Mining tables from large scale HTML texts

Chen, Hsin-Hsi; Tsai, Shih‐Chuan; Tsai, Jin-He

doi:10.3115/990820.990845

Cited by 126 publications

(99 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the initial two sibling pages, we tested (1) whether TISP was able to recognize HTML data tables and discard HTML tables used only for layout, (2) whether it was able to pair all sibling tables correctly, and (3) whether it was able to recognize the correct pattern template or pattern combination. For the rest of sibling pages from the same web site, we tested (1) whether TISP was able to interpret tables using the recognized structure patterns, (2) whether it correctly detected the need for dynamic adjustment, and (3) whether it recognized new structure patterns correctly.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Hidden-Web Table Interpretation by Sibling Page Comparison

Tao¹,

Embley²

2007

Conceptual Modeling - ER 2007

View full text Add to dashboard Cite

Abstract. The longstanding problem of automatic table interpretation still illudes us. Its solution would not only be an aid to table processing applications such as large volume table conversion, but would also be an aid in solving related problems such as information extraction and semi-structured data management. In this paper, we offer a conceptual modeling solution for the common special case in which so-called sibling pages are available. The sibling pages we consider are pages on the hidden web, commonly generated from underlying databases. We compare them to identify and connect nonvarying components (category labels) and varying components (data values). We tested our solution using more than 2,000 tables in source pages from three different domains-car advertisements, molecular biology, and geopolitical information. Experimental results show that the system can successfully identify sibling tables, generate structure patterns, interpret tables using the generated patterns, and automatically adjust the structure patterns, if necessary, as it processes a sequence of hidden-web pages. For these activities, the system was able to achieve an overall F-measure of 94.5%.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Other table interpretation systems work based on some simple assumptions and heuristics (e.g. [2,6]). These simple assumptions (labels are either the first row or the first column) are easily broken in complex tables.…”

Section: Introductionmentioning

confidence: 99%

Automatic Hidden-Web Table Interpretation by Sibling Page Comparison

Tao¹,

Embley²

2007

Conceptual Modeling - ER 2007

View full text Add to dashboard Cite

show abstract

“…Recently due to the popularity of web pages, detection and analysis of tables in HTML documents get a lot of attention (Wang & Hu, 2002;Chen, Tsai, & Tsai, 2000). HTML provides table tags which often help detect and segment tables, but offers little help on semantic analysis.…”

Section: Table Analysismentioning

confidence: 99%

A Lexical Knowledge Representation Model for Natural Language Understanding

Chen

Ding

Ding³

2009

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques.However, it is a daunting problem how to capture deep semantic information effectively and support the construction of a large-scale knowledge base efficiently. This paper describes a new knowledge representation model, SenseNet, which provides semantic support for commonsense reasoning and natural language processing. SenseNet is formalized with a Hidden MarkovModel. An inference algorithm is proposed to simulate human-like natural language understanding procedure. A new measurement, confidence, is introduced to facilitate the natural language understanding. We present a detailed case study of applying SenseNet to retrieving compensation information from company proxy filings.

show abstract

“…Alaaeldin Hafez, Jitender Deogun, and Vijay V. Raghavan [7] propose the Item-Set Tree: A Data Structure for Data Mining. Chen, et al tried to extract tables from ASCII text [2]. Penn, et al attempted to reformat existing web information for handheld devices [4].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Gatterbauer, et al attempted to discover tabular structure without the HTML table tag, through cues such as onscreen data placement [3]. Chen, et al tried to extract tables from ASCII text [2]. Penn, et al attempted to reformat existing web information for handheld devices [4].…”

Section: Literature Reviewmentioning

confidence: 99%

Web Search Results Visualization Using Enhanced Branch and Bound Bookshelf Tree Incorporated with B3-Vis

Jayanthi¹,

Prema²

2012

IJMLC

View full text Add to dashboard Cite

Abstract-Enhancements in data mining for effective information retrieval is an emerging trend. This growth in turn has motivated researchers to seek new techniques for knowledge extraction. This research paper, induce the need for an incremental data mining approach based on data structure called the Bookshelf tree. The provoked approach is shown to be effective for solving problems related to efficiency of handling data updates, accuracy, processing input transactions, and answering user queries. This paper proposes a Branch and Bound Bookshelf Tree incorporated with association mining for self organization of the results retrieved from the RFDDb. This research work focus on the new techniques for keyword search over a mass of tables, and show that they can achieve substantially higher relevance than solutions based on a traditional search engine using Referenced attribute Functional Dependency Database (RFDDb). Branch and Bound is for best optimized result and the bookshelf tree is for organizing result for effective and efficient Information Retrieval (IR).B3-Vis Technique is proposed for visualizing the results retrieved from the Branch and Bound Bookshelf Tree. The relevant queries are arranged in each frame of Book Shelf for effective Information Retrieval. Finally, the search results are presented in visual mode, which allows a user to navigate between extracted schemas.Index Terms-Book Shelf Data structure, B3-VIS technique, information retrieval, referenced attribute functional dependency database (RFDDb), visualization, web-mining. I. INTRODUCTIONWhile searching the web, the user is often confronted by a great number of results, generally displayed in a list which is sorted according to the relevance of the results. Facing the limits of existing approach, this paper proposes exploration of new organizations [1] and presentations of search results, as well as new types of interactions with the results to make their exploration more intuitive and efficient. This research work is mainly focused on affording a knowledge mining tool in the form of a search engine that results list in visual mode in spite of Web page URLs as in the case of the existing conventional search engines.Branch and Bound perform a systematic search, often taking much less time than taken by a nonsystematic search. Many knowledge discovery applications, such as on-line services and World Wide Web, require accurate mining information from data that changes on a regular basis [7]. In World Wide Web, every day hundreds of remote sites are created and removed. Users could be interested in finding association between keywords in web search, not necessarily satisfying the measures of the data mining rules. The main focus of this paper is the processing of the results coming from an information retrieval system. Although the relevance depends on the results quality, the effectiveness of the results processing represents an alternative way to improve the relevance for the user. RFDDb provide a schema auto-complete tool to help database desi...

show abstract

Mining tables from large scale HTML texts

Cited by 126 publications

References 4 publications

Automatic Hidden-Web Table Interpretation by Sibling Page Comparison

Automatic Hidden-Web Table Interpretation by Sibling Page Comparison

A Lexical Knowledge Representation Model for Natural Language Understanding

Web Search Results Visualization Using Enhanced Branch and Bound Bookshelf Tree Incorporated with B3-Vis

Contact Info

Product

Resources

About