Download presentation
Presentation is loading. Please wait.
Published byConnor O'Connor Modified over 11 years ago
1
Internet Research: Whats hot in Search, Advertizing & Cloud Computing Rajeev Rastogi Yahoo! Labs Bangalore
2
The most visited site on the internet 600 million+ users per month Super popular properties – News, finance, sports – Answers, flickr, del.icio.us – Mail, messaging – Search
3
Unparalleled scale 25 terabytes of data collected each day – Over 4 billion clicks every day – Over 4 billion emails per day – Over 6 billion instant messages per day Over 20 billion web documents indexed Over 4 billion images searchable No other company on the planet processes as much data as we do!
4
Yahoo! Labs Bangalore Focus is on basic and applied research – Search – Advertizing – Cloud computing University relations – Faculty research grants – Summer internships – Sharing data/computing infrastructure – Conference sponsorships – PhD co-op program
5
Web Search
6
What does search look like today?
7
Search results of the future: Structured abstracts yelp.com babycenter epicurious answers.com LinkedIn webmd New York Times Gawker
8
Search results of the future: Query refinement
9
Search results of the future: Rich media
10
Technologies that are enabling search transformation Information extraction (structured abstracts) Web page classification (query refinement) Multimedia search (rich media)
11
Reviews Information extraction (IE) Goal: Extract structured records from Web pages Name Address Category Phone Price Map
12
Multiple verticals Business, social networking, video, ….
13
Price Category Address PhonePrice One schema per vertical Name Title Education Connections Posted by Title Date RatingViews
14
IE on the Web is a hard problem Web pages are noisy Pages belonging to different Web sites have different layouts Noise
15
Web page types Template-based Hand-crafted
16
Template-based pages Pages within a Web site generated using scripts, have very similar structure – Can be leveraged for extraction ~30% of crawled Web pages Information rich, frequently appear in the top results of search queries E.g. search query: Chinese Mirch New York – 9 template-based pages in the top 10 results
17
Wrapper Induction Learn Annotate Pages Sample pages Website pages Learn Wrappers Apply wrappers Records XPath Rules Extract Annotations Extract Website pages Sample Enables extraction from template-based pages
18
Example XPath: /html/body/div/div/div/div/div/div/span /html/body//div//span Generalize
19
Filters Apply filters to prune from multiple candidates that match XPath expression XPath: /html/body//div//span Regex Filter (Phone): ([0-9] 3 ) [0-9] 3 -[0-9] 4
20
Limitations of wrappers Wont work across Web sites due to different page layouts Scaling to thousands of sites can be a challenge – Need to learn a separate wrapper for each site – Annotating example pages from thousands of sites can be time-consuming & expensive
21
Research challenge Unsupervised IE: Extract attribute values from pages of a new Web site without annotating a single page from the site Only annotate pages from a few sites initially as training data
22
Conditional Random Fields (CRFs) Models conditional probability distribution of label sequence y=y 1,…,y n given input sequence x=x 1,…,x n – f k : features, k : weights Choose k to maximize log-likelihood of training data Use Viterbi algorithm to compute label sequence y with highest probability
23
CRFs-based IE Name Category Address Phone Noise Web pages can be viewed as labeled sequences Train CRF using pages from few Web sites Then use trained CRF to extract from remaining sites
24
Drawbacks of CRFs Require too many training examples Have been used previously to segment short strings with similar structure However, may not work too well across Web sites that – contain long pages with lots of noise – have very different structure
25
An alternate approach that exploits site knowledge Build attribute classifiers for each attribute – Use pages from a few initial Web sites For each page from a new Web site – Segment page into sequence of fields (using static repeating text) – Use attribute classifiers to assign attribute labels to fields Use constraints to disambiguate labels – Uniqueness: an attribute occurs at most once in a page – Proximity: attribute values appear close together in a page – Structural: relative positions of attributes are identical across pages of a Web site
26
Attribute classifiers + constraints example Chinese Mirch Chinese, Indian 120 Lexington Avenue New York, NY 10016 (212) 532 3663 Page1: Jewel of India Indian 15 W 44 th St New York, NY 10016 (212) 869 5544 Page2: 21 Club American 21 W 52 nd St New York, NY 10019 (212) 582 7200 Page3: Phone Address Category Name Category Category, Name Name Name, Noise Address Phone Uniqueness constraint: Name Precedence constraint: Name < Category 21 Club American 21 W 52 nd St New York, NY 10019 (212) 582 7200 Category Name Address Phone
27
Other IE scenarios: Browse page extraction Similar-structured records
28
IE big picture/taxonomy Things to extract from – Template-based, browse, hand-crafted pages, text Things to extract – Records, tables, lists, named entities Techniques used – Structure-based (HTML tags, DOM tree paths) – e.g. Wrappers – Content-based (attribute values/models) – e.g. dictionaries – Structure + Content (sequential/hierarchical relationships among attribute values) – e.g. hierarchical CRFs Level of automation – Manual, supervised, unsupervised
29
Web Page Classification: Requirements Quality – High Precision and Recall – Leverage structured input (links, co-citations) and output (taxonomy) Scalability – Large numbers of training Examples, Features and Classes – Complex Structured input and output Cost – Small human effort (for labeling of pages) – Compact classifier model – Low prediction time
30
Structured Output Learning Structured Output Examples – Multi-class – Taxonomy Naïve approach – Separate binary classifier per class – Separate classifier for each taxonomy level Better approach – single (SVM) classifier – Higher accuracy, more efficient – Sequential Dual Method (SDM) Visit each example sequentially and solve associated QP problem (in dual) efficiently Order of magnitude faster Sport Cricket Health One-day Test FitnessMedicine Soccer
31
Classification With Relational Information Relational Information – Web page links, structural similarity Graph representation – Pages as nodes (with labels) – Edge weights (s(j,k)): Page similarity, out-link/co-citation existence, etc. Classification can be expressed as an optimization problem: Co-citation Similar structure Link
32
Multimedia Search Availability & consumption of multimedia content on the Internet is increasing – 500 billion images will be captured in 2010 Leveraging content and metadata are important for MM search Some big technical challenges are: – Results diversity – Relevance – Image Classification, e.g., pornography
33
Near-Duplicate Detection Multiple near-similar versions of an image exist on the internet –scaled, cropped, captioned, small scene change, etc. Near-duplicates adversely impact user experience Can we use a compact description and dedup in constant time? Fourier-Mellin Transform (FMT): translation, rotation, and scale invariant Signature generation using a small number of low-frequency coefficients of FMT
34
Filtering noisy tags to improve relevance Measures such as IDF may assign high weights to noisy tags – Treat Tag-Sets as Bag-of-words, random collection of terms Boosting weights of tags based on their co-occurrence with other tags can filter out noise idfco-occur
35
Online Advertizing
36
Search query Ad Sponsored search ads
37
How it works Advertiser Sponsored search engine I want to bid $5 on canon camera I want to bid $2 on cannon camera Engine decides when/where to show this ad on search results page Advertizer pays only if user clicks on ad Ad Index
38
Ad selection criterion Problem: which ads to show from among ads containing keyword? Ads with highest bid may not maximize revenue Choose ads with maximum expected revenue – Weigh bid amount with click probability AdBidClick Prob Expected Revenue A1$40.10.4 A2$20.71.4 A3$30.30.9
39
Contextual Advertising Ads
40
Contextual ads Similar to sponsored search, but now ads are shown on general Web pages as opposed to only search pages – Advertizers bid on keywords – Advertizer pays only if user clicks, Y! & publisher share paid amount – Ad matching engine ranks ads based on expected revenue (bid amount * click probability)
41
Estimating click probability Use logistic regression model p(click | ad, page, user) = f i : i th feature for ad, page, user w i : weight for feature f i Training data: ad click logs (all clicks + non-click samples) Optimize log-likelihood to learn weights
42
Features Ad: bid terms, title, body, category,… Page: url, title, keywords in body, category, … User – Geographic (location, time) – Demographic (age, gender) – Behavioral Combine above to get (billions of) richer features E.g: (apple ad title) (ipod page body) (20 < user age < 30) Select subset that leads to improvement in likelihood
43
Banner ads Show Web page with display ads Ad Creates Brand Awareness
44
How it works Engine guarantees 1M impressions Advertiser pays a fixed price – No dependence on clicks Engine does admission control, decides allocation of ads to pages Advertiser Banner Ad Engine I want 1M impressions On finance.yahoo.com, gender = male, age = 20-30 during the month of April 2009 Ad Index
45
Allocation Example SUPPLY (Qty, Price) DEMAND (Target, Qty) Age Gender Male Female 20 - 30> 30 (Gender=Male, 12M) (Age>30, 12M) (10M,$20)(10M,$10) Suboptimal Optimal (6M,$10) Value=$60M Value= $120M (6M, $20) Unallocated 12
46
Research problem Goal: Allocate demands so that the value of unallocated inventory is maximized Similar to transportation problem
47
Transportation problem 1 1 ji 2 2 Demands SupplyPrice d1 d2 di s1 sj s2 pj p2 p1 Edges to Ri xi1 xi2 xij xij: Units of demand I allocated to region j
48
Ads taxonomy Search pagesWeb pages Contextual Sponsored search Banner Online Ads Keywords Attributes Targeting: Guarantees:NG G CPC CPM/CPCCPMCPC Model:
49
Major trend: Ads convergence Today Contextual CPC Display CPM Separate systems for contextual & display Tomorrow Unified Ads marketplace – Unify contextual & Display – Increase supply & demand – Enable better matching – CPC, CPM ads compete Y! Ad Exchange CPC, CPM Advertiser: Creates demand Publisher: Creates supply of pages
50
Research challenge Which ad to select between competing CPC, CPM ads? – Use eCPM For CPM ads: eCPM = bid For CPC ads: eCPM = bid * Pr(click) – Select ad with max eCPM to maximize revenue Problem: ad with highest eCPM may not get selected – eCPMs estimated based on historical data, which can differ from actual eCPMs – Variance in estimated eCPMs higher for CPC ads – Selection gets biased towards ads which have higher variance as they have higher probability of over-estimated eCPMs Estimated eCPM CPC ad CPM ad Actual eCPM Estimated eCPM
51
Cloud Computing
52
Much of the stuff we do is compute/data-intensive Search – Index 100+ billion crawled Web pages – Build Web graph, compute PageRank Advertizing – Construct ML models to predict click probability Cluster, classify Web pages – Improve search relevance, ad matching Data mining – Analyze TBs of Web logs to compute correlations between (billions of) user profiles and page views
53
Solution: Cloud computing A cloud consists of – 1000s of commodity machines (e.g., Linux PCs) – Software layer for Distributing data across machines Parallelizing application execution across cluster Detecting and recovering from failures – Yahoo!s software layer based on Hadoop Open Source
54
Cloud computing benefits Enables processing of massive compute-intensive tasks Reduces computing and storage costs – Resource sharing leads to efficient utilization – Commodity hardware, open source Shields application developers from complexity of building in reliability, scalability in their programs – In large clusters, machines fail every day – Parallel programming is hard
55
Cloud computing at Yahoo! 10,000s of nodes running Hadoop, TBs of RAM, PBs of disk Multiple clusters, largest is a 1600 node cluster
56
Hadoops Map/Reduce Framework Framework for parallel computation over massive data sets on large clusters As an example, consider the problem of creating an index for word search. – Input: Thousands of documents/web pages – Output: A mapping of word to document IDs Farmer1 has the following animals: bees, cows, goats. Some other animals … Animals: 1, 2, 3, 4, 12 Bees: 1, 2, 23, 34 Dog: 3,9 Farmer1: 1, 7 …
57
Hadoops Map/Reduce Machine1 Machine2 Machine3 Animals: 1,3 Dog: 3 Animals:2,12 Bees: 23 Dog:9 Farmer1: 7 Machine4 Animals: 1,3 Animals:2,12 Bees:23 Machine5 Dog: 3 Dog:9 Farmer1: 7 Machine4 Animals: 1,2,3,12 Bees:23 Machine5 Dog: 3,9 Farmer1: 7 Input splitMap Tasks intermediate output (sorted) ShuffleReduce Tasks Index example (contd.)
58
Research challenges Rack 1 Rack 2 Rack i Rack n Compute Nodes in Racks Data Blocks for a given job distributed and replicated across nodes in a rack and across racks Data Distribution and Replication Challenges: Optimize distribution to provide maximum locality Optimize replication to provide best fault tolerance Job Queues based on priorities and SLAs 123 L1L1 L2L2 SDS Q 1 40% YST Q 2 35% ATG Q m 25% LmLm Job Scheduling Challenges: Schedule jobs to maximize resource utilization while preserving SLAs Schedule jobs to maximize data locality Performance modeling
59
Summary Internet is an exciting place, plenty of research needed to improve – User experience – Monetization – Scalability Search -> Information extraction, classification, …. Advertizing -> Click prediction, ad placement, …. Cloud computing -> Job scheduling, perf modeling, … Solving problems will require techniques from multiple disciplines: ML, statistics, economics, algos, systems, …
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.