Báo cáo khoa học: "Parsing without lexicon: the MorP system" pot

Báo cáo khoa học: "Parsing without lexicon: the MorP system" pot

Báo cáo khoa học: "Parsing without lexicon: the MorP system" pot

... Keywords: parsing, morphology. The development of the parser to be presented has been supported by the Swedish Research Council for the Humanities. The parser is called MorP, for morphology based ... after 1,000 words. The texts were run through the MorP parser and the output was compared to the manual tagging of the texts. MorP was run by a batch file that cal...

Ngày tải lên: 18/03/2014, 02:20

6 107 0
Báo cáo khoa học: "Acquiring a Lexicon from Unsegmented Speech" potx

Báo cáo khoa học: "Acquiring a Lexicon from Unsegmented Speech" potx

... words from the parse to better fit the utterance. • Finally, it reparses the utterance with the old dictionary and the new words, and adds the new words to the dictionary if the resulting ... generated by tak- ing the union of the sememe for each word in the utterance. Figure 1 contains the first 6 utterances from the database. We describe the results of a...

Ngày tải lên: 08/03/2014, 07:20

3 315 0
Báo cáo khoa học: Unique features of the hemoglobin system of the Antarctic notothenioid fish Gobionotothen gibberifrons ppt

Báo cáo khoa học: Unique features of the hemoglobin system of the Antarctic notothenioid fish Gobionotothen gibberifrons ppt

... consequently, the curves are similar to those obtained with the stripped hemolysate in the presence of effectors. Discussion In the Antarctic suborder Notothenioidei, most species of the family Nototheniidae ... and 5% of the total, respectively) [2, 4,14]. The two Hbs have the b-chain in common, with the exception of those of Cygnodraco mawsoni [15] which share the a-chai...

Ngày tải lên: 08/03/2014, 08:20

7 417 0
Báo cáo khoa học: "Building Emotion Lexicon from Weblog Corpora" potx

Báo cáo khoa học: "Building Emotion Lexicon from Weblog Corpora" potx

... as the number of emotion classes decreases. The upper bound recall indicates the upper limit on the fraction of the 307,751 instances solvable by the corresponding method and thus reflects the ... as votes. Label S with the emotion that receives the most votes. (2) If more than two emotions get the same num- ber of votes, then label S with the emotion that has the m...

Ngày tải lên: 17/03/2014, 04:20

4 302 0
Báo cáo khoa học: "Parsing Mildly Non-projective Dependency Structures" potx

Báo cáo khoa học: "Parsing Mildly Non-projective Dependency Structures" potx

... dependents, and to the hy- pothesis [h, h, h, , ]. This allows us to infer p items representing the result of linking each of the dependent subtrees to the new head w h ; (2) ap- plying the various ... tied to the D-rules associated with the links they create. In this way, we ob- tain a representation of the underlying logic of the parser while abstracting away from contro...

Ngày tải lên: 17/03/2014, 22:20

9 231 0
Báo cáo khoa học: "Dialogue Processing in a CALL-System" pot

Báo cáo khoa học: "Dialogue Processing in a CALL-System" pot

... dialogue with the computer as the seller of the tickets. The motivation for the development of the sys- tem arises from the above mentioned pedagogi- cal considerations and the insight that ... case the police officer wants to know all about the accident and possible casualties and in the latter case the pizza deliv- ery wants to know the toppings and size of...

Ngày tải lên: 17/03/2014, 23:20

4 333 0
Tài liệu Báo cáo khoa học: "Parsing, Projecting & Prototypes: Repurposing Linguistic Data on the Web" doc

Tài liệu Báo cáo khoa học: "Parsing, Projecting & Prototypes: Repurposing Linguistic Data on the Web" doc

... 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 othe...

Ngày tải lên: 22/02/2014, 02:20

4 433 0
Báo cáo khoa học: "Endocentric Constructions and the Cocke Parsing Logic" ppt

Báo cáo khoa học: "Endocentric Constructions and the Cocke Parsing Logic" ppt

... elements are gathered together in pairs, namely: (all (the (old (men (on the corner) ) ) ) ) , (all (the ((old men) (on the corner)))), (all ( (the (old men)) (on the corner))), ((all (the (old ... tests their connectability by looking them up in the stored table of constructions, that is, in the grammar. If the ordered pair is matched by a pair of IC's in the...

Ngày tải lên: 07/03/2014, 18:20

6 300 0
Báo cáo khoa học: "Parsing Free Word Order Languages in the Paninian Framework" pptx

Báo cáo khoa học: "Parsing Free Word Order Languages in the Paninian Framework" pptx

... hE. 2The transformation rules are a device to represent the karaka charts more compactly. However, as is obvious, they affect the karaka charts and not the parse structure. There- fore, they ... in the sen- tence. The Paninian framework is similar to the broad class of case based grammars. What distinguishes the Paninian framework is the use of karaka re- lations rath...

Ngày tải lên: 08/03/2014, 07:20

7 353 0
Báo cáo khoa học: "PARSING VS. TEXT PROCESSING IN THE ANALYSIS OF DICTIONARY DEFINITIONS" pot

Báo cáo khoa học: "PARSING VS. TEXT PROCESSING IN THE ANALYSIS OF DICTIONARY DEFINITIONS" pot

... sample definition and the triples the parser found in it. ABDOMEN 0 1 N THE PART OF THE BODY BETWEEN THE THORAX AND THE PELVIS (THE) pmod (PART) (ABDOMEN 0 1 N) lm (THE) (ABDOMEN 0 1 N) ... speed. Input to the parser was a set of 8,832 definition texts from the machine-readable WT, chosen because their vocabulary permitted them to be parsed without enlarging the...

Ngày tải lên: 08/03/2014, 18:20

8 461 0
Từ khóa:
w