Tài liệu Báo cáo khoa học: "Text-to-text Semantic Similarity for Automatic Short Answer Grading" pdf

Tài liệu Báo cáo khoa học: "Extracting Semantic Orientations of Words using Spin Model" pdf

Tài liệu Báo cáo khoa học: "Extracting Semantic Orientations of Words using Spin Model" pdf

... examples that the shortest-path method can assign a non-zero orien- tation value. Since the shortest-path method is de- signed for 2 seed words, the method is extended to use the average shortest-path ... adjectives for comparison of methods. The result in Table 4 also shows that the global optimiza- tion of the spin model works well for the semantic orientation extraction. We also te...
Ngày tải lên : 20/02/2014, 15:20
  • 8
  • 435
  • 0
Tài liệu Báo cáo khoa học: "Text-to-text Semantic Similarity for Automatic Short Answer Grading" pdf

Tài liệu Báo cáo khoa học: "Text-to-text Semantic Similarity for Automatic Short Answer Grading" pdf

... can be more easily com- pared. 3 4 Automatic Short Answer Grading Our experiments are centered around the use of measures of similarity for automatic short answer grading. In particular, we carry ... performance of the system by integrating automatic feedback from the student answers. Overall, our system significantly and consistently out- performs other unsupervised methods...
Ngày tải lên : 22/02/2014, 02:20
  • 9
  • 577
  • 0
Tài liệu Báo cáo khoa học: "Bilingual Sense Similarity for Statistical Machine Translation" ppt

Tài liệu Báo cáo khoa học: "Bilingual Sense Similarity for Statistical Machine Translation" ppt

... evaluate the similarity for two vec- tors in the same language, so using cosine dis- tance to compute the similarity is straightfor- ward. And we can set a relatively large size for the vector, ... improved similarity function Alg2 makes it possible to incorporate monolingual semantic similarity on top of the bilingual se- mantic similarity, thus it may improve the accu- racy...
Ngày tải lên : 20/02/2014, 04:20
  • 10
  • 594
  • 0
Tài liệu Báo cáo khoa học: "Mining Wiki Resources for Multilingual Named Entity Recognition" pdf

Tài liệu Báo cáo khoa học: "Mining Wiki Resources for Multilingual Named Entity Recognition" pdf

... language is available for download (download.wikimedia.org) in a text format suitable for inclusion in a database. For the remainder of this paper, we refer to this format. 1 Within Wikipedia, ... language article, if available, for additional information. • A second pass checks for multi-word phrases that exist as titles of Wikipedia articles. • We look for certain typ...
Ngày tải lên : 20/02/2014, 09:20
  • 9
  • 429
  • 1
Tài liệu Báo cáo khoa học: "Using Structural Information for Identifying Similar Chinese Characters" pdf

Tài liệu Báo cáo khoa học: "Using Structural Information for Identifying Similar Chinese Characters" pdf

... Proceedings of ACL-08: HLT, Short Papers (Companion Volume), pages 93–96, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Using Structural Information for Identifying Similar ... pronunciations or in their internal structures are useful for computer-assisted language learning and for psycholinguistic studies. Al- though it is possible for us to...
Ngày tải lên : 20/02/2014, 09:20
  • 4
  • 415
  • 0
Tài liệu Báo cáo khoa học: "Kinds of Features for Chinese Opinionated Information Retrieval" pdf

Tài liệu Báo cáo khoa học: "Kinds of Features for Chinese Opinionated Information Retrieval" pdf

... set of features for text classification (index- ing) for an OIR query of the first level (finds opin- ionated information) and for an OIR query of the second level (finds opinionated information with sentiment ... politics. We therefore believe that a system capable of pro- viding access to opinionated information in other languages (especially in Chinese) might be of great use for indivi...
Ngày tải lên : 20/02/2014, 12:20
  • 6
  • 434
  • 0
Tài liệu Báo cáo khoa học: "A Unified Framework for Automatic Evaluation using N-gram Co-Occurrence Statistics" pptx

Tài liệu Báo cáo khoa học: "A Unified Framework for Automatic Evaluation using N-gram Co-Occurrence Statistics" pptx

... for such metrics to be used for automatic evaluation by the Automatic Summarization community. 4.3 Question Answering Evaluation One of the most common approaches to automatic question answering ... reference answer and its corresponding candidate answer. Because the denominator in the R(n) formula consists of a sum over the reference answers, this formula is essentially a...
Ngày tải lên : 20/02/2014, 16:20
  • 8
  • 462
  • 0
Tài liệu Báo cáo khoa học: "Incorporating Context Information for the Extraction of Terms" pdf

Tài liệu Báo cáo khoa học: "Incorporating Context Information for the Extraction of Terms" pdf

... 1996), incorporating information gained from the textual context of the candidate term. 2 Context information for terms The idea of incorporating context information for term extraction came ... context carries information about terms it should be involved in the procedure for their ex- traction. We incorporate context information in the form of weights constructed in a fully...
Ngày tải lên : 22/02/2014, 03:20
  • 3
  • 369
  • 0
Tài liệu Báo cáo khoa học: "Detecting Semantic Equivalence and Information Disparity in Cross-lingual Documents" doc

Tài liệu Báo cáo khoa học: "Detecting Semantic Equivalence and Information Disparity in Cross-lingual Documents" doc

... Association for Computational Linguistics, pages 120–124, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Detecting Semantic Equivalence and Information ... clas- sified if both pairs originated from it are correctly judged (“YES-YES” for bidirectional, “YES-NO” for forward, and “NO-YES” for backward entail- ment). Two-way classification re...
Ngày tải lên : 19/02/2014, 19:20
  • 5
  • 528
  • 0
Tài liệu Báo cáo khoa học: "Unsupervised Semantic Role Induction with Global Role Ordering" doc

Tài liệu Báo cáo khoa học: "Unsupervised Semantic Role Induction with Global Role Ordering" doc

... syntactic and semantic features could provide clues to the semantic role label of a constituent, non- local features such as predicate voice could provide information about the expected semantic role ... Dirichlet(α order ) for all interval I do draw θ SR p,I ∼ Dirichlet(α SR ) for all adjacency adj ∈ {0, 1} do draw θ ST OP p,I,adj ∼ Beta(α ST OP ) for all role r ∈ P R ∪ SR do fo...
Ngày tải lên : 19/02/2014, 19:20
  • 5
  • 398
  • 0

Xem thêm