Báo cáo khoa học: "Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach" docx

... of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach Hao Tang, Joseph Keshet, and Karen Livescu Toyota ... sur- face pronunciations, the ways a speaker may actu- ally produce the word. In the task of lexical access we are given a surface pronunciation of a word, and our goal i...

Ngày tải lên: 16/03/2014, 19:20

... Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm Brian Roark Murat Saraclar AT&T Labs - Research {roark,murat}@research.att.com Michael Collins Mark ... lattice-based MMIE/CMLE in challenging large scale ASR tasks such as Switchboard. In fact, state-of-the-art acoustic modeling, as seen, for example, at annual Switchboard evaluations, invariably...

Ngày tải lên: 23/03/2014, 19:20

... uses a large-vocabulary tagger (Ratnaparkhi, 1996) as a preprocessing stage may compensate for its smaller vocabu- lary. Also, the main reason for using a smaller vocabulary is the computational ... computationally tractable for large datasets and a good approximation to the theoretically optimal method. The parser which uses this approach outperforms both a genera- tive model and...

Ngày tải lên: 23/03/2014, 19:20

... parses (Taskar et al., 2004; McDonald et al., 2005). A radically different approach is to perform disambiguation deterministically, using a greedy parsing algorithm that approximates a globally ... tries to separate positive and negative cases in training data by a hyperplane using a linear kernel function. The goal is to find the hyperplane that separates the training data into two...

Ngày tải lên: 23/03/2014, 18:20

... ac- quaintance with the associated causal relation (pursuing a global goal) rain state (e.g., 'I want to have my mon- ey back'), the application of another rule almost identical to ... interacting agents. Knowledge about the state of the dialog is represented in a dedicated language and changes of this state are described by a compact set of rules. An appropri- ate or...

Ngày tải lên: 24/03/2014, 05:21

... increased character accuracy to the relat ive increased MAP for the three lexicon adaptation ap- proaches are different. A key factor making the proposed LAICA approach advantageous is that we ... parts randomly: 5K as the adaptation corpus and 5K as the testing set. We show the ASR char- acter accuracy results after lexicon adaptation by the proposed approach in Table 3. LAICA-1 LAICA-2 A...

Ngày tải lên: 20/02/2014, 07:20

... CSAIL mcollins@csail.mit.edu Brian Roark OGI/OHSU roark@cslu.ogi.edu Murat Saraclar Bogazici University murat.saraclar@boun.edu.tr Abstract We describe a method for discriminative training of a ... statistical parser to produce string probabilities. In the work of Wen Wang and Mary Harper (Wang and Harper, 2002; Wang, 2003; Wang et al., 2004), a constraint depen- dency grammar and a fi...

Ngày tải lên: 20/02/2014, 15:20

... alignment A t . A g = arg min A ITG(e,f) |A ∪ A t − A ∩ A t | (3) Inference details appear in Section 4.3. Given A g and A m , we update the model param- eters away from A m and toward A g . θ ... states early when the results are falling off the agenda beams. Similar search and beaming strate- gies appear in many decoders for machine trans- lation (Huang and Chiang, 2007...

Ngày tải lên: 07/03/2014, 22:20

... sub-corpora, baseline, or mixture model. 4.4 Domain Adaptation Another popular task in SMT is domain adapta- tion (Foster et al., 2010). It tries to take advantage of any out-of-domain training data by ... translation performance significantly on a large-scale Arabic-to-English MT task. 1 Introduction Significant progress has been made in statisti- cal machine translation (SMT) in recent year...

Ngày tải lên: 17/03/2014, 00:20

... an interaction partner for ADAM10 that enhances a- sec- retase shedding of APP, probably by regulating matu- ration of the prodomain of ADAM10 [22]. The catalytical domain of ADAM10 contains a typical zinc-binding ... 102, 1595–1605. 106 Arduise C, Abache T, Li L, Billard M, Chabanon A, Ludwig A, Mauduit P, Boucheix C, Rubinstein E & Le NF (2008) Tetraspanins regulate ADAM10-medi- a...

Ngày tải lên: 16/02/2014, 09:20