Báo cáo khoa học: "Using Rejuvenation to Improve Particle Filtering for Bayesian Word Segmentation" doc

... Association for Computational Linguistics, pages 85–89, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Using Rejuvenation to Improve Particle Filtering for Bayesian ... here is to use rejuvenation; the core idea is to restore sample diversity after each resampling step by per- forming MCMC resampling steps on each particle s...

Ngày tải lên: 30/03/2014, 17:20

... “They came to outside”, the preposition to is an extrane- ous error whereas in the sentence “They arrived to the town” the preposition to is a confusion er- ror (cf. arrived in the town). Most ... usually reported (a single number for unweighted precision/recall over the whole corpus). For example, from this graph, PERC is seen to have similar performance as LM for the 75-90%...

Ngày tải lên: 30/03/2014, 21:20

... These formalisms were intended to free us from the tyranny of atomic nonterminal symbols, but for good performance, we are forced toward analyses putting more and more informa- tion in an atomic ... used to guide the parse, say major category information, only such information can be used to filter spurious hypotheses by top-down filtering. Note that this problem occurs even i...

Ngày tải lên: 31/03/2014, 17:20

... multi -word strings, it is less likely for a word near the beginning or end of a sentence to be at an edu boundary. Thus it is reasonable to expect the position within a sentence of a token to be ... paragraph boundaries in the RST-DT do not correspond to a well-formed subtree in the hu- man annotated discourse parse for that document. Therefore, to perform accurate and effici...

Ngày tải lên: 08/03/2014, 02:21

... dominates the words in the connective but nothing else. For single word connectives, this might correspond to the POS tag of the word, how- ever for multi -word connectives it will not. For example, ... asbestos fiber, crocidolite, is unusually resilient once it enters the lungs, with even brief exposures to it causing symptoms that show up decades later, re- searchers said. (2b)...

Ngày tải lên: 08/03/2014, 01:20

... possible WordNet senses for the modifier noun and head noun in the compound, allowing the annotator to select the correct WordNet sense for each word. After selecting correct senses for the words ... with the correct WordNet noun senses for constituent words, the correct semantic relation between those words, and the correct WordNet verb sense for that relation. In addition to...

Ngày tải lên: 08/03/2014, 02:21

... dataset relating to one topic and tested that model using the other top- ics. Figure 1 shows the results of this experiment. The tendency seems to be that performance in a given topic is best if ... 68.9 81.1 Figure 1: Topic dependency in sentiment classification. Ac- curacies, in percent. Best performance on a test set for each model is highlighted in bold. does not perform to the sta...

Ngày tải lên: 17/03/2014, 06:20

... co-markup matrix for all annotators 5 ; then for all but one annotators, and by subtraction find the portion that is due to this one annotator. We then regard the data as two-annotator data (one 4 whatever ... of the 10 texts, each person was given the text to read, and a separate wordlist on which to write down annota- tions. The wordlist contained words from the text, in their appe...

Ngày tải lên: 17/03/2014, 06:20

... is formed from the information speci- fied in the content-determination rule. • Surface Realisation: The SPL is converted into a surface form, i.e., actual words interspersed with text-formatting ... model) are then used to choose between the re- maining lexicalizable ancestors. For example, to lexicalize the action (Activate with role fillers Actor:Sam and Actee:Toggle- Switch...

Ngày tải lên: 17/03/2014, 08:20

... passed on to another component, the surface generator. The job of generator is to use whatever syntactic and lexical information is needed to translate the logical propositions into English. ... needed to devise a method for automatically generating DCG rules. 8. Conclusions We have shown how focus of attention can be used as the basis for a language generator to decide...

Ngày tải lên: 17/03/2014, 19:21