Slides from my presentation at the ECIR 2012 workshop on "Information Retrieval Over Query Sessions" (SIR2012) held in Barcelona, Spain.
Title: Exploring Session Search
Abstract:
Exploratory search is typically characterized by recall-oriented information needs and by uncertainty and evolution of the information need. As searchers interact with the system, their understanding of the topic evolves in response to found information. These two characteristics – uncertainty of information need and the desire to find multiple documents – drive the need to run multiple queries. Furthermore, these queries are not independent of each other because they often retrieve overlapping sets of documents. Yet traditional information retrieval systems often treat searchers’ queries in isolation, ignoring the evolution of a person’s understanding of the information need and the historical coupling among queries.
I this talk, I will describe some interface ideas we're exploring to help people incorporate their search history into their ongoing retrieval and sense-making tasks, and will touch on some issues related to retrieval algorithms and evaluation.
The Allotrope Foundation led discussion on building an open framework for laboratory data - recommending a holistic approach to build upon & promote industry standards & best practices by providing software that instantiates them.
Presentation given at the 2012 IASA Annual Conference on the use of analytics in the insurance industry. Case study examples provided with extrract of recent survey.
Explaining the Explainability: ‘Why’ and ‘How’ of Explainability in ResearchMelih Bahar
The harder the question we are trying to solve, the more sophisticated the machine learning models tend to become, making it almost impossible to interpret. This might mean more features, complex algorithms or complex patterns.
E(X)plainableAI (XAI) has been a very trending topic recently. To explain the outcomes of these models, mostly focusing on the point of view of the end user. For research, however, the machine learning models we use are mostly taken for granted as black-boxes because we usually focus on performance and don’t really need to explain the predictions to anyone else.
In this talk, I will cover why explainability (specifically using SHAP values) of a model is important also for the research phase and how it can help not just the end user but also us data scientists that are building the models. We will see several different ways of looking at a model or its predictions can help us improve performance even before the production phase.
Melih is a data scientist at Riskified where he joined almost 2.5 years ago. Today, he is working mainly on the research and improvement of the ATO product.
Originally from Turkey and coming from an engineering background, he pivoted his way into the Data Science/Machine Learning world to follow his passion for data and AI.
He believes in constant learning and endless curiosity. When not doing DS/ML, you can find him doing any kind of sports or tasting new whisky.
Slides from my presentation at the ECIR 2012 workshop on "Information Retrieval Over Query Sessions" (SIR2012) held in Barcelona, Spain.
Title: Exploring Session Search
Abstract:
Exploratory search is typically characterized by recall-oriented information needs and by uncertainty and evolution of the information need. As searchers interact with the system, their understanding of the topic evolves in response to found information. These two characteristics – uncertainty of information need and the desire to find multiple documents – drive the need to run multiple queries. Furthermore, these queries are not independent of each other because they often retrieve overlapping sets of documents. Yet traditional information retrieval systems often treat searchers’ queries in isolation, ignoring the evolution of a person’s understanding of the information need and the historical coupling among queries.
I this talk, I will describe some interface ideas we're exploring to help people incorporate their search history into their ongoing retrieval and sense-making tasks, and will touch on some issues related to retrieval algorithms and evaluation.
The Allotrope Foundation led discussion on building an open framework for laboratory data - recommending a holistic approach to build upon & promote industry standards & best practices by providing software that instantiates them.
Presentation given at the 2012 IASA Annual Conference on the use of analytics in the insurance industry. Case study examples provided with extrract of recent survey.
Explaining the Explainability: ‘Why’ and ‘How’ of Explainability in ResearchMelih Bahar
The harder the question we are trying to solve, the more sophisticated the machine learning models tend to become, making it almost impossible to interpret. This might mean more features, complex algorithms or complex patterns.
E(X)plainableAI (XAI) has been a very trending topic recently. To explain the outcomes of these models, mostly focusing on the point of view of the end user. For research, however, the machine learning models we use are mostly taken for granted as black-boxes because we usually focus on performance and don’t really need to explain the predictions to anyone else.
In this talk, I will cover why explainability (specifically using SHAP values) of a model is important also for the research phase and how it can help not just the end user but also us data scientists that are building the models. We will see several different ways of looking at a model or its predictions can help us improve performance even before the production phase.
Melih is a data scientist at Riskified where he joined almost 2.5 years ago. Today, he is working mainly on the research and improvement of the ATO product.
Originally from Turkey and coming from an engineering background, he pivoted his way into the Data Science/Machine Learning world to follow his passion for data and AI.
He believes in constant learning and endless curiosity. When not doing DS/ML, you can find him doing any kind of sports or tasting new whisky.
At the 2012 Face of Finance Conference, at Bentley University, in Waltham, MA, Tom Tullis (Fidelity Investments) gave a presentation on user research during the "UX Financial Research" session.
Presentation for Metadata Working Group at Cornell. Based on book chapter (with Diane Hillmann) in "Metadata in Practice". For some reason it has become unexpectedly citable.
PSY 540 Short Presentation Guidelines and Rubric Overvi.docxpotmanandrea
PSY 540 Short Presentation Guidelines and Rubric
Overview
Twice during this course you will assume the role of a psychology professional in an applied setting and apply theories to suggest solutions to contemporary
problems through a short presentation. The purpose of these presentations is to help you identify gaps in and propose improvements for professional disciplines
based on the strengths and limitations of human cognitive systems while assessing foundational theories of cognitive psychology for their relevance to real-world
issues.
Short presentations should be approximately five minutes in length and should be directed towards someone with limited or no background knowledge of
psychological concepts or terminology. Because of this, you will want to explain relevant terms and concepts as you work through your presentation. Be sure to
identify the group your presentation is intended for as well as the group that will most benefit from your proposed strategies. Additionally, be sure to
appropriately use professional terms and theories.
Your presentation can use a platform of your choosing. Potential example platforms include:
• PowerPoint
• Prezi
• Jing
• Webcam video recordings
For this assignment, you may submit a URL to your presentation or upload a video or PowerPoint presentation with either associated audio or the delivery script
included in the notes section. For additional information about uploading video files, reference the Uploading a Video Assignment guide. If you have difficulty
recording and submitting presentation files, reach out to the SNHU Help Desk for technical assistance at www.snhu.edu/techsupport and contact your instructor.
http://prezi.com/
http://www.techsmith.com/jing.html
https://my.snhu.edu/offices/its/is/resources/documents/uploading_a_video_assignment.pdf
http://www.snhu.edu/techsupport
Rubric
Instructor Feedback: This activity uses an integrated rubric in Blackboard. Students can view instructor feedback in the Grade Center. For more in formation,
review these instructions.
Critical Elements Proficient (100%) Needs Improvement (85%) Not Evident (0%) Value
Setting and Audience Cl earl y i denti fi es the s peci fi c appl ied s etti ng
and s peci fi c target audi ence for the
pres entati on
Identi fi es the appl i ed s etti ng and target
audi ence for the pres entati on, but the
s etti ng and audi ence l ack s peci fi c detai l
Does not i denti fy the appl i ed s etti ng and
target audi ence for the pres entati on
35
Theories Incl udes references to theori es to s upport
the pres entati on and di rectl y connects them
to the appl i ed s etti ng
Incl udes references to theori es to s upport
the pres entati on, but does not di rectl y
connect them to the appl i ed s etti ng, or
theori es are i ncorrectl y appl ied
Does not i ncl ude theori es to s upport the
pres entati on
20
Concepts and
Terminology
Expl ai ns co ...
Semantics empowered Physical-Cyber-Social Systems for EarthCubeAmit Sheth
Presentation at the EarthCube Face Face-to-Face Workshop of Semantics & Ontologies Workgroup: April 30-May 1, 2012, Ballston, VA.
Workshop site: http://earthcube.ning.com/group/semantics-and-ontologies/page/workshops
For more recent material on this topic, see: http://wiki.knoesis.org/index.php/PCS
Guest Lecture on Litigation Holds, Preservation, and Search Methodologies. If you want to download this rather than just view, please email me at sonya@sonyasigler.com
The emergence in recent years of initiatives like the Linked Open Data (LOD) has led to a significant increase in the amount of structured semantic data on the Web. In this paper we argue that the shareability and wider reuse of such data can very often be hampered by the existence of vagueness within it, as this makes the data’s meaning less explicit. Moreover, as a way to reduce this problem,
we propose a vagueness metaontology that may represent in an explicit way the nature and characteristics of vague elements within semantic data.
2013 3 27 TAR Webinar Part 4 Getting Started SiglerSonya Sigler
Getting started using technology assisted review can be difficult if lawyers aren't used to this type of technology. Part 4 of this webinar series provides in depth coverage on how to get started with TAR tools.
Part 5 in this series of webinars on Demystifying Technology Assisted Review covers Dispelling Myths and Offering Practice Tips. Sonya Sigler of SFL Data, Paige Hunt of Perkins Coie, and CHris Mammen of Hogan Lovells cover this topic in depth.
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...DanBrown980551
Do you want to learn how to model and simulate an electrical network from scratch in under an hour?
Then welcome to this PowSyBl workshop, hosted by Rte, the French Transmission System Operator (TSO)!
During the webinar, you will discover the PowSyBl ecosystem as well as handle and study an electrical network through an interactive Python notebook.
PowSyBl is an open source project hosted by LF Energy, which offers a comprehensive set of features for electrical grid modelling and simulation. Among other advanced features, PowSyBl provides:
- A fully editable and extendable library for grid component modelling;
- Visualization tools to display your network;
- Grid simulation tools, such as power flows, security analyses (with or without remedial actions) and sensitivity analyses;
The framework is mostly written in Java, with a Python binding so that Python developers can access PowSyBl functionalities as well.
What you will learn during the webinar:
- For beginners: discover PowSyBl's functionalities through a quick general presentation and the notebook, without needing any expert coding skills;
- For advanced developers: master the skills to efficiently apply PowSyBl functionalities to your real-world scenarios.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Clients don’t know what they don’t know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clients’ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
Connector Corner: Automate dynamic content and events by pushing a buttonDianaGray10
Here is something new! In our next Connector Corner webinar, we will demonstrate how you can use a single workflow to:
Create a campaign using Mailchimp with merge tags/fields
Send an interactive Slack channel message (using buttons)
Have the message received by managers and peers along with a test email for review
But there’s more:
In a second workflow supporting the same use case, you’ll see:
Your campaign sent to target colleagues for approval
If the “Approve” button is clicked, a Jira/Zendesk ticket is created for the marketing design team
But—if the “Reject” button is pushed, colleagues will be alerted via Slack message
Join us to learn more about this new, human-in-the-loop capability, brought to you by Integration Service connectors.
And...
Speakers:
Akshay Agnihotri, Product Manager
Charlie Greenberg, Host
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...James Anderson
Effective Application Security in Software Delivery lifecycle using Deployment Firewall and DBOM
The modern software delivery process (or the CI/CD process) includes many tools, distributed teams, open-source code, and cloud platforms. Constant focus on speed to release software to market, along with the traditional slow and manual security checks has caused gaps in continuous security as an important piece in the software supply chain. Today organizations feel more susceptible to external and internal cyber threats due to the vast attack surface in their applications supply chain and the lack of end-to-end governance and risk management.
The software team must secure its software delivery process to avoid vulnerability and security breaches. This needs to be achieved with existing tool chains and without extensive rework of the delivery processes. This talk will present strategies and techniques for providing visibility into the true risk of the existing vulnerabilities, preventing the introduction of security issues in the software, resolving vulnerabilities in production environments quickly, and capturing the deployment bill of materials (DBOM).
Speakers:
Bob Boule
Robert Boule is a technology enthusiast with PASSION for technology and making things work along with a knack for helping others understand how things work. He comes with around 20 years of solution engineering experience in application security, software continuous delivery, and SaaS platforms. He is known for his dynamic presentations in CI/CD and application security integrated in software delivery lifecycle.
Gopinath Rebala
Gopinath Rebala is the CTO of OpsMx, where he has overall responsibility for the machine learning and data processing architectures for Secure Software Delivery. Gopi also has a strong connection with our customers, leading design and architecture for strategic implementations. Gopi is a frequent speaker and well-known leader in continuous delivery and integrating security into software delivery.
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
As AI technology is pushing into IT I was wondering myself, as an “infrastructure container kubernetes guy”, how get this fancy AI technology get managed from an infrastructure operational view? Is it possible to apply our lovely cloud native principals as well? What benefit’s both technologies could bring to each other?
Let me take this questions and provide you a short journey through existing deployment models and use cases for AI software. On practical examples, we discuss what cloud/on-premise strategy we may need for applying it to our own infrastructure to get it to work from an enterprise perspective. I want to give an overview about infrastructure requirements and technologies, what could be beneficial or limiting your AI use cases in an enterprise environment. An interactive Demo will give you some insides, what approaches I got already working for real.
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualityInflectra
In this insightful webinar, Inflectra explores how artificial intelligence (AI) is transforming software development and testing. Discover how AI-powered tools are revolutionizing every stage of the software development lifecycle (SDLC), from design and prototyping to testing, deployment, and monitoring.
Learn about:
• The Future of Testing: How AI is shifting testing towards verification, analysis, and higher-level skills, while reducing repetitive tasks.
• Test Automation: How AI-powered test case generation, optimization, and self-healing tests are making testing more efficient and effective.
• Visual Testing: Explore the emerging capabilities of AI in visual testing and how it's set to revolutionize UI verification.
• Inflectra's AI Solutions: See demonstrations of Inflectra's cutting-edge AI tools like the ChatGPT plugin and Azure Open AI platform, designed to streamline your testing process.
Whether you're a developer, tester, or QA professional, this webinar will give you valuable insights into how AI is shaping the future of software delivery.
PHP Frameworks: I want to break free (IPC Berlin 2024)Ralf Eggert
In this presentation, we examine the challenges and limitations of relying too heavily on PHP frameworks in web development. We discuss the history of PHP and its frameworks to understand how this dependence has evolved. The focus will be on providing concrete tips and strategies to reduce reliance on these frameworks, based on real-world examples and practical considerations. The goal is to equip developers with the skills and knowledge to create more flexible and future-proof web applications. We'll explore the importance of maintaining autonomy in a rapidly changing tech landscape and how to make informed decisions in PHP development.
This talk is aimed at encouraging a more independent approach to using PHP frameworks, moving towards a more flexible and future-proof approach to PHP development.
GraphRAG is All You need? LLM & Knowledge GraphGuy Korland
Guy Korland, CEO and Co-founder of FalkorDB, will review two articles on the integration of language models with knowledge graphs.
1. Unifying Large Language Models and Knowledge Graphs: A Roadmap.
https://arxiv.org/abs/2306.08302
2. Microsoft Research's GraphRAG paper and a review paper on various uses of knowledge graphs:
https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
SF Women in eDiscovery Sept 2011
1. Getting to a Manageable Review Set
Intake
Focus on finding,
Duplicates
Data 25% reviewing & using the
100%
“right” data,
Junk/Spam/
Porn not just filtering data
20%
NR/Priv
20%
Non-
Responsive
20%
Responsive Produced
& Priv 15% 12.25%
These figures vary based upon the data set received
12/5/2011 1
2. Review risks
Failure to collect the right data
Failure to find responsive documents
Failure to recognize responsive documents
Failure to recognize privileged documents
Inconsistent treatment of documents (e.g.,
duplicates)
Failure to complete project in a timely manner
Sophisticated Tools
– Understand What They Do and Don’t Do Well
– Inform Yourself, Speak to References, Consultants
12/5/2011 2
3. Search Methodologies
Visualization
Measurement
Relationship
Analysis
documents with
causal or
sequential relationship
Context
Social Network Analysis
relationships among relevant people
relationships among relevant people
Clustering
Clustering Ontology
Ontology
Concept similarity of
similarity of generalized
generalized
salient features
salient features words or phrases
words or phrases
specific exact words,
Content Keyword
Keyword specific exact words
specific exact words
proximity searches, stemming
12/5/2011 3
4. Myth
Keyword Searching is the Way to Go
If I agree to keyword terms, I am OK
Missing in Action (Under-inclusive)
Unwanted Extras (Over-inclusive)
Multiple subject/persons (Disambiguate)
Reality: Keyword Search is one tool among many!
12/5/2011 4
5. "simple keyword searches end
up being both over- and under-
inclusive."
Judge Paul Grimm, Victor Stanley, Inc. v. Creative Pipe, Inc., No. MJG-06-2662, 2008 U.S. Dist. LEXIS 42025
(D. Md. May 29, 2008).
Keyword culling
6. Keyword Accuracy Example
Keyword search reduced the
document set by only 47%
And 88% of the documents
returned by keyword
search were not responsive
(Over-inclusive)
8,553 responsive documents
missed by keyword search
(Almost 8% of responsive
documents missed by
keyword search - Under-inclusive)
12/5/2011 6
7. Under Inclusive - Missing in Action
Missing abbreviations / acronyms / clippings:
– incentive stock option but not ISO
Missing inflectional variants:
– grant but not grants, granted, granting
Missing spellings or common misspellings:
– gray but not grey
– privileged but not priviliged, priviledged, privilidged,
priveliged, privelidged, priveledged, …
Missing syntactic variants:
• board of directors meetingbut not meeting of the board of
directors, BOD meeting, board meeting, BOD mtg…
Missing Synonyms/Paraphrases:
• Hire date but not start date
12/5/2011 7
8. Over-Inclusive - Unwanted Extras (a)
Options
Target: Sheila was granted 100,000 options at $10
Match: What are our options for lunch?
Match in a signature line:
Amanda Wacz
Acme Stock Options Administrator
Destroy
Target:destroyevidence
Match in a disclaimer: The information in this email, and any
attachments, may contain confidential and/or privileged
information and is intended solely for the use of the named
recipient(s). Any disclosure or dissemination in whatever form, by
anyone other than the recipient is strictly prohibited. If you have
received this transmission in error, please contact the sender
and destroy this message and any attachments. Thank you.
12/5/2011 8
9. Over-Inclusive - Unwanted Extras (b)
alter*
Target: alter, alters, altered, altering
Matches: alternate, alternative, alternation, altercate,
altercation, alterably, …
grant
Target:stock optiongrant
Matches names:Grant Woods, Howard Grant
12/5/2011 9
10. Failure to Disambiguate
Words that Relate to Multiple Subjects
Example: refund is used to refer to:
– FERC-ordered refunds owed by Enron for
overcharging
– Tax refunds (both corporate and personal)
– Mundane business matters
In a given matter, one might be of interest
while the others are not
12/5/2011 10
11. Technology Enhanced Review:
Speed, Predictable Costs, and Accuracy
Automate any portion of the review
Source Eliminate
Data Duplicates &
System Files
100% Non-Responsive
30% Isolation Example from a real case
ontologies
NR by
30% Technology Responsive
Enhanced by Technology
Review Enhanced
(removed Review Priv by
another 18%) (removed High-Speed
another 7%) Manual Review
22% 3%
15%
12/5/2011 11
12. Example: “priv” ontology
Valuable, re-usable work product
Combines classifiers into concepts,
into bigger concepts
12/5/2011 12
13. Disclaimer Detection
Disclaimers can throw
off attempts to detect
privileged
communications
Prevalent throughout
many companies,
even on trivial
communications
Detect them
automatically, and
exclude them from
searches
12/5/2011 13
14. Privileged by Actor Only
Responsive Privileged by Actor and Term
D omain of D isclaimer
D etection
Privileged by Term Only
Privileged by
D isclaimer Only
12/5/2011 14
15. Priv Logs
Expensive - But Do NOT Have to Be
In re Vioxx Products Liability Litigation (E.D. La 2007)
Merck’s Priv Log had 30,000 items on it
– How to Make a Judge Angry
– How to Waste Client Money
– How to Attract Sanctions
12/5/2011 15
16. Transparency of Process
Discussing Review Protocols
– Provide transparent, defensible, sophisticated search
based on document content
– Clustering, Ontologies, Analytics, and yes, sometimes
Keywords too
Develop search methodologies for each case
– Use technology experts in consultation with case / legal
experts
Results verifiable by Quality Control
– Defensible sampling
Sophisticated Tools
– Understand What They Do and Don’t Do Well
– Inform Yourself, Speak to References, Consultants
12/5/2011 16
17. Blair &Maron:
Keyword search is incomplete
What the lawyers thought
100%
they were finding
90%
Responsive documents
80%
70%
60%
50%
What they
40% actually found
30%
20%
10%
0%
Predicted Obtained
Blair and Maron, Communications of the ACM, 28, 1985, 289-299
18. Blair and Maron
“It is impossibly difficult for users to
predict the exact words, word
combinations, and phrases that are
used by all (or most) relevant
documents and only (or primarily) by
those documents.”
Blair & Maron Study: 20% recall
Lawyers picked 3 key terms,
B & M found 26 more
Defense: “Unfortunate incident”
Plaintiff: “Disaster”
Blair and Maron, Communications of the ACM, 28, 1985, 289-299
20. Document categorization in Legal Discovery:
Computer Classification vs. Manual Review
Herbert L. Roitblat, Anne Kershaw, & Patrick Oot
21. 1
0.95
0.9
Agreement with original
0.85
0.8
0.75
0.7
0.65
0.6
0.55
0.5
Team A Team B System C System D
Manual Computer
review classification 2010, JASIST
Roitblat, Kershaw, &Oot,
24. Substantial disagreement between
Team A & Team B
28%
629 580 858
A
Both
B
0 500 1000 1500 2000
Responsive Documents
Roitblat, Kershaw, &Oot, 2010, JASIST
25. Conclusion
The computer systems yielded comparable level of
performance relative to manual review
Fewer people, less time, less cost
Measure performance to evaluate
26. Will lawyers lose control?
Computer system amplifies the
intelligence of the Expert
30. Setup
Sample
Responsive Non-
Expert judges responsive
sample
Repeat as needed
Model learns
Model
predicts
Responsive Non-responsive
Model categorizes all remaining
documents
31. Predictive coding achieves much higher
accuracy (Jaccard)
Team A Only Team A and Team B Team B
0.304 0.281 0.415
Humans Humans and Predictive Coding Predictive Coding
0.186 0.688 0.126
Responsive Documents
Data from Roitblat, et al. and an Internal OrcaTec Case Study
32. Why doesn’t everyone use it?
• Attorneys don’t understand the
technology
• May not be aware of the accuracy data
• May not understand how to fit into their
work flow
• Not in everyone’s economic interest
• Acceptable to judges?
33. Defensible?
Measure TREC Roitblat, e Roitblat Predictiv
2008 t al. Team et al. e
A Team B Coding*
Precision 0.210 0.197 0.183 0.899
Recall 0.555 0.488 0.539 0.873
*OrcaTec internal Result
Keyword and Boolean selection / searching yielded only 20% of the responsive documents.
OrcaTec’s performance compares very favorably to similar measures observed using teams of human reviewers and other predictive coding systems. In the TREC 2008 ad hoc task, the highest recall achieved by a system was 0.555 (i.e., 55.5% of the documents identified as relevant were retrieved; Run “wat7fuse”). The precision corresponding to that level of recall was 0.210, meaning that 21% of the retrieved documents were determined to be relevant.Roitblat, Kershaw, and Oot measured precision and recall for two human teams. Team A yielded precision of 0.197 and recall of 0.488. Team B yielded precision of 0.183 and recall of 0.539.