  |  | first *property* | tree rules |

<!-- .note -->
*Sentence 2:* (note 08)

```conllu
# sent_id = dict:mysticism:autoencoder:x2:2
# text = (note 08)
1	(	(	PUNCT	-LRB-	_	2	punct	_	SpaceAfter=No
2	note	note	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
3	08	08	NUM	CD	NumForm=Digit|NumType=Card	2	obj	_	SpaceAfter=No
4	)	)	PUNCT	-RRB-	_	2	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **note** | imperative | you *not said here* | 08 |  |  |  |  | vn say-37.7-1-1 «NP V NP.topic»: agent=Agent 08=Topic |

## Example 3 {#x3}

<!-- .ven lang=en -->
An autoencoder is trained on its reconstruction error: how far the world that comes out is from the world that went in. (note 08)

<!-- .note -->
*Sentence 1:* An autoencoder is trained on its reconstruction error: how far the world that comes out is from the world that went in.

<!-- fold The tree, 22 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:x3:1
# text = An autoencoder is trained on its reconstruction error: how far the world that comes out is from the world that went in.
1	An	a	DET	DT	Definite=Ind|PronType=Art	2	det	_	_
2	autoencoder	autoencoder	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	trained	train	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
5	on	on	ADP	IN	_	8	case	_	_
6	its	its	PRON	PRP$	Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs	8	nmod:poss	_	_
7	reconstruction	reconstruction	NOUN	NN	Number=Sing	8	compound	_	_
8	error	error	NOUN	NN	Number=Sing	4	obl	_	SpaceAfter=No
9	:	:	PUNCT	:	_	20	punct	_	_
10	how	how	ADV	WRB	PronType=Int	11	advmod	_	_
11	far	far	ADV	RB	Degree=Pos	20	advmod	_	_
12	the	the	DET	DT	Definite=Def|PronType=Art	13	det	_	_
13	world	world	NOUN	NN	Number=Sing	20	nsubj	_	_
14	that	that	PRON	WDT	PronType=Rel	15	nsubj	_	_
15	comes	come	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	13	acl:relcl	_	_
16	out	out	ADP	RP	_	15	compound:prt	_	_
17	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	20	cop	_	_
18	from	from	ADP	IN	_	20	case	_	_
19	the	the	DET	DT	Definite=Def|PronType=Art	20	det	_	_
20	world	world	NOUN	NN	Number=Sing	4	obl	_	_
21	that	that	PRON	WDT	PronType=Rel	22	nsubj	_	_
22	went	go	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	20	acl:relcl	_	_
23	in	in	ADV	RB	_	22	advmod	_	SpaceAfter=No
24	.	.	PUNCT	.	_	4	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **train** | present · passive |  | a autoencoder |  | autoencoder's reconstruction error |  |  | vn hire-13.5.3 «NP V NP»: subject=Theme |
| 2 | **come out** | present | the world |  |  |  |  |  | vn become-109.1 «NP V ADJ»: agent=Patient |
| 3 | **is** | present | the world |  |  | the world |  | far *property* | tree rules |
| 4 | **go in** | past | the world |  |  |  |  |  | vn disappearance-48.2-1 «NP V»: agent=Theme |
| 5 | **err** |  | autoencoder |  |  |  |  |  | nom error «act intransitive»: poss=agent |

<!-- .note -->
*Sentence 2:* (note 08)

```conllu
# sent_id = dict:mysticism:autoencoder:x3:2
# text = (note 08)
1	(	(	PUNCT	-LRB-	_	2	punct	_	SpaceAfter=No
2	note	note	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
3	08	08	NUM	CD	NumForm=Digit|NumType=Card	2	obj	_	SpaceAfter=No
4	)	)	PUNCT	-RRB-	_	2	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **note** | imperative | you *not said here* | 08 |  |  |  |  | vn say-37.7-1-1 «NP V NP.topic»: agent=Agent 08=Topic |

## Example 4 {#x4}

<!-- .ven lang=en -->
That is the shape of an autoencoder: layers widen, narrow to a bottleneck, widen again; the seventh day is the latent space, where the whole of creation fits into one thought, and Mova does the same in miniature, text into a graph and back. (lesson 020)

<!-- .note -->
*Sentence 1:* That is the shape of an autoencoder: layers widen, narrow to a bottleneck, widen again; the seventh day is the latent space, where the whole of creation fits into one thought, and Mova does the same in miniature, text into a graph and back.

<!-- fold The tree, 44 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:x4:1
# text = That is the shape of an autoencoder: layers widen, narrow to a bottleneck, widen again; the seventh day is the latent space, where the whole of creation fits into one thought, and Mova does the same in miniature, text into a graph and back.
1	That	that	PRON	DT	Number=Sing|PronType=Dem	4	nsubj	_	_
2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
3	the	the	DET	DT	Definite=Def|PronType=Art	4	det	_	_
4	shape	shape	NOUN	NN	Number=Sing	0	root	_	_
5	of	of	ADP	IN	_	7	case	_	_
6	an	a	DET	DT	Definite=Ind|PronType=Art	7	det	_	_
7	autoencoder	autoencoder	NOUN	NN	Number=Sing	4	nmod	_	SpaceAfter=No
8	:	:	PUNCT	:	_	10	punct	_	_
9	layers	layer	NOUN	NNS	Number=Plur	10	nsubj	_	_
10	widen	widen	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	4	parataxis	_	SpaceAfter=No
11	,	,	PUNCT	,	_	12	punct	_	_
12	narrow	narrow	ADJ	JJ	Degree=Pos	10	advcl	_	_
13	to	to	ADP	IN	_	15	case	_	_
14	a	a	DET	DT	Definite=Ind|PronType=Art	15	det	_	_
15	bottleneck	bottleneck	NOUN	NN	Number=Sing	12	obl	_	SpaceAfter=No
16	,	,	PUNCT	,	_	17	punct	_	_
17	widen	widen	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	10	conj	_	_
18	again	again	ADV	RB	_	17	advmod	_	SpaceAfter=No
19	;	;	PUNCT	:	_	26	punct	_	_
20	the	the	DET	DT	Definite=Def|PronType=Art	22	det	_	_
21	seventh	seventh	ADJ	JJ	Degree=Pos	22	amod	_	_
22	day	day	NOUN	NN	Number=Sing	26	nsubj	_	_
23	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	26	cop	_	_
24	the	the	DET	DT	Definite=Def|PronType=Art	26	det	_	_
25	latent	latent	ADJ	JJ	Degree=Pos	26	amod	_	_
26	space	space	NOUN	NN	Number=Sing	33	nsubj	_	SpaceAfter=No
27	,	,	PUNCT	,	_	30	punct	_	_
28	where	where	ADV	WRB	PronType=Rel	30	advmod	_	_
29	the	the	DET	DT	Definite=Def|PronType=Art	30	det	_	_
30	whole	whole	ADJ	JJ	Degree=Pos	26	amod	_	_
31	of	of	ADP	IN	_	32	case	_	_
32	creation	creation	NOUN	NN	Number=Sing	30	obl	_	_
33	fits	fit	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	parataxis	_	_
34	into	into	ADP	IN	_	36	case	_	_
35	one	one	NUM	CD	NumForm=Word|NumType=Card	36	nummod	_	_
36	thought	thought	NOUN	NN	Number=Sing	33	obl	_	SpaceAfter=No
37	,	,	PUNCT	,	_	40	punct	_	_
38	and	and	CCONJ	CC	_	40	cc	_	_
39	Mova	Mova	PROPN	NNP	Number=Sing	40	nsubj	_	_
40	does	do	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	33	conj	_	_
41	the	the	DET	DT	Definite=Def|PronType=Art	42	det	_	_
42	same	same	ADJ	JJ	Degree=Pos	40	obj	_	_
43	in	in	ADP	IN	_	44	case	_	_
44	miniature	miniature	NOUN	NN	Number=Sing	40	obl	_	SpaceAfter=No
45	,	,	PUNCT	,	_	46	punct	_	_
46	text	text	NOUN	NN	Number=Sing	44	conj	_	_
47	into	into	ADP	IN	_	49	case	_	_
48	a	a	DET	DT	Definite=Ind|PronType=Art	49	det	_	_
49	graph	graph	NOUN	NN	Number=Sing	40	obl	_	_
50	and	and	CCONJ	CC	_	51	cc	_	_
51	back	back	ADV	RB	_	49	conj	_	SpaceAfter=No
52	.	.	PUNCT	.	_	4	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is a** | present | That | the shape |  |  |  | of a autoencoder | tree rules |
| 2 | **widen** | present | layers |  |  |  |  |  | vn other\_cos-45.4 «NP.patient V»: agent=Patient |
| 3 | **widen** | present | layers *not said here* |  |  |  | again |  | vn other\_cos-45.4 «NP.patient V»: agent=Patient |
| 4 | **is a** | present | the seventh day | the latent space |  |  |  |  | tree rules |
| 5 | **fit** | present | the latent space |  |  | one thought |  |  | vn funnel-9.3-1 «NP V NP PP.destination»: agent=Agent into thought=Destination |
| 6 | **do** | present | Mova | the same |  | miniature and text |  | into a graph | vn act-114-1 «NP V NP»: agent=Agent same=Eventuality |

<!-- .note -->
*Sentence 2:* (lesson 020)

```conllu
# sent_id = dict:mysticism:autoencoder:x4:2
# text = (lesson 020)
1	(	(	PUNCT	-LRB-	_	2	punct	_	SpaceAfter=No
2	lesson	lesson	NOUN	NN	Number=Sing	0	root	_	_
3	020	020	NUM	CD	NumForm=Digit|NumType=Card	2	flat	_	SpaceAfter=No
4	)	)	PUNCT	-RRB-	_	2	punct	_	_
```

<!-- .note -->
The frames reader finds no event or fact in this sentence.

## Example 5 {#x5}

<!-- .ven lang=en -->
The note says this is the shape of an autoencoder: the layers widen, narrow to a bottleneck, and widen again. (lesson 020)

<!-- .note -->
*Sentence 1:* The note says this is the shape of an autoencoder: the layers widen, narrow to a bottleneck, and widen again.

<!-- fold The tree, 20 words -->
```conllu
# sent_id = dict:mysticism:autoencoder:x5:1
# text = The note says this is the shape of an autoencoder: the layers widen, narrow to a bottleneck, and widen again.
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	note	note	NOUN	NN	Number=Sing	3	nsubj	_	_
3	says	say	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
4	this	this	PRON	DT	Number=Sing|PronType=Dem	7	nsubj	_	_
5	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	7	cop	_	_
6	the	the	DET	DT	Definite=Def|PronType=Art	7	det	_	_
7	shape	shape	NOUN	NN	Number=Sing	3	ccomp	_	_
8	of	of	ADP	IN	_	10	case	_	_
9	an	a	DET	DT	Definite=Ind|PronType=Art	10	det	_	_
10	autoencoder	autoencoder	NOUN	NN	Number=Sing	7	nmod	_	SpaceAfter=No
11	:	:	PUNCT	:	_	14	punct	_	_
12	the	the	DET	DT	Definite=Def|PronType=Art	13	det	_	_
13	layers	layer	NOUN	NNS	Number=Plur	14	nsubj	_	_
14	widen	widen	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	3	parataxis	_	SpaceAfter=No
15	,	,	PUNCT	,	_	16	punct	_	_
16	narrow	narrow	ADJ	JJ	Degree=Pos	14	advcl	_	_
17	to	to	ADP	IN	_	19	case	_	_
18	a	a	DET	DT	Definite=Ind|PronType=Art	19	det	_	_
19	bottleneck	bottleneck	NOUN	NN	Number=Sing	16	obl	_	SpaceAfter=No
20	,	,	PUNCT	,	_	22	punct	_	_
21	and	and	CCONJ	CC	_	22	cc	_	_
22	widen	widen	VERB	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	14	conj	_	_
23	again	again	ADV	RB	_	22	advmod	_	SpaceAfter=No
24	.	.	PUNCT	.	_	3	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **say** *speech: assert* | present | the note |  |  |  |  |  | vn say-37.7-1-1 «NP V that S»: agent=Agent |
| 2 | **is a** | present | this | the shape |  |  |  | of a autoencoder | tree rules |
| 3 | **widen** | present | the layers |  |  |  |  |  | vn other\_cos-45.4 «NP.patient V»: agent=Patient |
| 4 | **widen** | present | the layers *not said here* |  |  |  | again |  | vn other\_cos-45.4 «NP.patient V»: agent=Patient |

<!-- .note -->
*Sentence 2:* (lesson 020)

```conllu
# sent_id = dict:mysticism:autoencoder:x5:2
# text = (lesson 020)
1	(	(	PUNCT	-LRB-	_	2	punct	_	SpaceAfter=No
2	lesson	lesson	NOUN	NN	Number=Sing	0	root	_	_
3	020	020	NUM	CD	NumForm=Digit|NumType=Card	2	flat	_	SpaceAfter=No
4	)	)	PUNCT	-RRB-	_	2	punct	_	_
```

<!-- .note -->
The frames reader finds no event or fact in this sentence.

<!-- div src -->

**Text:** the mysticism dictionary of Mova's schools (`world/data/dictionary-schools/`), written for Mova. **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 meaning and example read on its own. Elamur Cosmic License.

<!-- /div -->

<!-- pn -->
- ← previous: [attractor](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/attractor/)
- next →: [axis](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/axis/)
- ↑ back to [A in mysticism dictionary](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/)