Báo cáo khoa học: "Homophones and Tonal Patterns in English-Chinese Transliteration" doc

... between Mandarin Chinese and Cantonese, and report work in progress for dealing with homophones and tonal patterns despite potential skewed distributions of indi-vidual Chinese characters in the ... Virga and Khudanpur, 2003). Direct orthographic mapping (e.g. Li et al., 2004), mak-ing use of individual Chinese graphemes, tends 1 Mandarin names are transcribed in Hanyu Pinyin and Cantonese ... especially when the training data is limited. In this paper we report some work in progress and compare E2C in Cantonese and Mandarin Chinese. Related work will be briefly reviewed in Sec-tion 2....

Báo cáo khoa học: " LOCAL AND GLOBAL STRUCTURES IN DISCOURSE UNDERSTANDING" docx

... reflect intuitive attention, interest and judgment processes of the understander that occur during reading a text, on the other. They should be usable in interpreting very different kinds of ... in his working memory and to take them all into account in making the resulting decision. Again, the face-to-face dialogue is a good example: in order to react adequately to a response in ... "making sense" does not necessarily amount to incorporating the corresponding event or situation into some goal-plan hierarchy. Instead, making sense may mean for the understander, for instance,...

Tài liệu Báo cáo khoa học: "Structural and Topical Dimensions in Multi-Task Patent Translation" ppt

... of tokens and average typefrequencies in text sections.We reserved patent data published between1979 and 2007 for training and documents pub-lished in 2008 for tuning and testing in SMT.For ... error rate training In contrast to task pooling and task mixtures, thespeciﬁc setting addressed by multi-task minimumerror rate training is one in which the generativetrain test pooling mixtureA-C ... pooling data fromseparate tasks into a single training set. Instead ofa trivial enlargement of training data by pooling,we train the pooled models on the same amountof sentences as the individual...

Báo cáo khoa học: "SVD and Clustering for Unsupervised POS Tagging" docx

... type i. We next include a normalization step in which each row in each of L* and R* is scaled to unit length, yielding matrices L** and R**. Finally, we form a single descriptor matrix ... r2 = 300, and we again normalize the descriptors to unit length, yielding a new pair of latent descriptor matrices L** and R**. Finally, we concatenate L** and R** into a single matrix ... high numbers of induced tags, resulting in fine-grained labelings. The value of this flexibility is discussed in the next section. Figure 1 shows, as a function of k2, the tagging accuracy...

Báo cáo khoa học: "Methods and Practical Issues in Evaluating Alignment Techniques" doc

... not taken into account in the final grading of the systems. The overall ranking for all systems (excluding the TECH corpus results) is given in Figure 2, in terms of the Sent and Char F-measures. ... macro-structure of the document. It examines the tree structure of an SGML document in a first pass, weighting each node according to the number of characters contained within the subtree rooted ... and Kenneth W. Church. 1991. A Program for Aligning Sentences in Bilin- gual Corpora. In 29th Annual Meeting of the Association -for Computational Linguis- tics, Berkeley, CA. N. Ide and...

Báo cáo khoa học: "DENORMALIZATION AND CROSS REFERENCING IN THEORETICAL LEXICOGRAPHY" ppt

... designed for perspicuous handling of linguistic data. Data management was done record by record to maintain integrity, but the normal form constraints on at- omicity and singularity of fields were ... contains fields for various aspects of the form, meaning, meaning-to-form mapping, and use of that sense. For the update and retrieval operations defined on relations to work right, the information ... formal constraints are conceptual constraints based on the fact that the information in some fields determines what can be in other fields; Ullman spells out the main kinds of such dependency....

Báo cáo khoa học: Neuroglobin and cytoglobin expression in mice Evidence for a correlation with reactive oxygen species scavenging doc

... neuroglobin and cytoglobin in a situation of chronic hypoxia in mice were examined using real-time quantitative PCR. The kinetics of thehypoxic expression of neuroglobin (brain, eyes) and cytoglobin ... neuronal (brain and retina) and some endocrine tissues, whereas Cygb isdetected in the nucleus and in the cytoplasm of manytypes of tissue [2,3]. In response to hypoxia, Ngb is up-regulated in vitro ... concentration of Ngb in the mouse retina is > 100 lm, and is thus within therange of Mb in the muscle, indicating the importantrole of Ngb in retinal function [18]. However, in con-trast to...

Báo cáo khoa học: "Compounding and derivational morphology in a ﬁnite-state setting" pptx

... the same remainder to the right of the dotwere collapsed ( and ).Since they are indistinguishable in terms of futurebehavior, making a distinction results in an unnec-essary increase of the ... to deal withthe bracketing structure of compounding, whichwould be impossible to cover in full generality in the ﬁnite-state setting. In languages like German, spelling conventionsfor compounds ... verbal stemrealize (and non- could combine with a more complex form).However, since in English there is much less token-level inter-action between derivation and compounding, a ﬁnite-state ap-proximation...

Báo cáo khoa học: "Tractability and Structural Closures in Attribute Logic Type Signatures" pptx

... supertype branching fac-tors in this family increase linearly with size, thepartial orders can growin depthinstead in order tocontain this.That yields something roughly of the formshown in Figure ... Figure 3, which is an exampleof arecenttrend in using type-intensiveencodings of linguis-tic information into typed feature logic in HPSG,beginning with Sag (1997). These explicitly iso-late ... suspendingsubtype covering constraints is that other princi-ples of grammar and proof procedures such asSLD resolution, parsing or generation can add de-terministic information that may result in...

Báo cáo khoa học: "SEARCH AND INFERENCE STRATEGIES IN PRONOUN RESOLUTION" pot

... understanding dialogs. In Proceedin~ of =he Fifth International Joint Con- ference on Artificial Intelligence. Cambridge: MIT. Hobbs, J.R. (1978). Resolving pronoun references. Lingua, 44, ... order in which candldaces are evaluated, but has no machinery for carrying out the evaluation. The inference strategy helps to set up the represen- taclon of the information in the cexC agains ... however, deciding on the referent. A serial search strategy has no machinery for evaluating candidates, i~ can only direct ~he order in which candidates are examined. The process of selecting a plausible...

Xem thêm