Tài liệu Báo cáo khoa học: "Improving Chinese Semantic Role Labeling with Rich Syntactic Features" ppt

... 11-16 July 2010. c 2010 Association for Computational Linguistics Improving Chinese Semantic Role Labeling with Rich Syntactic Features Weiwei Sun ∗ Department of Computational Linguistics, Saarland ... phenomena. 2 Chinese SRL The Chinese PropBank (CPB) is a semantic anno- tation for the syntactic trees of the Chinese Tree- Bank (CTB). The arguments of a predicate ar...

Ngày tải lên: 20/02/2014, 04:20

... b-CD shows good substrate binding compared with Ebselen [15]. When the sub- strates were H 2 O 2 , t-BuOOH and CumOOH, we found that the GPX activities with 6-CySeCD for the reduc- tion of H 2 O 2 , ... were higher than with 6-SeCD. In the investigation of GPX mimics, Wilson’s disele- nides are successful [11]. As shown in Scheme 4, there are two processes (oxidation and reduction with...

Ngày tải lên: 19/02/2014, 02:20

... rows report the cross-pair similarity carried out with Eq. 6 with (Synt Trees with placeholders) and without (Only Synt Trees) augmenting the trees with placehold- ers, respectively. Each column ... based on text and hypothesis syntactic trees and we use such similarity with traditional intra-pair similarities to define a novel semantic kernel function. We experimented with suc...

Ngày tải lên: 20/02/2014, 12:20

... process, and (ii) to explore the role of the syntactic frame descrip- tions in verb classification, to demonstrate the im- plicit induction of lexical meaning components from syntactic properties, and ... human judgement (Schulte im Walde, 2002a). 3 German Semantic Verb Classes Semantic verb classes have been defined for sev- eral languages, with dominant examples concern- ing Engli...

Ngày tải lên: 20/02/2014, 21:20

... were also correlated with fluency, but the association was lower than for the direct count without normalization. Parse tree depth is the final feature correlated with fluency with correlation above ... but no actual syntactic prop- erties of the sentences. But certainly, problems with sentence fluency are expected to be mani- fested in syntax. We would expect for example that syntacti...

Ngày tải lên: 22/02/2014, 02:20

... Prototypes Eric H. Huang, Richard Socher ∗ , Christopher D. Manning, Andrew Y. Ng Computer Science Department, Stanford University, Stanford, CA 94305, USA {ehhuang,manning,ang}@stanford.edu, ∗ richard@socher.org Abstract Unsupervised ... neural language models. 1 1 Introduction Vector-space models (VSM) represent word mean- ings with vectors that capture semantic and syntac- tic informat...

Ngày tải lên: 19/02/2014, 19:20

... train a Chinese- to-English SMT system, we need to perform both Chinese- to-English and English-to -Chinese word alignment. We only evaluate the English-to -Chinese word alignment here. GIZA++ with ... probabili- ties of words in the same cept. The team leader plays a key role in the project undertaking. The team leader plays a key role in the project undertaking. 826 3.1 I...

Ngày tải lên: 20/02/2014, 04:20

... word (e.g., with respect to case and tense). Syntactic Features: Part-of-speech tags of the three words preceding the medical term and the three words following it. 312 Lexico -Syntactic Features: ... instances with that label as positive instances and instances with any other label as negative instanc- es. The final class label is assigned by choosing the class that was assig...

Ngày tải lên: 20/02/2014, 05:20

... you ⇓ Output all rules for replacing the incorrect ASR sequence with the correct text, using the entire sequence (a) or splices (b), with or without surrounding anchors: (a) the okay one and / ok why ... how the transcripts improve, words with lower information content (e.g., a lower tf.idf score) are corrected more often and with more improvement than words with higher information...

Ngày tải lên: 20/02/2014, 07:20

... On the other hand, the system with preceding infor- mation is not significantly better than the system without it 5 . Other non-local information may im- prove performance with our framework and this ... of the classifier on development data is 74.64 (without preceding information) and 75.14 (with preceding information). 470 Table 5: Performance with filtering on the development data. (&l...

Ngày tải lên: 20/02/2014, 12:20