Báo cáo khoa học: "Automatic Induction of Finite State Transducers for Simple Phonological Rules" pptx

... Automatic Induction of Finite State Transducers for Simple Phonological Rules Daniel Gildea and Daniel Jurafsky International Computer Science Institute and University of California at Berkeley ... have chosen to represent rules as subse- quential finite state transducers. Subsequential finite state transducers are a subtype of finite state transduc-...

Ngày tải lên: 08/03/2014, 07:20

... re- strictive form of free order CCG. Both Hoffman and Baldridge ignore morphology and treat the inflected forms as different words. The rest of this section contains an overview of the underlying formalism ... consist of morphological infor- mation like existence of a “PRESPART” morpheme in (8), and part -of- speech of the word. However, there is still a problem in cases like (9a)...

Ngày tải lên: 17/03/2014, 06:20

... set of rules (and in- crease recall) we next performed a simple transfor- mation of the derived rule set. If all children of a rule tree node are of type *scope* or * (i.e. non- cue words), the ... developed a super- vised classifier for identifying speculation cues and a manually compiled list of lexico-syntactic rules for identifying their scopes. For the performance of t...

Ngày tải lên: 20/02/2014, 04:20

... ill-formed input can be characterized as finite state transducers (Lang, 1989); the composition of an input string with such a finite state transducer results in a FSA that can then be input for ... FSA. It is also straight- forward to show that the complexity of this process is cubic in the number of states of the FSA (in the case of ordinary parsing the number of...

Ngày tải lên: 31/03/2014, 06:20

... have chosen for the systems to be generated is the one of expert systems because the design of software for an MT system of the scope of gurotra has much in common with the design of a very ... Specialized vs generic software tools for MT Developing the software for a specific task or class of tasks requires that one knows the structure of the tasks involved. In th...

Ngày tải lên: 08/03/2014, 18:20

... where: V is the set of the states of T, i its initial state, F the set of its final states, A and B respectively the input and output alphabet of the transducer, ~ the state transition function ... use of a great set of complex rules of. ten difficult to check, handle, or even understand. Finite- state automata and transducers can also be used to represent the syntac...

Ngày tải lên: 23/03/2014, 20:21

... rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of 4.4% over the state -of- the-art methods. 1 Introduction Recently, ... ex- amples of the previous section. From the point of view of bag -of- word methods, the pairs (T 1 , H 1 ) and (T 1 , H 2 ) have both the same intra-pair simi- larity...

Ngày tải lên: 20/02/2014, 12:20

... there are two sentences in each of the 454 (1) kono software-no riten-ha hayaku ugoku koto this software-POST advantage-POS T quickly run to The advantage of this software is to run quickly. (2) ... the polarity of words There are some works that discuss learning the po- larity of words instead of sentences. Hatzivassiloglou and McKeown proposed a method of learning the polarity...

Ngày tải lên: 20/02/2014, 12:20

... out two separate sets of experiments, for the domains of mp3 players and restaurant reviews. We divided data into 80% for training, 10% for development, and 10% for test for our experiments. ... there are somewhat a fixed set of features of a specific type of product, for exam- ple, ease of use, durability, battery life, photo quality, and shutter lag for digit...

Ngày tải lên: 20/02/2014, 12:20

... according to a mix of the initial method of Section 3.2, for calibration, and the new methods above. We again used a sentence length of 24, and sequence lengths for the initial method of l = 1, 8, ... 24. A sample of sentences gen- erated for each of these six types is in Figure 3. For our data, we generated 1000 sentences per gen- eration method, giving a corpus of 6000...

Ngày tải lên: 20/02/2014, 12:20