Báo cáo khoa học: "A Bayesian Model for Unsupervised Semantic Parsing" ppt

... θ c,t [draw sem class for arg] GenSemClass(c  c,t ) [recurse] Figure 2: The generative story for the Bayesian model for unsupervised semantic parsing. tributions over syntactic paths for the argument type ... Association for Computational Linguistics, pages 1445–1455, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Bayesian Model...

Ngày tải lên: 23/03/2014, 16:20

... use a nearly identical model to the FLAT model, but instead of having a single m variable, we have three: one for IE, one for Austronesian and one for “all languages.” For a general tree, we ... in Figure 3 (on a log-scale for the x-axis). The two best-performing models are the two hier- archical models. The flat model does significantly worse and the random model does terribly...

Ngày tải lên: 08/03/2014, 02:21

... the Association for Computational Linguistics, pages 469–477, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics A Statistical Model for Unsupervised and ... labelled information for training. Our sys- tem extracts transliteration pairs in an unsupervised fashion. It is also able to utilize labelled information if available, obtaining impr...

Ngày tải lên: 19/02/2014, 19:20

... of the Association for Computational Linguistics, pages 1048–1057, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics A Statistical Model for Lost Language Decipherment Benjamin ... generative Bayesian model. This model assumes that each word in the lost language is composed of mor- phemes which were generated with latent coun- terparts in the kno...

Ngày tải lên: 17/03/2014, 00:20

... search for argument key clustering with the factored model and then discuss its extension ap- plicable to the coupled model. 6.1 Role Induction For the factored model, semantic roles for every predicate ... introduce two Bayesian models for un- supervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters...

Ngày tải lên: 17/03/2014, 22:20

... University) for excellent technical assistance. This work was supported by grants from the Swedish Foundation for Health Care Sciences and Allergy Research, the Swedish Research Council for Medicine ... the fate of an aller- gen upon inhalation, we addressed this issue for a major dust mite allergen, Der p 2. First, a model for Der p 2-sensitization was established in C57BL ⁄ 6 J...

Ngày tải lên: 07/03/2014, 21:20

... different qualities. For example, both topic “css test” and “test suite” are the bi-gram matching for query “css test suite”; however, the former might be more informative. To model that, we use ... following sub-sections, we will detail two sub-models: the expert matching model P(c|e) and the evidence matching model P(e|q). 3.2 Expert Matching Model We expand the evidence...

Ngày tải lên: 08/03/2014, 01:20

... certain kinds of shallow semantic information (such as verb tense). The tags are useful for identifying verbs, nouns, and adverbs, and the words themselves repre- sent lexico -semantic information in the ... predicates like force generally introduce E-type SEs: (7) I forced [John to run the race with me]. (8) * I forced [John to know French]. The feature force-PREV is extracted if a memb...

Ngày tải lên: 08/03/2014, 02:21

... used, and sub- section 2.2 describes the model. 2.1 The Formalism In order to handle the non-linear phenomenon of Arabic, our model adopts the two-level formalism presented by (Pulman and Hepple, ... first to appear on the left of LEx. In our morphographemic model, we add a similar formalism for expressing error rules (3). (3) ERROR FORMALISM ErrSurf =~ Surf { PLC- PRC } whe...

Ngày tải lên: 08/03/2014, 07:20

... of the Association for Computational Linguistics, pages 885–894, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Discriminative Model for Joint Morphological ... Experimental Results We compare the performance of the pipeline model (§4) and the joint model (§3) on morphological dis- ambiguation and unlabeled dependency parsing. Model Tagge...

Ngày tải lên: 17/03/2014, 00:20