Báo cáo khoa học: "Robust PCFG-Based Generation using Automatically Acquired LFG Approximations" doc

Báo cáo khoa học: "Robust PCFG-Based Generation using Automatically Acquired LFG Approximations" doc

Báo cáo khoa học: "Robust PCFG-Based Generation using Automatically Acquired LFG Approximations" doc

... 1033–1040, Sydney, July 2006. c 2006 Association for Computational Linguistics Robust PCFG-Based Generation using Automatically Acquired LFG Approximations Aoife Cahill 1 and Josef van Genabith 1,2 1 National ... discriminative disambiguation model using a hand-crafted HPSG grammar for generation. Belz (2005) describes a method for building statistical generation mod- els u...

Ngày tải lên: 23/03/2014, 18:20

8 239 0
Báo cáo khoa học: "Robust VPE detection using Automatically Parsed Text" pdf

Báo cáo khoa học: "Robust VPE detection using Automatically Parsed Text" pdf

... Effects of using the empty categories 5 Experiments with Automatically Parsed data The next set of experiments use the BNC and Treebank, but strip POS and parse information, and parse them automatically ... summarise the findings : • Using the BNC, which is tagged with a com- plex tagging scheme but has no parse data, it is possible to get 76% F1 using lexical forms and POS data alon...

Ngày tải lên: 17/03/2014, 06:20

6 305 0
Tài liệu Báo cáo khoa học: "Automatic Headline Generation using Character Cross-Correlation" doc

Tài liệu Báo cáo khoa học: "Automatic Headline Generation using Character Cross-Correlation" doc

... words in the original headline must be found in the document body. • 260 documents were randomly selected from the 3170 documents. After automatically generating the headlines, 3 native Arabic ... model for headline generation in which they divide head- line generation process into two steps; namely the step of distilling the information source from the observation of a document...

Ngày tải lên: 20/02/2014, 05:20

5 614 0
Báo cáo khoa học: "Sentence Diagram Generation Using Dependency Parsing Elijah Mayfield Division of Science and Mathematics " docx

Báo cáo khoa học: "Sentence Diagram Generation Using Dependency Parsing Elijah Mayfield Division of Science and Mathematics " docx

... Workshop, pages 45–53, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Sentence Diagram Generation Using Dependency Parsing Elijah Mayfield Division of Science and Mathematics University of ... scholars.” and “The students studied their assignment.” By developing an algorithm to automatically analyze a sentence using structural grammar, we hope that the advantages of structural...

Ngày tải lên: 08/03/2014, 01:20

9 523 0
Báo cáo khoa học: "Stochastic Language Generation Using WIDL-expressions and its Application in Machine Translation and Summarization" pot

Báo cáo khoa học: "Stochastic Language Generation Using WIDL-expressions and its Application in Machine Translation and Summarization" pot

... WIDL-expressions for Headline Generation. We generate WIDL- expressions starting from an input document. First, we extract a weighted list of topic keywords from the input document using the algorithm ... system. Headline Generation Evaluation. To evaluate the accuracy of our headline generation system, we use the documents from the DUC 2003 eval- uation competition. Half of these docu...

Ngày tải lên: 23/03/2014, 18:20

8 378 0
Báo cáo khoa học: "Flexible Guidance Generation using User Model in Spoken Dialogue Systems" pdf

Báo cáo khoa học: "Flexible Guidance Generation using User Model in Spoken Dialogue Systems" pdf

... the dia- logue manager, and are utilized in the dialogue management and response generation. 3 Response Generation using User Models 3.1 Classification of User Models We define three dimensions as ... user, and accordingly change the system’s responses. 3.2 Response Generation Strategy using User Models Next, we describe the response generation strategies adapted to individual users...

Ngày tải lên: 31/03/2014, 03:20

8 317 0
Tài liệu Báo cáo khoa học: "Robust Extraction of Named Entity Including Unfamiliar Word" doc

Tài liệu Báo cáo khoa học: "Robust Extraction of Named Entity Including Unfamiliar Word" doc

... entities including unfamiliar words which do not occur or occur few times in a training corpus using a large unannotated cor- pus. The proposed method consists of two steps. The first step is ... large unannotated corpus. The second step is to employ traditional machine learning approaches using both features of original morphemes and fea- tures of similar morphemes. The experiments of ext...

Ngày tải lên: 20/02/2014, 09:20

4 384 1
Báo cáo khoa học: Protein database searches using compositionally adjusted substitution matrices docx

Báo cáo khoa học: Protein database searches using compositionally adjusted substitution matrices docx

... amino acid biases. Accordingly, we have proposed a rationale for automatically transforming any standard matrix, constructed using Eqn (1) with a unique valid q, into a matrix valid in a nonstandard context, ... MINIREVIEW Protein database searches using compositionally adjusted substitution matrices Stephen F. Altschul, John C. Wootton, E. Michael ... alignments computed by all four mo...

Ngày tải lên: 07/03/2014, 21:20

9 349 0
Báo cáo khoa học: "Detecting Erroneous Sentences using Automatically Mined Sequential Patterns" pdf

Báo cáo khoa học: "Detecting Erroneous Sentences using Automatically Mined Sequential Patterns" pdf

... Republic, June 2007. c 2007 Association for Computational Linguistics Detecting Erroneous Sentences using Automatically Mined Sequential Patterns Guihua Sun ∗ Xiaohua Liu Gao Cong Ming Zhou Chongqing ... build a machine learning model to automatically classify each sentence into one of the two classes, “erro- neous” and “correct.” To build the learning model, we automatically extract...

Ngày tải lên: 08/03/2014, 02:21

8 487 0
Báo cáo khoa học: "Improve SMT Quality with Automatically Extracted Paraphrase Rules" docx

Báo cáo khoa học: "Improve SMT Quality with Automatically Extracted Paraphrase Rules" docx

... The alignment was obtained using GIZA++ (Och and Ney, 2003) and then we symmetrized the word alignment using the grow- diag-final heuristic. Parameters were tuned using Minimum Error Rate Training ... translations for unknown terms using phrasal paraphrases. Callison-Burch et al. (2006) and Marton et al. (2009) paraphrase unknown terms in the input sentences using phrasal par...

Ngày tải lên: 07/03/2014, 18:20

9 298 0
Từ khóa:
w