Differences
This shows you the differences between two versions of the page.
Last revision Both sides next revision | |||
courses:rg:unsupervised-methods-for-head-assignments [2011/05/19 15:02] bejcek vytvořeno |
courses:rg:unsupervised-methods-for-head-assignments [2011/05/23 10:34] popel Section 5 -> Equation 5 + more details |
||
---|---|---|---|
Line 5: | Line 5: | ||
===== Introduction ===== | ===== Introduction ===== | ||
- | * The paper describes **two** methods for **unsupervised** head assignment and tests them on **two** corpora | + | * The paper describes **two** methods for **unsupervised** head assignment and tests them on **two** corpora |
* It is the **first** successful unsupervised head assignment. | * It is the **first** successful unsupervised head assignment. | ||
* There is a problem when converting dependency structures into head annotations: | * There is a problem when converting dependency structures into head annotations: | ||
===== What do we dislike about the paper ===== | ===== What do we dislike about the paper ===== | ||
- | * There is a wrong definition of **entropy** in Section 5. | + | * Equation 5 is misleading/wrong: entropy is here computed for the distribution |
- | * We found three possible interpretations of "// | + | * We found three possible interpretations of "// |
+ | - apply one fixed annotation of the heads (but it can be any annotation) | ||
+ | - apply the (partial) annotation which is consistent with all possible head annotations | ||
+ | - apply all possible head annotations | ||
* It is also unclear, what " | * It is also unclear, what " | ||
* The **greediness** of the entropy model could be its main weakness resulting in not so good numbers. | * The **greediness** of the entropy model could be its main weakness resulting in not so good numbers. |