Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Implications of Web 2.0 on Information Research Wen-Lian Hsu Academia Sinica, Taiwan 中央研究院資訊所 許聞廉

Similar presentations


Presentation on theme: "1 Implications of Web 2.0 on Information Research Wen-Lian Hsu Academia Sinica, Taiwan 中央研究院資訊所 許聞廉"— Presentation transcript:

1 1 Implications of Web 2.0 on Information Research Wen-Lian Hsu Academia Sinica, Taiwan 中央研究院資訊所 許聞廉 hsu@iis.sinica.edu.tw

2 2 Outline  What is Web 2.0?  Web 2.0 and Research Human-based Computation Folksonomy (Social Tagging) Academic Data Analysis GIO-Info  Conclusion

3 3

4 4 What is Web 2.0?  Web 2.0 Conference (October 2004)  Tim O'Reilly The Web As a Platform Harnessing Collective Intelligence Data is the Next Intel Inside End of the Software Release Cycle Lightweight Programming Models Software Above the Level of a Single Device Rich User Experiences

5 5 Key Web 2.0 services/applications  Blogs  Wikis  Tagging and social bookmarking  Multimedia sharing  RSS and syndication  Podcasting  P2P

6 6 Social Bookmarking Source: http://funp.com/push/

7 7 Soruce: http://www.hemidemi.com/ Source: http://digg.com/

8 8 Blog Content comments adsense Social bookmark Source: http://carol.bluecircus.net/

9 9 Skype Source: S.A Baset, H. Schulzrinne (September 14, 2004). An Analysis of the Skype Peer-to-Peer Internet Telephony Protocol. Technical Report. Columbia University.

10 10 Wikipedia

11 11 Second Life

12 12 Symbiosis ( 共生機制 ) is the Key Blog Social bookmark

13 13 The Web Changes in Several Dimensions  Dynamics  Heterogeneity  Collaboration  Composition  Socialization

14 14 Current Research Activities  Information Retrieval on Blogs NTCIR-7 CLIRB (Cross-Lingual Information Retrieval for Blog)  Question Answering on Blogs TREC 2007 QA Track  Question Answering on Wikipedia QA@CLEF 2007  CLEF 2006 WiQA given a Wikipedia page, locate information snippets in Wikipedia  PASCAL Ontology Learning Challenge Ontology construction Ontology extension Ontology population Concept naming  LinkKDD2006, Textlink2007, MRDM2007

15 15 International Competition  1 st /9 place in the NTCIR5 2005 CLQA Chinese Question Answering Contest (44.5%)  1 st /13 place in the WS CityU closed track of the SIGHAN 2006 Word Segmentation Contest (97.2%)  2 nd /10 place in the WS CKIP closed track of the SIGHAN 2006 Word Segmentation Contest (95.7%)  2 nd /8 place in the NER CityU closed track of the SIGHAN 2006 Named Entity Recognition Contest (88%)  1 st place in the NTCIR6 2006 CLQA Chinese Question Answering Contest (55.3%)  1 st place in the NTCIR6 2006 CLQA English-Chinese Question Answering Contest (34%)

16 16 Factoid Questions  PERSON: 請問芬蘭第一位女總統為誰? Who is Finland's first woman president?  LOCATION: 請問狂牛症最早起源於何國? Which country is the mad cow disease originated from?  ORGANIZATION: 請問收購南韓三星汽車的外國廠商為何? Which corporation bought South Korea's Samsung Motors?  TIME  NUMBER  ARTIFACT

17 17 IASL QA Architecture SVM InfoMap Question Processing AutoTagMencius ME LuceneAutoTag Passage Retrieval Answer Ranking Mencius Filter word index char index documents Answers Answer Extraction

18 18 Chinese Question Taxonomy for NTCIR CLQA Factoid Question Answering

19 19 Knowledge Representation of Chinese Questions Chinese Question: 2004 年奧運在哪一個城市舉行 ? (In which city were the Olympics held in 2004?) [5 Time]:[3 Organization]:[7 Q_Location]:([9 LocaitonRelatedEvent])

20 20 QC by SVM  Two types of feature used for CQC Syntactic features  Bag-of-Words character-based bigram (CB) word-based bigram (WB)  Part-of-Speech (POS) AUTOTAG  POS tagger developed by CKIP, Academia Sinica Semantic Features  HowNet Senses HowNet Main Definition (HNMD) HowNet Definition (HND)

21 21 Question Classification Accuracy

22 22 Answer Extraction Mencius Filter Answer Extraction 廿一世紀美國總統 總統父子檔美國第二對 美國總統性事錄 翻開美國總統傳訊史 美國總統匆忙赴晚宴 陸文斯基瘋狂愛上美國總統 美國總統大選選舉人票分析 前越南總統阮文紹病逝美國 美國總統柯林頓表示 陸文斯基 阮文紹 柯林頓

23 23 Templates generated by local alignment .. 因 /Cbb/O 台中縣 /Nc/LOC 議長 /Na/OCC 顏清標 /Nb/PER 涉嫌 /VK/O.... 清朝 /Nd/O 台灣 /Nc/LOC 巡撫 /Na/OCC 劉銘傳 /Nb/PER 所 /D/O..  LOC OCC PER(contains only NEs)  被 /P/O 大陸 /Nc/LOC 國家 /Na/O 主席 /Na/OCC 江澤民 /Nb/O 形容為 /VG/O.. /COMMA/O 香港 /Nc/LOC 行政 /Na/O 長官 /Na/OCC 董建華 /Nb/PER 近日.. 俄羅斯 /Nc/LOC 男子 /Na/O 選手 /Na/OCC 史莫契柯夫 /Nb/O 在 /P/O..  LOC Na OCC Nb (template contains POS-tag)  由 /P/O 建業 /Nc/O 所長 /Na/OCC 張龍憲 /Nb/PER 擔任 /VG/O 由 /P/O 安侯 /Nb/O 所長 /Na/OCC 魏忠華 /Nb/PER 擔任 /VG/O  由 N 所長 PER 擔任 (template contains paritial POS-tag, word)  在 /P/O 卡達首都 /Nc/LOC 多哈 /D/PER,LOC 舉行 /VC/O 於 /P/O 國父紀念館 /Nc/ORG - 舉行 /VC/O 在 /P/O 國父紀念館 /Nc/ORG 廣場 /Nc/O 舉行 /VC/O  P Nc – 舉行 (template with gap ‘-’ )

24 24 Answer Extraction from Template  Question: 誰是台灣國防部長?  Q-Type: PERSON Q-KEYWORD: 台灣 國防部長  Tagged Passages 前任 /A/O 美國 /Nc/LOC 國防部長 /Na/OCC 溫柏格 /Nb/PER 認為 /VE/O , /COMMACATEGORY/O 美國 /Nc/LOC 國防部長 /Na/OCC 柯恩 /Nb/PER 今天 /Nd/O 表示 /VE/O , /COMMA/O 華府 /Nc/ORG,LOC 當局 /Na/O 正 /D/O 設法 /VF/O 釐清 /VC/O 台灣 /Nc/LOC 【 /PAR/O 路透 /Nb/ORG 東京 /Nc/LOC 十九日 /Nd/TIME 電 /VC/ART 】 /PAREN/O 台灣 /Nc/LOC 國防部長 /Na/OCC 唐飛 /Nb/PER 昨天 /Nd/O  Template matching and Relation building Template: LOC OCC PER Relation:  美國, 國防部長, 溫柏格, 柯恩  台灣, 國防部長, 唐飛

25 25 Answer Extraction from Template  Question: 黛安娜王妃的死亡車禍事故發生在哪裡? Q-TYPE: LOCATION Q-KEYWORD: 黛安娜 王妃 死亡 車禍 事故 發生  Tagged Passages.. 則 /D/O 把 /P/O 英國 /Nc/LOC 黛安娜 /Nb/PER 王妃 /Na/O 的 /DE/O 巴黎 /Nc/LOC 死 亡 /VH/O 車禍 /Na/O , /COMMA/O 搬上 /VC/O 舞台 /Na/O.... 英國 /Nc/LOC 王妃 /Na/O 黛安娜 /Nb/PER 離開 /VC/O 人世 /Nc/O 四個多月 /Nd/TIME..  Template matching and Relation building Template:  PER Na DE LOC – Na  LOC Na PER - VC Relation:  黛安娜 /PER, 王妃 /Na, 巴黎 /LOC, 車禍 /Na  英國 /LOC, 黛安娜 /PER, 王妃 /Na, 離開 /VC

26 26 Answer Ranking  Features are combined as weighted sum  Answer Ranking Features IR Score Answer Frequency (voting) * QFocus adjacency:  “ 美國總統 [ 布希 ] 表示 ”  “ 前往 [ 惠氏藥廠 ] 參觀 ” * Question Term and Answer Term (QAT) Co-occurrence * Answer Template

27 27 Web 2.0 and Research  Human-based Computation  Folksonomy (Social Tagging)  Academic Data Analysis  GIO-Info

28 28 Human-based Computation

29 29 Human-based Computation  Social Search wayfinding tools informed by human judgment  CAPTCHA reversed Turing test (Turing test 是由人來詢問系統,這裡 則是由系統來詢問使用者)  Interactive Genetic Algorithm (IGA) a genetic algorithm informed by human judgment. 由人工提供 fitness function 結果  例子:描繪罪犯畫像,系統以 GA 方式產生嫌犯畫像, 目擊者負責評分看那個比較像,不斷重複過程直到接近 罪犯樣子為止

30 30 CAPTCHA Completely Automated Public Turing test to tell Computers and Humans Apart  A CAPTCHA is a type of challenge-response test used in computing to determine whether the user is human. wikipedia SOURCE: http://recaptcha.net/

31 31 CAPTCHA blog CAPTCHA blog CAPTCHA blog CAPTCHA Unrecognized text Recognized text

32 32 The ESP Game  a two-player game  The goal is to guess what your partner is typing on each image.  Once you both type the same word(s), you get scores. Source: http://www.espgame.org/ ESP

33 33 The Phetch Game Play as a describer

34 34 The Phetch Game Play as a seeker Phetch

35 35 How about a game for describing idioms? 罄竹難書如沐春風 高抬貴手不動如山 壞事做太多 罄竹難書 : 壞事做太多 虎頭蛇尾 : 做事沒有毅力 ………

36 36 Folksonomy (Social Tagging)

37 37 Folksonomy (Social Tagging)  Also known as social tagging, collaborative tagging, social classification, social indexing  Folksonomy is the practice and method of collaboratively creating and managing tags to annotate and categorize content. Wikipedia

38 38

39 39 del.icio.us Tags: Descriptive words applied by users to links. Tags are searchable My Tags: Words I’ve used to describe links in a way that makes sense to me

40 40 Semantic Web Source: Tim Berners-Lee

41 41 Using Folksonomy to Help Semantic Web  Top-down Semantic Annotation Approach  Define an ontology first  Use the ontology to add semantic markups to web resources.  The semantics is provided by the ontology which is shared among different web agents and applications. Problem  Negotiation  Evolution (hard to maintain)  High Barrier (background) Source: Xian Wu, Lei Zhang, Yong Yu. “ Exploring Social Annotations for the Semantic Web ”

42 42 Using Folksonomy to Help Semantic Web  Bottom-up approach with social tagging  Advantage No common ontology or dictionary are needed Easy to access Sensitive to information drift  Disadvantage Ambiguity Problem: For example, “XP” can refer to either “Extreme Programming” or “Windows XP”. Group Synonymy Problem: two seemingly different annotations may bear the same meaning. Source: Xian Wu, Lei Zhang, Yong Yu. “ Exploring Social Annotations for the Semantic Web ”

43 43 Or Folksonomy is the Solution?  Ontology is Overrated Classification of the web has failed Classification itself is filled with bias and error Tagging is the solution Source: http://www.shirky.com/writings/ontology_overrated.html

44 44 Academic Data Analysis

45 45 Academic Data Analysis CiteSeer Google Scholar e-Lib, Lib 2.0 concept adding into application, so search platform provide open API for collecting more data Users participate and interact with data and people Add My Library, Tag Ex. Citeulike, BibSonomyCiteulike BibSonomy Add Comments, Rating, Recommendation Ex. TechlensTechlens Domain Focus Groups Ex. BotanicusBotanicus Windows Live Academic Search PudMed Arxiv Citation index Papers, journal/conference, authors

46 46 An Example  Let’s use an example of TechLen to imagine what research on IR /NLP can do. Authors Readers Papers

47 47 The Terminology Alfred V Aho Entities Alfred AhoAV AhoAho, A. V. References Links Alfred Aho, John Hopcroft, Jeffrey Ullman AV Aho, BW Kernighan, PJ Weinberger Entity Groups G1 (Programming Languages) G2 (Databases) G3 (Algorithms)

48 48 Imagine how we can make use of them Papers Authors Readers Comments Rating Reference Extraction Entity Resolution

49 49 New Research Topics  From those changes, key emerging challenge for “Data Mining” is tackling the problem of dealing with richly structured, finding patterns behind heterogeneous datasets, …, etc.  Several researches focus on those problem like (Social) Network Analysis Link Mining PASCAL Ontology Learning Challenge …

50 50 Society Nodes: individuals (Authors, Readers) Links: social relationship (family/work/friendship/belong to,…etc.) S. Milgram (1967) Social networks: Many individuals with diverse social interactions between them. John Guare Six Degrees of Separation, Science source: www.cs.uiuc.edu/~hanjwww.cs.uiuc.edu/~hanj

51 51 Communication networks The Earth is developing an electronic nervous system, a network with diverse nodes and links are -computers -routers -satellites -Papers -User IP -Comments -Response -… -phone lines -TV cables -EM waves - Relations between artifacts Communication networks: Many non- identical components with diverse connections between them. source: www.cs.uiuc.edu/~hanjwww.cs.uiuc.edu/~hanj Artifacts in Techlens

52 52 Link-based Object Ranking  Perhaps the most well known link mining task is that of link-based object ranking (LBR), which is a primary focus of the link analysis community. The objective of LBR is to exploit the link structure of a graph to order or prioritize the set of objects within the graph.  Example PageRank What paper is most important in this area? What journal/conference is most important in this area? What topic is important in this area?

53 53 Link-based Object Classification/ Link- based Classification (LBC)  Predicting the category of an object based on its attributes and its links and attributes of linked objects  Web: Predict the category of a web page, based on words that occur on the page, links between pages, anchor text, html tags, etc.  Citation: Predict the topic of a paper, based on word occurrence, citations, co-citations  Epidemic : Predict disease type based on characteristics of the people; predict person’s age based on ages of people they have been in contact with and disease type

54 54 Group Detection  Cluster the nodes in the graph into groups that share common characteristics. That is, Predicting when a set of entities belong to the same group based on clustering both object attribute values and link structure. Web: identifying communities Citation: identifying research communities

55 55 Entity Resolution  Predicting when two objects are the same, based on their attributes and their links Web: predict when two sites are mirrors of each other Citation: predicting when two citations are referring to the same paper Epidemics: predicting when two disease strains are the same Biology: learning when two names refer to the same protein

56 56 Link Prediction  Predict whether a link exists between two entities, based on attributes and other observed links Web: predict if there will be a link between two pages Citation: predicting if a paper will cite another paper, or predict the venue type of a publication (conference, journal, workshop) based on properties of the paper Epidemics: predicting who a patient’s contacts are ( 在流行病學上需要去找出病源 ( 灶 )/ 傳染源 )

57 57 Other Possible Research Directions  Expert Finding like giving a suggestion of Paper Reviewer, Conference committee member  Ecological Evolution of Some Research Like one topic with different solution in a time period A domain’s topic distribution

58 58 GEO-Info 地理資訊

59 59 GEO-Info Google Earth/Map GIS Limited user, limited usage Open for every one Google Earth Community Google Earth Blog Ogle Earth…. User Participate GML Photo-sharing User Annotation

60 60 Some Research Topics  Until now, a lot of information can be combined into google earth/map by KML.  Hence such information can be integrated by geocoding, some models become very interesting, such as Photo Annotation, Sharing, and Search Live information Planning 3D, Flights Animation Travel experience, comments Transportation information, survival information Climate Change

61 61 Some Information bundled with Google Earth/Map ( 中山公園 ) Integrated with Youtube (video & tags) Photo sharing, (photo & Tags)

62 62 Some Application Integrate more Information on Map Personal Life Information Integration GeoDDupe: A Novel Interface for Interactive Entity Resolution in Geospatial Data

63 63 Photo link with Map Source: http://www.panoramio.com

64 64 Image-based Rendering (IBR)  IBR relies on a set of two-dimensional images of a scene to generate a three-dimensional model and then render some novel views of this scene.  Web 2.0 enables sharing of photographs on a truly massive scale

65 65 Microsoft PhotoSynth  From SIFT to PhotoSynth

66 66 Conclusion  Research results can be easily integrated on the Web 2.0 platform  make restricted-domain research more useful for the public (such as image-based rendering) Software agent  Benefit human-based computation  Certain research topics will be easier to tackle, such as personalization in virtual world (more data available)  Data becomes more task oriented (e.g. Wikipedia)  More versatile data networks available

67 67 誠徵研究助理(歡迎替代役) 1. 資訊相關研究所畢業。 2. 具備研讀英文論文能力。 3. 對 「中文自然語言處理」 ( 「自然輸入法」、「問 答系統」 ) 或「生物資訊」(「生物資訊演算法」、 「生物文獻檢索分析」)研究有熱忱。 4. 熟悉下列任一程式語言: C/C++/C#/JAVA 與問題 解決能力 5. 應徵輸入法相關工作者具下列任一條件尤佳: WinCE/Win32 API 。 6. 善於溝通與團隊合作。

68 68 Acknowledgement  I would also like to thank two Ph. D. students of mine who help organize the slides: 李政緯,呂俊宏

69 69 Thank You


Download ppt "1 Implications of Web 2.0 on Information Research Wen-Lian Hsu Academia Sinica, Taiwan 中央研究院資訊所 許聞廉"

Similar presentations


Ads by Google