Matches in ScholarlyData for { ?s ?p ?o. }
- item-4 hasContent yajun-wang.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent zheng-chen.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent botao-hu.
- item-6 previous item-5.
- language-independent-identification-of-parallel-se creator rohit-g-bharadwaj.
- language-independent-identification-of-parallel-se creator vasudeva-varma.
- language-independent-identification-of-parallel-se type InProceedings.
- language-independent-identification-of-parallel-se label "Language Independent Identification of Parallel Sentences Using Wikipedia".
- language-independent-identification-of-parallel-se sameAs language-independent-identification-of-parallel-se.
- language-independent-identification-of-parallel-se abstract "This paper details a novel classification based approach to identify parallel sentences between two languages in a language independent way. We substitute the required language specific resources by the richly structured multilingual content, Wikipedia. Our approach is particularly useful to extract parallel sentences for under-resourced languages like most Indian and African languages, where resources are not readily available with necessary accuracies. We extract various statistics based on the cross lingual links present in Wikipedia and use them to generate feature vectors for each sentence pair. Binary classification of each pair of sentences into parallel or non-parallel has been done using these feature vectors. We achieved a precision upto 78% which is encouraging when compared to other state-of-art approaches.These results support our hypothesis of using Wikipedia to evaluate the parallel coefficient between sentences that can be used to build bilingual dictionaries.".
- language-independent-identification-of-parallel-se hasAuthorList authorList.
- language-independent-identification-of-parallel-se hasTopic World_Wide_Web.
- language-independent-identification-of-parallel-se isPartOf proceedings.
- language-independent-identification-of-parallel-se title "Language Independent Identification of Parallel Sentences Using Wikipedia".
- 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 rohit-g-bharadwaj.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent vasudeva-varma.
- item-2 previous item-1.
- learning-facial-attributes-by-crowdsourcing-in-soc creator hong-yuan-mark-liao.
- learning-facial-attributes-by-crowdsourcing-in-soc creator winston-h-hsu.
- learning-facial-attributes-by-crowdsourcing-in-soc creator yan-ying-chen.
- learning-facial-attributes-by-crowdsourcing-in-soc type InProceedings.
- learning-facial-attributes-by-crowdsourcing-in-soc label "Learning Facial Attributes by Crowdsourcing in Social Media".
- learning-facial-attributes-by-crowdsourcing-in-soc sameAs learning-facial-attributes-by-crowdsourcing-in-soc.
- learning-facial-attributes-by-crowdsourcing-in-soc abstract "Facial attributes such as gender, race, age, hair style, etc., carry rich information for locating designated persons and pro ling the communities from image/video collections (e.g., surveillance videos or photo albums). For plentiful facial attributes in photos and videos, collecting costly manual annotations for training detectors is time-consuming. We propose an automatic facial attribute detection method by exploiting the great amount of weakly labelled photos in social media. Our work can (1) automatically extract training images from the semantic-consistent user groups and (2) filter out noisy training photos by multiple mid-level features (by voting). Moreover, we introduce a method to harvest less-biased negative data for preventing uneven distribution of certain attributes. The experiments show that our approach can automatically acquire training photos for facial attributes and is on par with that by manual annotations.".
- learning-facial-attributes-by-crowdsourcing-in-soc hasAuthorList authorList.
- learning-facial-attributes-by-crowdsourcing-in-soc hasTopic World_Wide_Web.
- learning-facial-attributes-by-crowdsourcing-in-soc isPartOf proceedings.
- learning-facial-attributes-by-crowdsourcing-in-soc title "Learning Facial Attributes by Crowdsourcing in Social Media".
- 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 yan-ying-chen.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent winston-h-hsu.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent hong-yuan-mark-liao.
- item-3 previous item-2.
- learning-to-tokenize-web-domains creator sourangshu-bhattachaya.
- learning-to-tokenize-web-domains creator sriram-srinivasan.
- learning-to-tokenize-web-domains type InProceedings.
- learning-to-tokenize-web-domains label "Learning to Tokenize Web Domains".
- learning-to-tokenize-web-domains sameAs learning-to-tokenize-web-domains.
- learning-to-tokenize-web-domains abstract "Domain Match is an Internet monetization product offered by web companies like Yahoo! The product offers display of ads and search results, when a user requests a webpage from a domain which is non-existent or does not have any content. This product earns significant amount of advertising revenue for major internet companies like Yahoo! Hence it is an important product receiving millions of queries per day. Domain Match (DM) works by tokenizing the input domains and sub-folders into keywords and then displaying ads and search results queried on the keywords. In this poster, we describe a machine learning based solution, which automatically learns to tokenize new domains, given a training dataset containing a set of domains and their tokenizations. We use positional frequency and parts of speech as features for scoring tokens. Tokens are scored combined using various scoring models. We compare two ways of training the models: a simple gain function based training and a large margin training. Experimental results are encouraging.".
- learning-to-tokenize-web-domains hasAuthorList authorList.
- learning-to-tokenize-web-domains hasTopic World_Wide_Web.
- learning-to-tokenize-web-domains isPartOf proceedings.
- learning-to-tokenize-web-domains title "Learning to Tokenize Web Domains".
- 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 sriram-srinivasan.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent sourangshu-bhattachaya.
- item-2 previous item-1.
- leveraging-auxiliary-text-terms-for-automatic-imag creator jianping-fan.
- leveraging-auxiliary-text-terms-for-automatic-imag creator jinye-peng.
- leveraging-auxiliary-text-terms-for-automatic-imag creator ning-zhou.
- leveraging-auxiliary-text-terms-for-automatic-imag creator xiaoyi-feng.
- leveraging-auxiliary-text-terms-for-automatic-imag creator yi-shen.
- leveraging-auxiliary-text-terms-for-automatic-imag type InProceedings.
- leveraging-auxiliary-text-terms-for-automatic-imag label "Leveraging Auxiliary Text Terms for Automatic Image Annotation".
- leveraging-auxiliary-text-terms-for-automatic-imag sameAs leveraging-auxiliary-text-terms-for-automatic-imag.
- leveraging-auxiliary-text-terms-for-automatic-imag abstract "This paper proposes a novel algorithm to annotate web images by automatically aligning the images with their most relevant auxiliary text terms. First, the DOM-based web page segmentation is performed to extract images and their most relevant auxiliary text blocks. Second, automatic image clustering is used to partition the web images into a set of groups according to their visual similarity contexts, which significantly reduces the uncertainty on the relatedness between the images and their auxiliary terms. The semantics of the visually-similar images in the same cluster are then described by the same ranked list of terms which frequently co-occur in their text blocks. Finally, a relevance re-ranking process is performed over a term correlation network to further refine the ranked term list. Our experiments on a large-scale database of web pages have provided very positive results.".
- leveraging-auxiliary-text-terms-for-automatic-imag hasAuthorList authorList.
- leveraging-auxiliary-text-terms-for-automatic-imag hasTopic World_Wide_Web.
- leveraging-auxiliary-text-terms-for-automatic-imag isPartOf proceedings.
- leveraging-auxiliary-text-terms-for-automatic-imag title "Leveraging Auxiliary Text Terms for Automatic Image Annotation".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.