Báo cáo khoa học: "Using Restriction to Extend Parsing Algorithms for Complex-Feature-Based Formalisms" pptx

... Using Restriction to Extend Parsing Algorithms for Complex-Feature-Based Formalisms Stuart M. Shieber Artificial Intelligence Center SRI International and Center for the Study of ... 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 i...

Ngày tải lên: 31/03/2014, 17:20

... generative story for the observed data. Each generated word token corresponds to a customer sit- 85 ting at one of the unboundedly many tables in an imaginary Chinese restaurant. Customers choose their ... table. The former hap- pens with probability proportional to the number of customers already sitting at a table and corresponds to generating one more token of the word type all cus...

Ngày tải lên: 30/03/2014, 17:20

... 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) A form of asbestos ... and Temporal (information in two clauses are related because of their timing). These top-level discourse relation senses are general enough to be annotated with high inter-annotator agreeme...

Ngày tải lên: 08/03/2014, 01:20

... hands’ for the relation for the compound vegetable truck but the verb sense ‘carries: transmits or serves as the medium for transmission’ for the compound ra- dio wave, for example). To return ... created for this annotation task, showing the annotator the compound to be annotated and the WordNet gloss (meaning) for that compound (see Figure 1). This page also showed the ann...

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 ... annotators (1 to 22) according to the degree of agreement with the rest, separately for each text, and average over the texts to obtain the conformity rank of an annotator....

Ngày tải lên: 17/03/2014, 06:20

... 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-23) under ... an- cestor class that is too general to meet the communica- tive goal; if the user is simply told "Perform an action on the switch", he will not know that he is supposed to...

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

... ability to listen to incoming SMS messages using text -to- speech (TTS). Au- tomatic speech recognition (ASR) affords users a hands-free, eyes-free method of replying to SMS messages. However, to ... respect to the top n-best reply candidates. The voice search approach consistently outperformed dictation and canned responses, achieving as high as 89.7% task completion with re...

Ngày tải lên: 23/03/2014, 16:20

... “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