Group items tagged

When your readers search for information in real life, their first step is to typically seek out a friend for the answer. If their friend doesn't have the answer they need, someone in that friend's social network may. Eventually, they get an answer they trust, because it came from a source they trust. Your readers can now have that same experience on the web and it all starts with the source they trust. That source is you, the blog publisher.

OpenEphyra is an open framework for question answering (QA). It retrieves answers to natural language questions from the Web and other sources. Visit http://www.ephyra.info/ for more details and information on joining this open research initiative.

The True Knowledge answer engine is a technology capable of answering questions put to it on any topic. If you would like to take it for a spin you can login (or apply for a beta account if you haven't done so already) using the box to the right.

I've been running Simpy for almost 4 years now. Every once in a while I get the "Why should I use Simpy?", "Why is Simpy better than, say, del.icio.us?" This post answers those questions in the form of "Why I use Simpy" answer. This are my personal reasons for using Simpy, but you can also read other people's opinions. I also encourage you to add your reasons in the comments, so I can add your reasons to this list.

A small, digital book startup thinks it has a solution to the age-old student lament: overpriced textbooks that have little value when the course is over. The answer? Make them open source -- and give them away.

Once students have gathered information on a topic, it is important that they reflect on whether the information they have gathered is sufficient to answer the research question. This requires students to make sense of the information they have gathered-to synthesize the information into new knowledge. In order to address the different leaning modalities that students possess, teachers should have students use a variety of forms of representation for this sensemaking stage (see Forms of Representation matrix).

Sensemaking is a process designed to enable groups of people to see patterns that were once hidden to them and develop a common understanding of what is required to address an issue. While the sensemaking (and subsequent intervention design) process will result in the production of artefacts (reports, lists of action items, descriptions of the current situation etc) much of the value is derived through participation in the process. It is not a process where you say 'make sense of this and tell me the answer'. Much of the benefit comes from determining 'what it means' for yourself. Sensemaking is beneficial at an individual level as our values and assumptions are tested and either confirmed or found wanting.

The Sematic Web Client Library represents the complete Semantic Web as a single RDF graph. The library enables applications to query this global graph using SPARQL- and find(SPO) queries. To answer queries, the library dynamically retrieves information from the Semantic Web by dereferencing HTTP URIs and by following rdfs:seeAlso links. The library is written in Java and is based on the Jena framework.

The prototype we describe is a biomedical knowledge base, constructed for a demonstration at Banff WWW2007 , that integrates 15 distinct data sources using currently available Semantic Web technologies such as the W3C standard Web Ontology Language [OWL] and Resource Description Framework [RDF]. This report outlines which resources were integrated, how the knowledge base was constructed using free and open source triple store technology, how it can be queried using the W3C Recommended RDF query language SPARQL [SPARQL], and what resources and inferences are involved in answering complex queries. While the utility of the knowledge base is illustrated by identifying a set of genes involved in Alzheimer's Disease, the approach described here can be applied to any use case that integrates data from multiple domains.

"Cyber English is a pedagogical experiment in practical theory in developing an alternative option to tradition education and a project to answer the various voices of America for better educational practice"

MindCanvas is a research service to help companies gather insights about customers' thoughts & feelings. We use Game-like Elicitation Methods (GEMs) to let online users participate in answering the complex questions that you face in designing a product or service.

I want a page, a site, a thing that is created, curated, edited, and discussed. It's a blog that treats a topic as an ongoing and cumulative process of learning, digging, correcting, asking, answering. It's also a wiki that keeps a snapshot of the latest knowledge and background. It's an aggregator that provides annotated links to experts, coverage, opinion, perspective, source material. It's a discussion that doesn't just blather but that tries to accomplish something (an extension of an article like this one that asks what options there are to bailout a bailout). It's collaborative and distributed and open but organized.

I was listening to Melvyn Bragg's radio program, In Our Time , this morning on my iPod. The topic was Albert Camus. In discussing his novel, The Stranger, one of the distinguished panellists felt that Camus was suggesting that meaning is not pre-inscribed in the world around us and we are continuously seeking meaning in an inherently meaningless world. I almost toppled off the step machine. Do we live in an inherently meaningless world? On first thought I think the answer is yes. The onus is on us to make sense of our world. By the way, Melvyn's podcast is a joy. I particularly like its eclectic nature. Today it's Camus, last week The Four Humours, and before that we had The Sassanian Empire, Discovery of Oxygen, Mutation and The Fibonacci Series.

Online study group community Cramster announced today that the company has raised a $3 million investment and after checking out the site, we can see why. This active, full featured and well design service looks really compelling for students and has a solid business model. Members can participate in forums about homework, get quick answers to questions 24 hours a day and access explanations of problems from more than 200 of the most popular text books in 7 subject areas. There are free and paid membership levels at $10 per month and users deemed helpful by others can receive financial rewards like gift certificates.

Our goal in creating this site is to provide the basis for a thriving community of UIMA developers who can announce, discuss, design, share, and critique UIMA-compliant components, resources and solutions. The Unstructured Information Management Architecture (UIMA) is a software framework that supports rapid development and deployment of multimodal analytics - applications which provide value by processing human-readable text, audio and/or video in order to extract information, answer questions, summarize documents, etc.

The YAGO-NAGA project started in 2006 with the goal of building a conveniently searchable, large-scale, highly accurate knowledge base of common facts in a machine-processible representation. We have already harvested knowledge about millions of entities and facts about their relationships, from Wikipedia and WordNet with careful integration of these two sources. The resulting knowledge base, coined YAGO, has very high precision and is freely available. The facts are represented as RDF triples, and we have developed methods and prototype systems for querying, ranking, and exploring knowledge. Our search engine NAGA provides ranked answers to queries based on statistical models.

Swingly is a new type of semantic search engine designed to help you find answers to questions - wherever they can be found on the Internet.

Mustru is a desktop search engine written in Java using Lucene, Lingpipe, and the Berkeley DB . Create an index from a set of directories on your local filesystem and use the Web based interface to query the index. Submit questions in natural language or boolean queries using keywords.

Today I finally plugged-in the Yahoo Boss Mashup Framework into the Google App Engine environment. Google App Engine (GAE) provides a pretty sweet yet simple platform for executing Python applications on Google's infrastructure. The Boss Mashup Framework (BMF) provides Python API's for accessing Yahoo's Search API's as well remixing data a la SQL constructs. Running BMF on top of GAE is a seemingly natural progression, and quite arguably the easiest way to deploy Boss - so I spent today porting BMF to the GAE platform. See also http://bossy.appspot.com/qa?query=who+is+brad+pitt+married+to