Course talk:CPSC522/Analysis of hierarchical prior for Language modeling
|Thread title||Replies||Last modified|
|Critique||1||16:14, 19 April 2018|
|Helpful suggestions||1||16:13, 19 April 2018|
On a scale of 1 to 5, where 1 means "strongly disagree" and 5 means "strongly agree" please rate and comment on the following:
- 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). 4
- The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 5
- The abstract is a concise and clear summary. 0
- There were appropriate (original) examples that helped make the topic clear. 4
- There was appropriate use of (pseudo-) code. 0
- 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. 5
- It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 5
- It links to appropriate other pages in the wiki. 3
- The references and links to external pages are well chosen. 4
- I would recommend this page to someone who wanted to find out about the topic. 5
- 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: 19
- A good page; no real complaints other than a missing abstract.
- Would it be possible to include some code?
- Maybe you can include links to the Recurrent Neural Network page, as well as links to LSTM and GRU.
- Nitpick: You can format the evaluation results' images so that they run horizontal across the page.
Its a thorough document. Here are three suggestions:
# Can you include a link to your code repository &/or a code snippet? # Can you include an abstract? # Can you describe your experimental setup - i.e I learnt only in your conclusion that you used TF and 2 models. Maybe you can put that before and also mention what the models are.