Automatic Annotation of Content-Rich HTML Documents: Structural and Semantic Analysis

Mukherjee, Saikat; Yang, Guang; Ramakrishnan, I. V.

doi:10.1007/978-3-540-39718-2_34

Cited by 47 publications

(29 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the observation that semantically related content elements in a web page exhibit spatial locality [64,65] and often share the same alignment (matching X or Y coordinate) on a web page. Since a frame tree represents the layout of a web page, we infer that geometrical alignment of frames may imply semantic relationship between their respective content.…”

Section: Geometric Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Transaction models for Web accessibility

Mahmud

Ramakrishnan

2011

World Wide Web

Self Cite

View full text Add to dashboard Cite

S S S t t t o o o n n n y y y B B B r r r o o o o o o k k k U U U n n n i i i v v v e e e r r r s s s i i i t t t y y yThe official electronic file of this thesis or dissertation is maintained by the University Libraries on behalf of The Graduate School at Stony Brook University. The Web has evolved into a dominant digital medium for conducting many types of online transactions such as shopping, paying bills, making travel plans, etc. Such transactions typically involve a number of steps spanning several web pages. For sighted users these steps are relatively straightforward to do with graphical web browsers. But they pose tremendous challenges for visually impaired individuals. This is because screen readers, the dominant assistive technology used by visually impaired users, function by speaking out the screen's content serially. Consequently, using them for conducting transactions can cause considerable information overload. But usually one needs to browse only a small fragment of a web page to do a step of a transaction (e.g., choosing an item from a search results list). Based on this observation this dissertation develops a model-directed transaction framework to identify, extract and aurally render only the "relevant" page fragments in each step of a transaction. The framework uses a process model to encode the state of the transaction and a concept model to identify the page fragments relevant for the transaction in that state. The two models are constructed from labeled transaction sequences using traditional classification and automata learning methods. © © © A A A l l l l l l R R R i i i g g g h h h t t t s s s RNext, we relax the requirement of needing fully labeled training data. Specifically, we present a framework to mine transaction models from partially labeled click stream data generated by transactions, where some or all the labels could be missing. Not having to rely exclusively on (manually) labeled click stream data has iii important benefits: Visually impaired users do not have to depend on third party (e.g., sighted users) for constructing transaction models. This makes it possible to mine personalized models from transaction click streams associated with sites that visually impaired users visit regularly. Since partially labeled data is relatively easier to generate, scaling up the construction of domain-specific transaction models (e.g., shopping, airline reservations, bill payments, etc.) is feasible. Lastly, adjusting the performance of deployed models over time with new training data is also doable.In terms on techniques used for mining we expand our repertoire to include web content analysis to partition a web page into segments consisting of semantically related content elements, contextual analysis of data surrounding clickable elements in a page and clustering of page segments based on contextual analysis.We provide qualitative and quantitative experimental evidence of the practical effectiveness of our models in improving user experience when conducting online transactions with n...

show abstract

Section: Geometric Segmentationmentioning

confidence: 99%

“…These techniques are either domain [36] or site [83] specific or depend on fixed sets of HTML markup [91]. Semantic partitioning of Web pages has been described in [63][64][65]. These systems require semantic information (e.g.…”

Section: Semantic Analysis Of Web Contentmentioning

confidence: 99%

Transaction models for Web accessibility

Mahmud

Ramakrishnan

2011

World Wide Web

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use the five-class scheme and adopt the layout features studied by Xiao et al [16] Web page segmentation is the preparing step for classifying block functions. It is a challenging task and has been widely studied [1,2,5,6,8,10,12,14,15]. Early researches relied on cues from HTML DOM trees, contents and links.…”

Section: Related Workmentioning

confidence: 99%

Learning Web Page Block Functions using Roles of Images

Yang

Shi

2008

2008 Third International Conference on Pervasive Computing and Applications

View full text Add to dashboard Cite

Making use ofblock information in Web IR and Data Mining tasks calls for a good understanding of the function of each block. Existing works on classifying block functions andjudging block importance have not made full use of the image factor, and only simple image features were considered. We regard image as a strong indicator of Web page blocks with various functions and propose to learn block functions using roles of images as part of block features. Blocks are generated from Web page segmentation and roles of images are automatically decided by image classification. We experiment on 140 Web pages and demonstrate that utilizing roles of images can significantly improve the classification quality of learning Web page block functions. We also measure the usefulness of diferent roles of images and evaluate the effect oftwo page segmentation methods.

show abstract

“…The method column shows the classification that is defined in section 2. The most common SAP techniques are manually-created rules [16], pattern matching [18], automatic discovery of patterns [10], and wrapper induction, either linguistic [12] or structural based [17]. While the machine learning methods, such as those used by Amilcare [12], usually perform better [21], the rule-based MUSE system using conditional processing has shown that rule-based systems can equal the performance of machine learning-based systems [16].…”

Section: Platform Summarymentioning

confidence: 99%

Survey of semantic annotation platforms

Reeve

Han

2005

Proceedings of the 2005 ACM Symposium on Applied Computing

195

114

View full text Add to dashboard Cite

The realization of the Semantic Web requires the widespread availability of semantic annotations for existing and new documents on the Web. Semantic annotations are to tag ontology class instance data and map it into ontology classes. The fully automatic creation of semantic annotations is an unsolved problem. Instead, current systems focus on the semi-automatic creation of annotations. The Semantic Web also requires facilities for the storage of annotations and ontologies, user interfaces, access APIs, and other features to fully support annotation usage. This paper examines current Semantic Web annotation platforms that provide annotation and related services, and reviews their architecture, approaches and performance.

show abstract

Automatic Annotation of Content-Rich HTML Documents: Structural and Semantic Analysis

Cited by 47 publications

References 32 publications

Transaction models for Web accessibility

Transaction models for Web accessibility

Learning Web Page Block Functions using Roles of Images

Survey of semantic annotation platforms

Contact Info

Product

Resources

About