|
Next revision
|
Previous revision
Next revision
Both sides next revision
|
courses:rg:2013:dep-tree-kernels [2013/03/04 21:16]
kosao7am vytvořeno |
courses:rg:2013:dep-tree-kernels [2013/03/04 22:28]
popel pdf link |
| 1. Given Figure 1, what is the smallest common subtree that includes both t1 (Troops) and t2 (near)? | ====== Questions ====== |
| | Aron Culotta, Jeffrey Sorensen: [[http://www.newdesign.aclweb.org/anthology-new/P/P04/P04-1054.pdf|Dependency Tree Kernels for Relation Extraction]], ACL 2004. |
| |
| 2. Section 5: "Therefore, d(a)=l(a)." When is this true and why? (Assume this holds for the following questions.) | |
| |
| 3. Let \phi_m = {general-pos-tag, entity-type, relation-arguments} (in accordance with the paper). | - 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: "Therefore, d(a)=l(a)." When is this true and why? (Assume this holds for the following questions.) |
| Based on Figure 2 and Section 5, compute the following matching functions and similarity functions: | - Let <latex>\phi_m</latex> = {general-pos-tag, entity-type, relation-arguments} (in accordance with the paper). Let <latex>\phi_s = \phi_m</latex> (unlike in the paper). Based on Figure 2 and Section 5, compute the following matching functions and similarity functions: |
| m(t0,u0)=? m(t1,u1)=? m(t2,u2)=? | * ''m(t0,u0)=? m(t1,u1)=? m(t2,u2)=?'' |
| s(t0,u0)=? s(t1,u1)=? s(t2,u2)=? | * ''s(t0,u0)=? s(t1,u1)=? s(t2,u2)=?'' |
| | - Let <latex>\lambda=0.5</latex>. Compute the contiguous kernel for the two trees in Figure 2: <latex>K_1(T,U)=?</latex>. Provide the final number and some counts along the way, so its clear how you got the number. Optionally, compute also the sparse kernel <latex>K_0(T,U)=?</latex>. |
| 4. Let \lambda=0.5. Compute (derive and explain) the contiguous kernel for the two trees in Figure 2: | - 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: |
| K_1(T,U)=? | * <latex>K_1</latex>(DT("Peter sleeps"), DT("Bob runs"))=? |
| Provide the final "number" and some counts along the way, so its clear how you got the number. | * <latex>K_2</latex>(DT("Peter sleeps"), DT("Bob runs"))=? |
| Optionally, compute also the sparse kernel K_0(T,U). | - Lets have a pair of sentences: |
| | * "Bob saw US troops that moved towards Baghdad" |
| 5. Let DT be a function that assigns the correct augmented dependency tree to a sentence. | * "US troops that moved towards Baghdad were seen by Bob" |
| Compute (estimate) contiguous kernel and bag-of-words kernel for the following sentences: | You want to check the relation between entities "US" and "Baghdad". Compute (estimate) <latex>K_1</latex> and <latex>K_2</latex>. |
| K_1(DT("Peter sleeps"), DT("Bob runs"))=? | |
| K_2(DT("Peter sleeps"), DT("Bob runs"))=? | |
| | |
| 6. 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 "US" and "Baghdad". | |
| Compute (estimate) K_1 and K_2. | |
