Tài liệu Báo cáo khoa học: "An Empirical Investigation of Discounting in Cross-Domain Language Models" ppt

... Linguistics An Empirical Investigation of Discounting in Cross-Domain Language Models Greg Durrett and Dan Klein Computer Science Division University of California, Berkeley {gdurrett,klein}@cs.berkeley.edu Abstract We ... Kneser-Ney language model to incorporate such growing discounts, result- ing in perplexity improvements over modified Kneser-Ney and Jelinek-Mercer basel...

Ngày tải lên: 20/02/2014, 04:20

... consists of 24 computer-mediated dialogues 1 in which two participants collaborate on a simple task of buying furniture for the living and dining rooms of a house (a variant of the task in (Walker, ... and the issue of tracking agreement. Next we describe our coding scheme and our intercoder reliability outcomes. Last we report our findings .on tracking agreement. 2 Trac...

Ngày tải lên: 20/02/2014, 18:20

... extracting, or- ganizing and inter-relating the pieces of information contained in a set of relevant documents, in order to obtain a comprehensive, non redundant report that satisfies the information ... only the first step towards fulfilling an information need. The next steps consist of extracting, organizing and relating the relevant pieces of information, in or- der to obtain a...

Ngày tải lên: 20/02/2014, 15:20

... 3 [4–7]. In addition to binding DNA, the HD is a protein interac- tion module that mediates interactions with other DNA-binding proteins and non-DNA-binding tran- Keywords homeodomain; Meis; ... the interaction of Pbx1 with the Hth domain of Meis2. Target- ing of the Hth domain to DNA suggests that it is not a portable trans- acting repression domain. However, the Hth domain can inhib...

Ngày tải lên: 16/02/2014, 15:20

... DeNero and Dan Klein. 2010. Discriminative mod- eling of extraction setsfor machine translation. In Pro- ceedings of the 48th AnnualMeeting of the Association for Computational Linguistics, pages ... Massachusetts Institute of Tech- nology. John DeNero and Dan Klein. 2008. The complexity of phrase alignment problems. In Proceedings of the 46th Annual Meeting of the Associati...

Ngày tải lên: 20/02/2014, 04:20

... are divided into a training set and a testing set by a ratio of 2:1. There are 15-20 training instances for each sense of the words, and occurs by the same frequency in the training and test ... the original ambiguous word, the method introduced here does not need human tagging of training corpus. In the training stage for WSD, statistics of EPs and context words are obtaine...

Ngày tải lên: 20/02/2014, 12:20

... glosses) grammar in tandem with the treebank, as part of our research into natural language understanding. Treebanking the output of the parser allows us to immediately identify problems in the grammar, and ... availability of a reason- ably robust existing HPSG of Japanese (JACY), and a wide range of open source tools for de- veloping the grammars. We made extensive use of...

Ngày tải lên: 20/02/2014, 12:20

... degree of scattering because of the arrangement of frequencies of words in rectangular coordinates as shown in Fig. 2. In such case, there will be some problems in the point of reliability if ... obtaining the cross point of the regression straight line and the current time period in rectangular coordinates, the slope of the regression straight line can estimate th...

Ngày tải lên: 20/02/2014, 16:20

... variations here, all of which argue for the use of independent deriva- tions under certain circumstances. 3.1 Adding Adjoining Constraints Already in very early work on tree-adjoining gram- mars ... precise and operational. In service of the former, we provide a rigorous speci- fication of our proposal in terms of a compilation of TAGs into corresponding linear indexed...

Ngày tải lên: 20/02/2014, 21:20

... (see details in Section 6.1) in our word-aligned bilingual training data. Then we extract all training events for verbal predicates which occur at least 10 times in the training data. A training event ... right. ing, we run the training toolkit in a parallel manner. 4 Argument Reordering Model In this section we introduce the discriminative ar- gument reordering model, features and...

Ngày tải lên: 19/02/2014, 19:20