Matches in ScholarlyData for { ?s ?p ?o. }
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent tatsuya-kawahara.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent hiroaki-nanjo.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent hiromitsu-nishizaki.
- item-6 next item-7.
- item-6 previous item-5.
- item-7 type ListItem.
- item-7 hasContent norihito-yasuda.
- item-7 next item-8.
- item-7 previous item-6.
- item-8 type ListItem.
- item-8 hasContent yoichi-yamashita.
- item-8 next item-9.
- item-8 previous item-7.
- item-9 type ListItem.
- item-9 hasContent katunobu-itou.
- item-9 previous item-8.
- 402 creator silvia-moraes.
- 402 creator susana-azeredo.
- 402 creator vera-lima.
- 402 type InProceedings.
- 402 label "Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese".
- 402 sameAs 402.
- 402 abstract "A frequent problem in automatic categorization applications involving Portuguese language is the absence of large corpora of previously classified documents, which permit the validation of experiments carried out. Generally, the available corpora are not classified or, when they are, they contain a very reduced number of documents. The general goal of this study is to contribute to the development of applications which aim at text categorization for Brazilian Portuguese. Specifically, we point out that keywords selection associated with neural networks can improve results in the categorization of Brazilian Portuguese texts. The corpus is composed of 30 thousand texts from the Folha de São Paulo newspaper, organized in 29 sections. In the process of categorization, the k-Nearest Neighbor (k-NN) algorithm and the Multilayer Perceptron neural networks trained with the backpropagation algorithm are used. It is also part of our study to test the identification of keywords parting from the log-likelihood statistical measure and to use them as features in the categorization process. The results clearly show that the precision is better when using neural networks than when using the k-NN.".
- 402 hasAuthorList authorList.
- 402 hasTopic Linguistics.
- 402 isPartOf proceedings.
- 402 keyword "Document Classification, Text categorisation".
- 402 keyword "Information Extraction, Information Retrieval".
- 402 keyword "Tools, systems, applications".
- 402 title "Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent susana-azeredo.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent silvia-moraes.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent vera-lima.
- item-3 previous item-2.
- 403 creator masaki-itagaki.
- 403 creator takako-aikawa.
- 403 type InProceedings.
- 403 label "Post-MT Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary".
- 403 sameAs 403.
- 403 abstract "A statistical machine translation (SMT) system requires homogeneous training data in order to get domain-sensitive (or context-sensitive) terminology translations. If the data contains various domains, it is difficult for an SMT to learn context-sensitive terminology mappings probabilistically. Yet, terminology translation accuracy is an important issue for MT users. This paper explores an approach to tackle this terminology translation problem for an SMT. We propose a way to identify terminology translations from MT output and automatically swap them with user-defined translations. Our approach is simple and can be applied to any type of MT system. We call our prototype Term Swapper . Term Swapper allows MT users to draw on their own dictionaries without affecting any parts of the MT output except for the terminology translation(s) in question. Using an SMT developed at Microsoft Research, called MSR-MT (Quirk et al., (2005); Menezes & Quirk (2005)), we conducted initial experiments to investigate the coverage rate of Term Swapper and its impact on the overall quality of MT output. The results from our experiments show high coverage and positive impact on the overall MT quality.".
- 403 hasAuthorList authorList.
- 403 hasTopic Linguistics.
- 403 isPartOf proceedings.
- 403 keyword "Lexicon, lexical database".
- 403 keyword "Machine Translation, SpeechToSpeech Translation".
- 403 title "Post-MT Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent masaki-itagaki.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent takako-aikawa.
- item-2 previous item-1.
- 404 creator junko-kubo.
- 404 creator keita-tsuji.
- 404 creator shigeo-sugimoto.
- 404 type InProceedings.
- 404 label "Temporal Aspects of Terminology for Automatic Term Recognition: Case Study on Women s Studies Terms".
- 404 sameAs 404.
- 404 abstract "The purpose of this paper is to clarify the temporal aspect of terminology focusing on the dictionary s impact on terms. We used women s studies terms as data and examined the changes of their values of five automatic term recognition (ATR) measures before and after dictionary publication. The changes of precision and recall of extraction based on these measures were also examined. The measures are TFIDF, C-value, MC-value, Nakagawa s FLR, and simple document frequencies. We found that being listed in dictionaries gives longevity to terms and prevent them from losing termhood that is represented by these ATR measures. The peripheral or relatively less important terms are more likely to be influenced by dictionaries and their termhood increase after being listed in dictionaries. Among the termhood, the potential of word formation that can be measured by Nakagawa s FLR seemed to be influenced most and the terms gradually gained it after being listed in dictionaries.".
- 404 hasAuthorList authorList.
- 404 hasTopic Linguistics.
- 404 isPartOf proceedings.
- 404 keyword "Controlled languages".
- 404 keyword "Lexicon, lexical database".
- 404 keyword "Standards for LRs".
- 404 title "Temporal Aspects of Terminology for Automatic Term Recognition: Case Study on Women s Studies Terms".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent junko-kubo.
- item-1 next item-2.