[ES] Spanish translation week 12, section 2 #570

GastonMazzei · 2020-09-18T03:25:25Z

Let's keep an eye on the associated videos
"beam search" --> here "búsqueda por haces" [https://www.youtube.com/watch?v=6D4EWKJgNn0&t=2732s]
"traducción inversa" [https://www.youtube.com/watch?v=6D4EWKJgNn0&t=3811s]
"entrenamiento previo para NLP" [https://www.youtube.com/watch?v=6D4EWKJgNn0&t=4963s]

Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

upper case Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Atcold

You need to edit docs/_config.yml as well.

docs/es/week12/12-2.md

GastonMazzei · 2020-09-18T04:56:02Z

You need to edit docs/_config.yml as well.

O.K. JUST DID... even tho "12.md" doesn't exist yet!

If merging conflicts let me know and I'll change the "/week12/12.md" to "../week12"

zxul767 · 2020-09-18T15:17:01Z

docs/_config.yml

@@ -295,6 +295,9 @@ es:
      sections:
        - path: es/week11/11-1.md
        - path: es/week11/11-2.md
+    - path: es/week12/12.md


My PR that's almost ready to get merged includes this, if you're concerned: https://github.com/Atcold/pytorch-Deep-Learning/pull/555/files

OK so I will add mine using the same header, fine?
i.e. this will be present

-path: es/week12/12.md sections: - path: es/week12/12-2.md

My question is if it wont generate a duplicate; sorry for the trouble just learning github lol

I think it shouldn't create a merge conflict because it's exactly the same, but even if it does, resolving it should be trivial.

And how should it be resolved then?

(A) by me adding yours - path: es/week12/12-3.md
(B) by me removing all except for - path: es/week12/12-2.md

Am i being clear with my question? i.e. what do you want me to do about it?

Typically, when your PR happens to be merged first, option (A) would apply. If my PR were to be merged first, then you'd just need to be sure that nothing got duplicated.

Oh ok, will leave as is and keep an eye on what happens next. Thanks!

added 12-2 in config

zxul767

I learned a lot by reviewing this translation, NLP is such an interesting topic!

I left several minor comments, but overall the translation looks great!

zxul767 · 2020-09-18T16:14:06Z

docs/es/week12/12-2.md

+
+<!-- The algorithm selects the best scoring hypothesis.-->
+
+El algoritmo selecciona la mejor hipótesis de puntuación.


May I suggest "...selecciona la hipótesis con mejor puntuación."?

Haha yes it is (an interesting topic). Great bug-detection skills! And great suggestions!
All were implemented

zxul767 · 2020-09-18T16:17:18Z

docs/es/week12/12-2.md

+
+<!-- The beam tree continues until it reaches the end of sentence token. Upon outputting the end of sentence token, the hypothesis is finished.-->
+
+El árbol de haces continúa hasta que llega al final del token de oración. Al generar el final del token de oración, la hipótesis está terminada.


May I suggest "...hasta que llega al token de final de oración."? In this case, "end of sentence" is acting as an adjective for "token"

Changed! thanks

zxul767 · 2020-09-18T16:18:33Z

docs/es/week12/12-2.md

+
+<!-- Why (in NMT) do very large beam sizes often results in empty translations?-->
+
+¿Por qué (en NMT) los tamaños de haces muy grandes a menudo dan como resultado traslaciones vacías?


I believe the more appropriate translation for "translations" is "traducciones" in this context

zxul767 · 2020-09-18T16:22:48Z

docs/_config.yml

@@ -422,6 +429,9 @@ tr:
 ja:
  title: '深層学習'
  chapters:
+    - path: ja/week03/03.md


Was this needed for the site to compile locally?

zxul767 · 2020-09-18T16:24:26Z

docs/es/week12/12-2.md

+<!-- A pure sampling technique where you truncate the distribution to the $k$ best and then renormalise and sample from the distribution.-->
+
+
+Una técnica de muestreo pura en la que se trunca la distribución al $ k $ best y luego se vuelve a normalizar y se muestra la distribución.


I believe "to the K best" here refers to "the K best samples", so the translation "a los K mejores" seems more appropriate.

zxul767 · 2020-09-18T17:09:07Z

docs/es/week12/12-2.md

+
+- ¡Muchos objetivos diferentes de preentrenamiento funcionan bien!
+
+- Crucial para modelar interacciones profundas y bidireccionales entre palabras


May I suggest replacing "Crucial para modelar..." with "Es muy importante modelar..."?

zxul767 · 2020-09-18T17:12:30Z

docs/es/week12/12-2.md

+
+### Algunas preguntas abiertas en NLP
+
+- ¿Cómo deberíamos integrar el conocimiento mundial?


In the previous PR, I suggested using "conocimiento del mundo real" instead of "conocimiento mundial", as that's what I've seen most commonly used in text for LATAM, but I'm not sure if the same applies in other Spanish-speaking regions of the world (particularly Spain)

zxul767 · 2020-09-18T17:13:48Z

docs/es/week12/12-2.md

+
+<!--- Models can learn a lot about language by predicting words in unlabelled text. This turns out to be a great unsupervised learning objective. Fine tuning for specific tasks is then easy-->
+
+- Los modelos pueden aprender mucho sobre el lenguaje al predecir palabras en texto sin etiquetar. Esto resulta ser un gran objetivo de aprendizaje sin supervisión. La puesta a punto para tareas específicas es fácil


Suggested change

- Los modelos pueden aprender mucho sobre el lenguaje al predecir palabras en texto sin etiquetar. Esto resulta ser un gran objetivo de aprendizaje sin supervisión. La puesta a punto para tareas específicas es fácil

- Los modelos pueden aprender mucho sobre el lenguaje al predecir palabras en texto sin etiquetar. Esto resulta ser un gran objetivo de aprendizaje sin supervisión. La puesta a punto para tareas específicas se vuelve entonces fácil

zxul767 · 2020-09-18T17:15:58Z

docs/es/week12/12-2.md

+
+<!--Interestingly, the lecturer (Mike Lewis, Research Scientist, FAIR) is working on a concept called ‘Grounded Language’. The aim of that field of research is to build conversational agents that are able to chit-chat or negotiate. Chit-chatting and negotiating are abstract tasks with unclear objectives as compared to text classification or text summarization.-->
+
+Curiosamente, el profesor (Mike Lewis, investigador científico, FAIR) está trabajando en un concepto llamado "Lenguaje fundamentado". El objetivo de ese campo de investigación es construir agentes conversacionales que sean capaces de charlar o negociar. Charlar y negociar son tareas abstractas con objetivos poco claros en comparación con la clasificación o el resumen del texto.


Suggested change

Curiosamente, el profesor (Mike Lewis, investigador científico, FAIR) está trabajando en un concepto llamado "Lenguaje fundamentado". El objetivo de ese campo de investigación es construir agentes conversacionales que sean capaces de charlar o negociar. Charlar y negociar son tareas abstractas con objetivos poco claros en comparación con la clasificación o el resumen del texto.

Curiosamente, el profesor (Mike Lewis, investigador científico, FAIR) está trabajando en un concepto llamado "Lenguaje Fundamentado". El objetivo de ese campo de investigación es construir agentes conversacionales que sean capaces de charlar o negociar. Charlar y negociar son tareas abstractas con objetivos poco claros en comparación con la clasificación o el resumen del texto.

zxul767 · 2020-09-18T17:18:45Z

docs/es/week12/12-2.md

+
+<!--‘World Knowledge’ is an abstract concept. We can test models, at the very basic level, for their world knowledge by asking them simple questions about the concepts we are interested in.  Models like BERT, RoBERTa and T5 have billions of parameters. Considering these models are trained on a huge corpus of informational text like Wikipedia, they would have memorized facts using their parameters and would be able to answer our questions. Additionally, we can also think of conducting the same knowledge test before and after fine-tuning a model on some task. This would give us a sense of how much information the model has ‘forgotten’.-->
+
+El "conocimiento mundial" es un concepto abstracto. Podemos probar modelos, en un nivel muy básico, para su conocimiento del mundo haciéndoles preguntas simples sobre los conceptos que nos interesan. Modelos como BERT, RoBERTa y T5 tienen miles de millones de parámetros. Teniendo en cuenta que estos modelos están entrenados en un enorme corpus de texto informativo como Wikipedia, habrían memorizado hechos usando sus parámetros y podrían responder nuestras preguntas. Además, también podemos pensar en realizar la misma prueba de conocimientos antes y después de ajustar un modelo en alguna tarea. Esto nos daría una idea de cuánta información ha "olvidado" el modelo.


May I suggest rephrasing "Podemos probar modelos... para su conocimiento del mundo..." as "Podemos probar el conocimiento del mundo que tienen los modelos (en un nivel muy básico)..."?

Great suggestions overall, and also great bug-detecting! implemented all of them, thanx!

Atcold

Sweet, thanks!

Atcold · 2020-09-23T02:32:10Z

Hmm, I got a notification from the PR.
Anything that I should pay attention to?

GastonMazzei · 2020-09-23T17:54:16Z

Hmm, I got a notification from the PR.
Anything that I should pay attention to?

You DID merge it and no changes happened since, so I'm as lost as you are.
Any more I can do to help?

Atcold · 2020-09-26T03:28:28Z

Hmm…

Yes, there are plenty of chapters to review! Check out the wiki!

GastonMazzei and others added 11 commits September 17, 2020 11:39

week 12 - class 12-02

a18a9b1

week 12 - class 12-02

8d595dc

Update docs/es/week12/12-2.md

bf3c45c

Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

2b6fa27

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

3be693b

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

19550b9

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

fc9161c

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

ea6501c

upper case Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

c3a91cc

Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

Update docs/es/week12/12-2.md

394a52e

infinitive to gerund Co-authored-by: Willebaldo Gómez <willebaldo.gomez@gmail.com>

creation

1a73af4

Atcold requested changes Sep 18, 2020

View reviewed changes

docs/es/week12/12-2.md Show resolved Hide resolved

docs/es/week12/12-2.md Show resolved Hide resolved

docs/es/week12/12-2.md Outdated Show resolved Hide resolved

GastonMazzei added 2 commits September 18, 2020 01:46

Update 12-2.md

f17dd6a

Update _config.yml

9d8924c

zxul767 reviewed Sep 18, 2020

View reviewed changes

GastonMazzei added 4 commits September 18, 2020 13:05

Update _config.yml

aa77edd

Update _config.yml

29964b7

Update _config.yml

4c305e1

added 12-2 in config

Update _config.yml

c1cf36c

zxul767 reviewed Sep 18, 2020

View reviewed changes

GastonMazzei added 2 commits September 18, 2020 15:50

Update 12-2.md

7f88764

Update 12-2.md

3b7ea4c

Atcold approved these changes Sep 19, 2020

View reviewed changes

Atcold merged commit 573f7d5 into Atcold:master Sep 19, 2020

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[ES] Spanish translation week 12, section 2 #570

[ES] Spanish translation week 12, section 2 #570

GastonMazzei commented Sep 18, 2020

Atcold left a comment

GastonMazzei commented Sep 18, 2020

zxul767 Sep 18, 2020

GastonMazzei Sep 18, 2020

GastonMazzei Sep 18, 2020

zxul767 Sep 18, 2020 •

edited

GastonMazzei Sep 18, 2020

zxul767 Sep 19, 2020

GastonMazzei Sep 19, 2020

zxul767 left a comment

zxul767 Sep 18, 2020

GastonMazzei Sep 18, 2020

zxul767 Sep 18, 2020

GastonMazzei Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

zxul767 Sep 18, 2020

GastonMazzei Sep 18, 2020

Atcold left a comment

Atcold commented Sep 23, 2020

GastonMazzei commented Sep 23, 2020

Atcold commented Sep 26, 2020


		<!-- The algorithm selects the best scoring hypothesis.-->

		El algoritmo selecciona la mejor hipótesis de puntuación.


		<!-- The beam tree continues until it reaches the end of sentence token. Upon outputting the end of sentence token, the hypothesis is finished.-->

		El árbol de haces continúa hasta que llega al final del token de oración. Al generar el final del token de oración, la hipótesis está terminada.


		<!-- Why (in NMT) do very large beam sizes often results in empty translations?-->

		¿Por qué (en NMT) los tamaños de haces muy grandes a menudo dan como resultado traslaciones vacías?

		<!-- A pure sampling technique where you truncate the distribution to the $k$ best and then renormalise and sample from the distribution.-->


		Una técnica de muestreo pura en la que se trunca la distribución al $ k $ best y luego se vuelve a normalizar y se muestra la distribución.


		- ¡Muchos objetivos diferentes de preentrenamiento funcionan bien!

		- Crucial para modelar interacciones profundas y bidireccionales entre palabras


		### Algunas preguntas abiertas en NLP

		- ¿Cómo deberíamos integrar el conocimiento mundial?


		<!--- Models can learn a lot about language by predicting words in unlabelled text. This turns out to be a great unsupervised learning objective. Fine tuning for specific tasks is then easy-->

		- Los modelos pueden aprender mucho sobre el lenguaje al predecir palabras en texto sin etiquetar. Esto resulta ser un gran objetivo de aprendizaje sin supervisión. La puesta a punto para tareas específicas es fácil


		<!--Interestingly, the lecturer (Mike Lewis, Research Scientist, FAIR) is working on a concept called ‘Grounded Language’. The aim of that field of research is to build conversational agents that are able to chit-chat or negotiate. Chit-chatting and negotiating are abstract tasks with unclear objectives as compared to text classification or text summarization.-->

		Curiosamente, el profesor (Mike Lewis, investigador científico, FAIR) está trabajando en un concepto llamado "Lenguaje fundamentado". El objetivo de ese campo de investigación es construir agentes conversacionales que sean capaces de charlar o negociar. Charlar y negociar son tareas abstractas con objetivos poco claros en comparación con la clasificación o el resumen del texto.


		<!--‘World Knowledge’ is an abstract concept. We can test models, at the very basic level, for their world knowledge by asking them simple questions about the concepts we are interested in. Models like BERT, RoBERTa and T5 have billions of parameters. Considering these models are trained on a huge corpus of informational text like Wikipedia, they would have memorized facts using their parameters and would be able to answer our questions. Additionally, we can also think of conducting the same knowledge test before and after fine-tuning a model on some task. This would give us a sense of how much information the model has ‘forgotten’.-->

		El "conocimiento mundial" es un concepto abstracto. Podemos probar modelos, en un nivel muy básico, para su conocimiento del mundo haciéndoles preguntas simples sobre los conceptos que nos interesan. Modelos como BERT, RoBERTa y T5 tienen miles de millones de parámetros. Teniendo en cuenta que estos modelos están entrenados en un enorme corpus de texto informativo como Wikipedia, habrían memorizado hechos usando sus parámetros y podrían responder nuestras preguntas. Además, también podemos pensar en realizar la misma prueba de conocimientos antes y después de ajustar un modelo en alguna tarea. Esto nos daría una idea de cuánta información ha "olvidado" el modelo.

[ES] Spanish translation week 12, section 2 #570

[ES] Spanish translation week 12, section 2 #570

Conversation

GastonMazzei commented Sep 18, 2020

Atcold left a comment

Choose a reason for hiding this comment

GastonMazzei commented Sep 18, 2020

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

zxul767 Sep 18, 2020 • edited

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

zxul767 left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Atcold left a comment

Choose a reason for hiding this comment

Atcold commented Sep 23, 2020

GastonMazzei commented Sep 23, 2020

Atcold commented Sep 26, 2020

zxul767 Sep 18, 2020 •

edited