More Related Content
Viewers also liked (18)
Similar to [submission] Final_Presentation (20)
![[DevDay2018] Embrace the challenge – working as a developer in Content Manage...](https://cdn.slidesharecdn.com/ss_thumbnails/sergeyurovskyquangdang-workingasadeveloperincontentmanagementsystems-codeenginestudio-180419091219-thumbnail.jpg?width=560&fit=bounds)
[submission] Final_Presentation
- 1. Higgs-Reader Team C. Arif Jafer, Camilo Celis, Marcus Low,
- 2. Contents ❏ Overview ❏ Problems & Requirements ❏ Goals Met ❏ Approach ❏ Architecture ❏ WebAnn - Training Set Creator Tool ❏ The Korean Language Model ❏ Final Reader ❏ Demo
- 3. Overview
- 4. Overview ● A reader engine is composed of: ○ A web-page text extraction algorithm, to find the main article text ○ Heuristics to find metadata, relevant images to the main article ○ User Interface to embody the reader engine
- 6. Overview ● Higgs-Reader (built upon DOM-Distiller) ○ Boilerpipe extended with a Korean Language Model ■ Tools to train the model - Weka / C4.5 Decision Trees ■ Tools to generate the training set - WebAnn ■ Integration of the model back into the reader engine ○ Existing Heuristics in DOM-Distiller will be tuned to improve the performance for Korean Web pages ○ Final Reader Chrome Extension
- 7. Goals Met ● Extended the DOM-Distiller reader engine, with enhanced support for Korean web pages. ● Created a new Korean Language model for text- extraction ● Tuned the existing heuristics to improve the performance on Korean web sites ● Created a Reader UI to embody the reader engine
- 8. Problems Encountered ● The existing reader engines, such as DOM-Distiller, had a poor support for non-English web pages. ● Korean websites did not commonly follow the website markup standards, such as OpenGraph protocol, schema.org, etc. ● Current HTML standards used by majority of websites tend to still use the <div> or <table> tags to separate content. This eliminates the possibility of identifying the semantics of any particular section of HTML source. ● Poor performance on multi-page websites. It should be able to retrieve all or at most K number of the pages at once. ● Poor performance on detection of relevant images or other rich-content media.
- 9. Requirements Met ● A Korean language model was made and integrated into the Boilerpipe algorithm. ○ Tooling for creating the training set (WebAnn) ● The existing DOM-Distiller was tuned to work with Korean websites. ● Better support for web pages, with their layouts made with tables. ● Better support for multi-page web pages. ● Enhanced the relevant image detection heuristic ● Chrome Extension Implementation (Final Reader) ● Comparison mechanism for testing purposes
- 10. Approach ● 4 Stages ○ Web Page Annotator ○ Korean Language Model for boilerpipe ○ Reader Engine tuning ○ Reader UI
- 11. Approach / Architecture (Overall)
- 12. Approach / Architecture (WebAnn) ● Web Page Annotator (WebAnn) ○ Built as a Chrome extension ○ Provides a simple UI to annotate different sections of a web page with predefined labels. ■ HEADING ■ FULL_CONTENT ■ SUPPLEMENTARY ■ COMMENTS ■ RELEVANT_IMAGES
- 13. WebAnn -- Training Set Creator Tool Ordinary Webpage
- 14. WebAnn -- Training Set Creator Tool Annotator in Action
- 15. Approach / Architecture (Machine Learning)
- 16. Approach / Architecture (Language Model) ● Korean Language Model ○ A corresponding model for each of the Models listed in Table 3.2 ○ Will be trained using Shallow Text features listed in Table 3.2 DensityRulesClassifier HeuristicsFilterBase IgnoreBlocksAfterContentFilter IgnoreBlocksAfterContentFromEndFilter KeepLargestFulltextBlockFilter MinFullTextWordsFilter NumWordsRulesClassifier TerminatingBlocksFinder prev_link_density prev_text_density prev_num_words prev_num_words_in_anchor_text curr_link_density curr_text_density curr_num_words curr_num_words_in_anchor_text next_link_density next_text_density next_num_words next_num_words_in_anchor_text
- 17. Approach / Architecture (Language Model) ● Korean Language Models ○ Trained using C4.5 Decision Trees algorithm ■ Existing English language models also trained with this algorithm ■ better performance on multi-category classification problems ■ Good performance in supervised learning ○ Use the Weka ML toolset ■ Provides a wide number of implementations for ML algorithms ■ easy to compare and evaluate different models by tuning the parameters ■ Provides cross-validation features, such as k-fold cross validation
- 18. Korean Language Heuristics ● Lack of <p> tags ● Terminating Blocks
- 19. Korean Language Model Decision Tree based on Number of Words Decision Tree based on Density of Words
- 20. Number of Words Korean Language Model English Model boilerplate content 21032 621 225 647 Confusion Matrix boilerplate content 21637 16 142 730 Correctly Classified Instances 22367 99.2986 % Incorrectly Classified Instances 158 0.7014 % Density of Words English Model boilerplate content 21105 548 220 652 Confusion Matrix boilerplate content 21637 16 142 730 Correctly Classified Instances 22367 99.2986 % Incorrectly Classified Instances 158 0.7014 %
- 21. Approach / Architecture (Language Model)
- 22. Approach / Architecture (Reader Engine) ● Reader Engine ○ Based on the DOM-Distiller project ○ New Language model will be integrated into Boilerpipe ○ Existing Heuristics will be tuned to improve performance on Korean web pages ○ Built upon Google Web Toolkit (GWT) ■ Can use Java libraries ■ Can use Java OOP features ■ Compiler will produce cross-browser JS code ■ Reader engine can be ported into any browser
- 23. Approach / Architecture (Reader Engine)
- 24. Final Reader UI (Implementation) Final Reader Old Reader
- 25. OLD READER (Live Demo) ● Small Chrome Extension using old dom- distiller code and old language model
- 26. FINAL READER (Live Demo) ● Faster build cycles ● Can be used to easily compare with Old Reader extension
- 27. Thank you