Báo cáo khoa học: "Improving Data Driven Wordclass Tagging by System Combination" pptx
... Improving Data Driven Wordclass Tagging by System Combination Hans van Halteren Dept. of Language and Speech University ... modelling between different data driven systems performing the same NLP task can be exploited to yield a higher accuracy than the best indi- vidual system. We do this by means of an ex- periment ... which the model is constructed (hand crafted...
Ngày tải lên: 17/03/2014, 07:20
... grammar -driven and a data- driven parser. We show how the con- version of LFG output to dependency representation allows for a technique of parser stacking, whereby the output of the grammar -driven ... data- driven dependency parser with features from a different parser to guide parsing. The additional parser em- ployed in this work, is not however, a data- driven parser trained...
Ngày tải lên: 17/03/2014, 02:20
... ASR systems on lecture transcription. This is in part caused by the mis- match between the language used in a lecture and the predictive language models employed by most ASR systems. Most ASR systems ... comple- mentary ASR systems, a technique first proposed in the context of NIST’s ROVER system (Fiscus, 1997) with a 12% relative error reduction (RER), and subsequently widely employed i...
Ngày tải lên: 20/02/2014, 07:20
Tài liệu Báo cáo khoa học: "Improving Word Representations via Global Context and Multiple Word Prototypes" pdf
... se- mantics of words by incorporating both local and global document context, and 2) accounts for homonymy and polysemy by learning mul- tiple embeddings per word. We introduce a new dataset with human ... on pairs 873
Ngày tải lên: 19/02/2014, 19:20
Tài liệu Báo cáo khoa học: "Improving Statistical Machine Translation with Monolingual Collocation" pdf
... Figure 3 shows an example: T1 is generated by the system where the phrase collocation prob- abilities are used and T2 is generated by the baseline system. In this example, since the collo- cation ... bi-directional alignments are obtained 830 Figure 3. Example of the translations generated by the baseline system and the system where the phrase collocation probabilities are...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Improving Chinese Semantic Role Labeling with Rich Syntactic Features" ppt
... methods have been intro- duced by (Sun et al., 2009; Sun, 2010; Ding and Chang, 2009). 2.1 Our System We implement a three-stage (i.e. pruning, AI and SRC) SRL system. In the pruning step, our ... facilitate comparison with previous work, we use CPB 1.0 and CTB 5.0, the same data set- ting with (Xue, 2008). The data is divided into three parts: files from 081 to 899 are used as traini...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: Improving Classification of Medical Assertions in Clinical Notes" pdf
... adding the new feature set, we evaluated our improved system on the test data and compared its performance with our original system. 4.1 Data The training set includes 349 clinical notes, with ... Fourth i2b2/VA Challenge, the asser- tion classification task was tackled by participating researchers. The best performing system (Berry de Bruijn et al., 2011) reached a micro-ave...
Ngày tải lên: 20/02/2014, 05:20
Tài liệu Báo cáo khoa học: "A Syntax-Driven Bracketing Model for Phrase-Based Translation" pptx
... the SDB model on phrase translation by studying the effects of syntax -driven features and differences of 1-best translation out- puts. 5.1 Effects of Syntax -Driven Features We conducted further ... the MT experiments on Chinese- to-English translation, using (Xiong et al., 2006)’s system as our baseline system. We modified the baseline decoder to incorporate our SDB mod- els as descri...
Ngày tải lên: 20/02/2014, 07:20
Tài liệu Báo cáo khoa học: "Improving the Scalability of Semi-Markov Conditional Random Fields for Named Entity Recognition" pdf
... The framework of our system. We first enumerate all possible candidate states, and then filter out low probability states by using a light-weight classifier, and represent them by using feature forest. Table ... used as the training data and the latter as the development data. For semi-CRFs, we used amis 3 for training the semi- CRF with feature-forest. We used GENIA taggar 4 for POS -ta...
Ngày tải lên: 20/02/2014, 12:20
Tài liệu Báo cáo khoa học: "Improving Pronoun Resolution Using Statistics-Based Semantic Compatibility Information" doc
... could such a system significantly improve the baseline without the semantic feature, it also out- performs the system with the combination of the cor- pus and the single-candidate model (by 11.5% ... resolution tasks. 4.3 System Evaluation Table 2 summarizes the performance of the systems with different combinations of statistics sources and learning frameworks. The systems without the...
Ngày tải lên: 20/02/2014, 15:20