Course talk:CPSC522/Natural Language Processing

From UBC Wiki

Contents

Thread titleRepliesLast modified
Critique007:31, 7 February 2018
Critique023:03, 5 February 2018
Critique 020:10, 4 February 2018
   The topic is relevant for the course. 5
   The writing is clear and the English is good. 5
   The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 5
   The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 5
   The abstract is a concise and clear summary. 5
   There were appropriate (original) examples that helped make the topic clear. 5
   There was appropriate use of (pseudo-) code. 3 (Although there wasn't pseudocode, given what you covered it wasn't really needed. Could be helpful if the page is expanded though.)
   It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 5
   It is correct. 5
   It was neither too short nor too long for the topic. 2 (It would be nice to expand the page a bit, especially with such a broad topic. Maybe the page could expand some of the syntactic/semantic tasks described earlier?)
   It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 3 (This page could probably be split up a bit into a few different pages, each of the syntactic/semantic tasks could probably just be their own page. Although I do think the page works as a broad intro on its own as well.)
   It links to appropriate other pages in the wiki. 4
   The references and links to external pages are well chosen. 5
   I would recommend this page to someone who wanted to find out about the topic. 4
   This page should be highlighted as an exemplary page for others to emulate. 4

If I was grading it out of 20, I would give it: 16 (I think it just needs to be expanded a little, but overall it's a good intro to the subject)

DavidJohnson (talk)07:31, 7 February 2018

On a scale of 1 to 5, where 1 means "strongly disagree" and 5 means "strongly agree"

  • The topic is relevant for the course - 5
  • The writing is clear and the English is good - 4 (The Abstract is not coherent. Could rephrase it.)
  • The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds) - 5
  • The formalism (definitions, mathematics) was well chosen to make the page easier to understand - 5
  • The abstract is a concise and clear summary - 5
  • There were appropriate (original) examples that helped make the topic clear - 5
  • There was appropriate use of (pseudo-) code - 3 (Could add details of a few NLP algorithms)
  • It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). - 2 (Not covered. Need to give a few details about each one)
  • It is correct - 5
  • It was neither too short nor too long for the topic - 3 (A bit Short. Could expand on different language models (character/word) and Word2vec)
  • It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page) - 3
  • It links to appropriate other pages in the wiki - 4 (Doesn't currently)
  • The references and links to external pages are well chosen - 5
  • I would recommend this page to someone who wanted to find out about the topic - 4
  • This page should be highlighted as an exemplary page for others to emulate - 4

If I was grading it out of 20, I would give it: 15

KevinDsouza (talk)23:02, 5 February 2018

NLP:

Suggestions for related pages could be algos that are used in NLP such as: word2vec, summarizer, etc.

Word segmentation edit: “This may be a difficult task as in some languages, like Chinese, the words are not separated by spaces.”

For each of the NPL tasks I would suggest linking each task to a different wiki page. Additionally, you could expand this section but having a definition and example for each of the tasks.

The first section of language models is a little awkward. I feel as if it needs more content. Also, some probabilities are in LaTeX and some are not. I would opt to keep things consistent.

I would say add more depth to the word2vec section so that it is similar to the N-Gram model section.

  • The topic is relevant for the course. 5 (However it is very broad. To make it easier perhaps try to narrow the focus?)
  • The writing is clear and the English is good. 5
  • The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 5
  • The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 3 (there is some inconsistency, see above)
  • The abstract is a concise and clear summary. 4 (I would add to it)
  • There were appropriate (original) examples that helped make the topic clear. 5
  • There was appropriate use of (pseudo-) code. 1 (need to add)
  • It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 5
  • It is correct. 5
  • It was neither too short nor too long for the topic. 2 (it is currently too short but it is apparent that it will be expanded)
  • It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 3
  • It links to appropriate other pages in the wiki. 3
  • The references and links to external pages are well chosen. 5
  • I would recommend this page to someone who wanted to find out about the topic. 4
  • This page should be highlighted as an exemplary page for others to emulate. 5

If I was grading it out of 20, I would give it: 16

VanessaPutnam (talk)20:10, 4 February 2018