parsing the lob corpus

Ngày tải lên: 31/03/2014, 18:20

Ngày tải lên: 08/03/2014, 18:20

... would rather spend their time annotating text than learning how to use the system. The software is thus designed from the ground up to support typical user work- flow, and everything the user ... levels, the main window of the CorpusTool is thus a window for project management (see Figure 1). 13 This window allows the user to add new annota- tion layers to the project, and edit/extend the ... perform cross- layer searches of the corpus. 1 Introduction In the last 20 years, a number of tools have been developed to facilitate the human annotation of text. These have been necessary where...

Ngày tải lên: 20/02/2014, 09:20

... because the they are separated by a short barrier. One speak- er, designated the Instruction Giver, has a route marked on her map; the other speaker, the In- struction Follower, has no route. The ... front of the other and are separated by a short barrier or a full screen. They both have a map with some objects. Some of them are in the same position and with the same name, but most of them ... each other (e. g. Maso Michelini vs. Maso Nichelini, see Fig. 1). One participant (the giver) must drive the other participant (the follower) from a starting point (the bus station) to the...

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 17/03/2014, 00:20

Ngày tải lên: 17/03/2014, 05:20

Ngày tải lên: 23/03/2014, 16:20

Ngày tải lên: 23/03/2014, 18:20

Ngày tải lên: 23/03/2014, 19:20

Ngày tải lên: 23/03/2014, 20:20

Ngày tải lên: 01/04/2014, 00:20

... When the slide is displayed, the title is shown but the type of the slide isn't. Finally, in this example, the consumer of the title information is the presentation audience, while the consumer ... multiple areas on a page and then link them together. When a text stream is directed at the collection, it fills the first area and then "flows" into the second when the first area is filled. ... created without any specific instructions, then the transformer object simply copies the source to the result. The XSLT Packages The XSLT APIs are defined in the following packages: Package Description http://java.sun.com/xml/jaxp-1.1/docs/tutorial/overview/3_apis.html...

Ngày tải lên: 16/10/2013, 12:15

... out of context start tag. In fact, they're really the same error. The problem is never caused by the missing end tag per se, rather it's caused by the fact that something following ... in the test chapter. It is unremarkable in every regard. This is a paragraph in the test chapter. It is The telltale sign that SP could not find the DTD, or some module of the DTD, is the ... The xp distribution includes several sample programs. One of these programs, Time, performs a validating parse of the document and prints the amount of time required to parse the DTD and the...

Ngày tải lên: 21/01/2014, 06:20

... corpora, we would expect the opposite effect. The larger the unanno- tated corpus, the better the combined system should p erform. While there is a general ten- dency to this effect, the improvements in ... below). The MI of each point in the lattice is com- puted. We then take the maximum over all MI values of the lattice as a measure of the affinity of attachment phrase and attachment node. The intuition ... from p, either on the right side (the attachment phrase) or on the left side (the at- tachment node). For RC attachment, general- izations other than elimination are introduced such as the replacement...

Ngày tải lên: 20/02/2014, 12:20

... derivations, the probability of a tree is the sum of the probabilities of the derivations producing that tree. The probability of a derivation is the product of the subtree probabilities. The original ... the number of subtrees headed by nodes with nonterminal A, that is a = Σ j a j . Then there is a PCFG with the following property: for every subtree in the training corpus headed by A, the ... subtrees thereof on a held- out corpus, either by taking their relative frequencies, or by iteratively training the subtree parameters using the EM algorithm (referred to as “UML-DOP”). The main...

Ngày tải lên: 20/02/2014, 12:20

... 0.2697 Y= the first right brother of the parent 0.1068 0.3717 0.2133 Y= the first left brother of the parent 0.2505 1.5603 0.6145 5.2 The analysis to the influence of the structural relation and the ... 1.1598 (Y= the parent) 0.4730 (Y= the first right brother) 0.2505 (Y= the first left brother of the parent) 0.0949 (Y= the second left brother) SD=2 0.6483 (Y= the grandpa) 0.1066 (Y= the second ... 1.1525 0.7502 Y= the first left brother of the current node 0.5832 2.1511 1.2186 Y= the second right brother of the current node 0.1066 0.5044 0.2525 Y= the second left brother of the current node...

Ngày tải lên: 20/02/2014, 18:20

... and b) and another edge which has been built from them (edge c), the latter should get a bet- ter score than the sequence of the original two edges. If there is another edge from the parser which ... results. The deci- sion when to switch to the next best path of a given WHG depends on the length of the input and on the time already used. After the pars- ing of one path is finished, the passive ... system, since they would distort the picture. For this same rea- son, the criterion we apply is whether the result delivered is a sensible combination of the frag- 411 Charting the Depths of...

Ngày tải lên: 20/02/2014, 19:20

... 189,244. We then ran the new language ID algorithm on the IGTs, and Table 1 shows the language distribution of the IGTs in ODIN according to the output of the algorithm. For instance, the third ... the crawled documents as ungrammatical (usually with an asterisk “*” at the beginning of the language line). Those IGTs are kept in ODIN too because they could be useful to other linguists, the ... 90%. The discovered knowledge can then be used for subsequent grammar and tool development work. The knowledge we capture in IGT instances—both the native annotations provided by the linguists them- selves,...

Ngày tải lên: 22/02/2014, 02:20

... extracted from the corpus. The enforcement of this criterion reduces on one hand the recall of the dis- course markers that can be detected, but on the other hand, increases significantly the precision. ... represented as binary trees. On the basis of the data derived from the corpus ,anal- ysis, the algorithm hypothesizes the following set of re- lations between the textual units: rhet_rel(JUSTIFICATION, ... of the marker in the textual unit to which it belonged: Begin- ning, Medial, or End. 4. The right boundary of the textual unit associated with the marker. 5. The relative position of the...

Ngày tải lên: 22/02/2014, 03:20

... expect the symbol below the top of the stack to give us the node where 3 is adjoined. If r/is not on the spine of an auxiliary tree then it is the only symbol on the stack. We now show how the ... result of the linearity in the rules, the stack ~/a associated with the object in the left-hand side of the derivation and the stack j3cJ associated with one of the objects in the right-hand ... the lig shared forest the set VI is the set of the elementary node addresses of the object tag grammar Go. The set of final states, F, of MG,. is the set VT. The transition function...

Ngày tải lên: 22/02/2014, 10:20