Báo cáo khoa học: "An Integrated Multi-document Summarization Approach based on Word Hierarchical Representation" pot

Báo cáo khoa học: "An Integrated Multi-document Summarization Approach based on Word Hierarchical Representation" pot

Báo cáo khoa học: "An Integrated Multi-document Summarization Approach based on Word Hierarchical Representation" pot

... 2009 Conference Short Papers, pages 113–116, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP An Integrated Multi-document Summarization Approach based on Word Hierarchical Representation ... Center”. 3 Summarization based on Word Hierarchical Representation 3.1 Word Significance Estimation In order to include the most significant concepts into the su...
Ngày tải lên : 31/03/2014, 00:20
  • 4
  • 235
  • 0
Tài liệu Báo cáo khoa học: "AN INTEGRATED HEURISTIC SCHEME FOR PARTIAL PARSE EVALUATION" docx

Tài liệu Báo cáo khoa học: "AN INTEGRATED HEURISTIC SCHEME FOR PARTIAL PARSE EVALUATION" docx

... handling com- mon word substitutions when the parser's input string is the output of a speech recognition system. When the input contains a pre-determined commonly substi- tuted word, the ... Evaluation Features So far, we have experimented with the following set of evaluation features: 1. The number and position of skipped words 2. The number of substituted words 3. The fra...
Ngày tải lên : 20/02/2014, 21:20
  • 3
  • 346
  • 0
Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

... constraint -based approach of formal description and computation of discourse structure. It considers both textual segments and discourse relations, and relies on expres- sion and satisfaction ... rely on a spe- cific operational model. These analysis models allow constraints to be expressed, on surface form as well as on annotations produced by the prece- dent analysers. All annota...
Ngày tải lên : 22/02/2014, 02:20
  • 4
  • 325
  • 0
Báo cáo khoa học: "An Integrated Architecture for Shallow and Deep Processing" doc

Báo cáo khoa học: "An Integrated Architecture for Shallow and Deep Processing" doc

... the deep components can back off to all readings. NE recognition is based on simple pattern matching techniques. Proper names (organizations, persons, locations), temporal expres- sions and quantities ... (Cunningham et al., 1997), the XML markup contains additive information, while the multi-level chart contains positional and abstraction -based in- formation, e.g., feature structures r...
Ngày tải lên : 08/03/2014, 07:20
  • 8
  • 414
  • 0
Báo cáo khoa học: "An Integrated Term-Based Corpus Query System" pptx

Báo cáo khoa học: "An Integrated Term-Based Corpus Query System" pptx

... recognition also incorporates the mapping of acronyms to their expanded forms. Our method for acronym acquisition is based on 246 both morphological and syntactic features of acronym definitions (see ... 2002) for details). We rely on syntactic patterns that are predominantly used to introduce acronyms in scientific papers in order to locate potential acronym definitions. Once a word...
Ngày tải lên : 08/03/2014, 21:20
  • 8
  • 337
  • 0
Báo cáo khoa học: "An Integrated Architecture for Generating Parenthetical Constructions" pptx

Báo cáo khoa học: "An Integrated Architecture for Generating Parenthetical Constructions" pptx

... CIRCUMSTANCE, PURPOSE, CONDITION, ANTITHESIS,or CONCES- SION relations. 26.6% of parentheticals in the cor- pus belong to this group. Because of the decision taken in the PDTB to only annotate clausal ... the CONCESSION relation. The trees in boxes i. and ii. correspond to regular uses of CONCESSION while the trees in iii. and iv. correspond to its parenthet- ical occurrences. Using these tre...
Ngày tải lên : 23/03/2014, 17:20
  • 6
  • 248
  • 0
Báo cáo khoa học: "An Integrated Platform for Computer-Aided Terminology" pdf

Báo cáo khoa học: "An Integrated Platform for Computer-Aided Terminology" pdf

... multi -word terms, while tools for automatic the- saurus construction yield clusters of single -word terms. On the one hand, term extractors focus on multi -word terms for ontological motivations: ... relation As in the preceding case, there is a non-synonymous semantic relation between the two terms. One of them denotes a concept richer than the other one because it carries an...
Ngày tải lên : 24/03/2014, 03:20
  • 8
  • 325
  • 0
Báo cáo khoa học: "An Interface for Rapid Natural Language Processing Development in UIMA" potx

Báo cáo khoa học: "An Interface for Rapid Natural Language Processing Development in UIMA" potx

... annotations or all annotations contained within the span of another annotation. getContainingAnnotations( Annotation a1 ) getNextClosest( Annotation a1 ) getPreviousClosest( Annotation a1 ... pattern. The Annotation Librarian pattern matching functionality allows the inclusion of an- notations, which provides an added level of power beyond regular expressions on text data only. 4 R...
Ngày tải lên : 17/03/2014, 00:20
  • 6
  • 407
  • 0
Báo cáo khoa học: "An Iterative Implicit Feedback Approach to Personalized Search" doc

Báo cáo khoa học: "An Iterative Implicit Feedback Approach to Personalized Search" doc

... performance. Efficiency of PAIR The iteration statistic in evaluation indicates that the average iteration times of our approach is 22 before convergence on condition that we set the threshold θ ... approach can implement result re-ranking and query expansion simultaneously and collaboratively. Based on this approach, we develop a client-side personalized web search agen...
Ngày tải lên : 17/03/2014, 04:20
  • 8
  • 243
  • 0
Báo cáo khoa học: "An Interactive Domain Independent Approach to Robust Dialogue Interpretation" pot

Báo cáo khoa học: "An Interactive Domain Independent Approach to Robust Dialogue Interpretation" pot

... interaction. With three questions, the system achieves a 37% reduction in error rate over partial parsing alone. 4.2 Discourse Based Interaction In a final evaluation, the quality of questions based ... augments temporal expressions from context. Based on this information, it computes the constraints on the speaker's schedule expressed by each sentence. Each constraint...
Ngày tải lên : 23/03/2014, 19:20
  • 7
  • 188
  • 0

Xem thêm