Differences
This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
courses:rg:2013:dep-tree-kernels [2013/03/04 21:16] kosao7am vytvořeno |
courses:rg:2013:dep-tree-kernels [2013/03/12 11:14] (current) popel |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | 1. Given Figure 1, what is the smallest common subtree that includes both t1 (Troops) and t2 (near)? | + | ====== Questions ====== |
+ | Aron Culotta, Jeffrey Sorensen: [[http:// | ||
- | 2. Section 5: " | ||
- | 3. Let \phi_m = {general-pos-tag, | + | - Given Figure 1, what is the smallest common subtree that includes both t1 (Troops) and t2 (near)? |
- | Let \phi_s = \phi_m (unlike in the paper). | + | - Section 5: " |
- | Based on Figure 2 and Section 5, compute the following matching functions and similarity functions: | + | - Let < |
- | | + | * '' |
- | | + | * '' |
+ | - Let < | ||
+ | - Let DT be a function that assigns the correct augmented dependency tree to a sentence. Compute (estimate) contiguous kernel and bag-of-words kernel for the following sentences: | ||
+ | * < | ||
+ | * < | ||
+ | - Lets have a pair of sentences: | ||
+ | * "Bob saw US troops that moved towards Baghdad" | ||
+ | * "US troops that moved towards Baghdad were seen by Bob" | ||
+ | You want to check the relation between entities " | ||
+ | |||
+ | ====== Answers ====== | ||
+ | - Depends on the exact definition of smallest common subtree, but keep in mind you need at least some non-trivial " | ||
+ | - d(a) is defined as the last member of the sequence - the first member + 1. If the sequence is contiguous (no missing indices) it can be shown (eg. by induction) that the equation holds, unless some of the indices is repeated. Note that e.g. a sequence (1,1,1) is valid according to the definition of sequence < | ||
+ | - Depends on how you treat " | ||
+ | * '' | ||
+ | * '' | ||
+ | - First this depends on the previous one (the " | ||
+ | * < | ||
+ | * When counting K_1 you leave out the < | ||
+ | - When you regard bag-of-words kernel as number of matching forms then K_2 is zero whereas K_1 is positive | ||
+ | - It was argued that we'll probably end up with different relation-args (//troops// being ARG_B in the first sentence, but ARG_A in the second sentence), thus there will be no match | ||
+ | | ||
- | 4. Let \lambda=0.5. Compute (derive and explain) the contiguous kernel for the two trees in Figure 2: | + | ====== Misc ====== |
- | | + | - There was some discussion what are the features for bag-of-words kernel (just presence of a word in sentence?) |
- | Provide the final " | + | - Feature selection, mainly the relation-args feature |
- | | + | |
- | + | ||
- | 5. Let DT be a function that assigns the correct augmented dependency tree to a sentence. | + | |
- | | + | |
- | K_1(DT(" | + | |
- | K_2(DT("Peter sleeps"), DT(" | + | |
- | + | ||
- | 6. Lets have a pair of sentences: | + | |
- | " | + | |
- | " | + | |
- | You want to check the relation between entities " | + | |
- | | + |