Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
courses:rg:2012:segments [2012/12/29 15:22] bilek |
courses:rg:2012:segments [2013/01/03 22:38] (current) popel |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ===Introduction, | + | =====Introduction, |
We introduced the basic idea of Czech sentence segmentation and the Czech sentence boundaries. We showed the segmentation chart on an example. | We introduced the basic idea of Czech sentence segmentation and the Czech sentence boundaries. We showed the segmentation chart on an example. | ||
- | ===Experiments with Automatic Identification of Segmentation Charts=== | + | =====Experiments with Automatic Identification of Segmentation Charts===== |
- | ==How to Obtain Segments from Syntactic Tree?== | + | ====How to Obtain Segments from Syntactic Tree?==== |
We are unsure of the exact definition of Edge and Path between the segments in this part. | We are unsure of the exact definition of Edge and Path between the segments in this part. | ||
Line 21: | Line 21: | ||
The most important question, though, is why do we do all this, because the data from the PDT tree are more thorough than the segments that we want to create! So, what is the exact reason? | The most important question, though, is why do we do all this, because the data from the PDT tree are more thorough than the segments that we want to create! So, what is the exact reason? | ||
- | 1) it is not because there are the training data | + | 1) To prepare |
- | 2) it is not because | + | > Probably no, because |
- | 3) It can be to show that it is difficult to create from the analytical tree, too | + | 2) To prepare |
- | 4) We can use it as a " | + | > No. Because they already have some manually annotated sentences. Moreover, the described approach (using PDT gold a-trees on input) |
+ | 3) As an " | ||
+ | > Probably no. There are better algorithms (with higher precision than 70%) exploiting gold a-trees. | ||
+ | 4) To show some difficult cases with creating segmentation charts (even when gold a-trees are available). | ||
+ | > Maybe. | ||
5) It can be just to fill up the space :) | 5) It can be just to fill up the space :) | ||
+ | > ? | ||
- | ==How to Obtain Segments from Plain Text?== | + | ====How to Obtain Segments from Plain Text?==== |
On the beginning we talk about the basic set of rules for subordination. They are some that could be made better; for example, the quotes for highlightning. | On the beginning we talk about the basic set of rules for subordination. They are some that could be made better; for example, the quotes for highlightning. | ||
Line 36: | Line 41: | ||
- | ===Evaluation and Analysis of the Results=== | + | =====Evaluation and Analysis of the Results===== |
- | ==Evaluation of Rules for Syntactic Trees== | + | ====Evaluation of Rules for Syntactic Trees==== |
Is 57% enough? 73% sounds like a more important number, but it is still not enough. | Is 57% enough? 73% sounds like a more important number, but it is still not enough. | ||
Line 49: | Line 54: | ||
" | " | ||
- | ==Evaluation of Rules for Plain Text== | + | ====Evaluation of Rules for Plain Text==== |
The question - why are these results better than the first experiment? | The question - why are these results better than the first experiment? | ||
Line 58: | Line 63: | ||
What means " | What means " | ||
- | ===Conclusion=== | + | =====Conclusion===== |
Nice idea - we can do some quick, but reliable preprocessing. However, the authors don't show how much it's helping the parsers (if it does). We don't even see the precision written. | Nice idea - we can do some quick, but reliable preprocessing. However, the authors don't show how much it's helping the parsers (if it does). We don't even see the precision written. | ||
Line 64: | Line 69: | ||
It is slightly light on information, | It is slightly light on information, | ||
- | ===Questions=== | + | =====Questions===== |
We can do step with the size 2 with indirect speech. | We can do step with the size 2 with indirect speech. | ||
řekl, že když se budeš modlit, tak se ti přání splní | řekl, že když se budeš modlit, tak se ti přání splní |