
	Where results make sense

Topic: Question answering

Related Topics

Search engine

Natural language processing

Behistun Inscription

Cocaine

White Star Line

Poet Laureate

In the News (Mon 28 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Question-Answering Using Semantic Relation Triples
		Question phraseology not envisioned during the prototype development (principally questions beginning with "why" or non-questions beginning with "name the...") were assigned to the what category, so that question elements would be present for each question.
		When a document containing the answer was added to the database, correct answers were identified in two-thirds of the cases, with an average inverse rank of 0.320, adding 0.153 to the overall score.
		For questions with correct answers, the scores were tabulated by the number of database records generated by the questions (which ranged from 2 to 10, with an average of 4.4 records).
	www.clres.com /trec8.html (4742 words)

	Question answering - Wikipedia, the free encyclopedia
		If the answer to a question is not present in the data sources, no matter how well we perform question processing, retrieval and extraction of the answer, we shall not obtain a correct result.
		Answer extraction depends on the complexity of the question, on the answer type provided by question processing, on the actual data where the answer is searched, on the search method and on the question focus and context.
		It had a very rudimentary way to answer questions, and on its own it lead to a series of chatterbots such as the ones that participate in the annual Loebner prize.
	en.wikipedia.org /wiki/Question_answering (2066 words)

	Text REtrieval Conference (TREC) QA Data
		TREC has had a question answering track since 1999; in each track the task was defined such that the systems were to retrieve small snippets of text that contained an answer for open-domain, closed-class questions (i.e., fact-based, short-answer questions that can be drawn from any domain).
		For question answering, the unit that is judged is the entire string that is returned by the system.
		Different QA runs very seldom return exactly the same answer strings, and it is very difficult to determine automatically whether the difference between a new string and a judged string is significant with respect to the correctness of the answer.
	trec.nist.gov /data/qa.html (810 words)

	Syntactic Clues and Lexical Resources in Question-Answering
		Questions containing the phrase "who was the author" were converted into "who wrote"; in those with "what is the name of", the triple for "name" was removed so that the words in the "of" phrase would be identified as the principal noun.
		Where Questions - Each sentence was examined for the presence of "in", "at", "on", "of", or "from" as a semantic relation, or the presence of a capitalized word (not present in the question) modifying the key noun.
		If the answer also occurred in a triple as a governing word with a HAS relation, the discourse entity from that triple was inserted into the answer as a genitive determiner of the answer.
	www.clres.com /trec9.html (6911 words)

	CNLP Technology - Question Answering
		Question Answering (QA) provides more precise responses to users' queries than Information Retrieval, which provides users a list of and links to, relevance-ranked documents in response to a query.
		During query processing, the system converts the question into a logical query representation used for first stage access into the document collection, as well as expanding the query to its semantic equivalents, and determining the focus of the query.
		Answer finding in sources combines two different approaches - keyword & NLP-based inferencing, after which answer triangulation takes place to select the most likely answer, given the system's detailed understanding of the user's question.
	www.cnlp.org /tech/question.asp (213 words)

	Learning Search Engine Specific Query Transformations for Question Answering
		Questions are classified into one of a set of known ``question types'' that identify the type of entity corresponding to the answer.
		To answer a natural language question, a promising approach is to automatically reformulate the question into a query that contains terms and phrases that are expected to appear in documents containing answers to the original question.
		These are the most common types of questions found in the Excite log, and have been estimated to account for more than 90% of natural language questions submitted to the search engine [20].
	www10.org /cdrom/papers/348 (7661 words)

	New Directions in Question Answering - The MIT Press
		Question answering systems, which provide natural language responses to natural language queries, are the subject of rapidly advancing research encompassing both academic study and commercial applications, the most well-known of which is the search engine Ask Jeeves.
		Question answering creates an important new method of information access and can be seen as the natural step beyond such standard Web search methods as keyword query and document retrieval.
		These include current methods, architecture requirements, and the history of question answering on the Web; the development of systems to address new types of questions; interactivity, which is often required for clarification of questions or answers; reuse of answers; advanced methods; and knowledge representation and reasoning used to support question answering.
	mitpress.mit.edu /catalog/item/default.asp?tid=10345&ttype=2 (292 words)

	Question Answering (Site not responding. Last check: 2007-11-04)
		So for example, if a reader is looking at a question on a very specific topic, then it is assumed that the reader has also looked at the more general questions first.
		When a question is posted, the system first looks in the knowledgebase of previously asked question to see if an answer can be obtained there.
		Each would have questions and answer sessions, and also dialogues that can be viewed by members of the community, in the spirit of newsgroups.
	www.cs.ucl.ac.uk /staff/a.hunter/tradepress/qa.html (1469 words)

	Answering Interview Question
		In this case, the standard textbook answer for the "greatest weakness" question is to give a veiled positive--"I work too much.
		Answer the questions behaviorally, with specific examples that show clear evidence backs up what you are saying about yourself.
		You are welcome to browse this material as a visitor of our site, but please do not violate the copyright by making copies of this material, either electronic, paper or any other type, with the exception of one paper copy of each page permitted for your own personal use and reference.
	www.collegegrad.com /interview/answeringinterviewquestion.shtml (1512 words)

	Scaling Question Answering to the Web
		These candidates are given to the answer selector (section 3.6) for scoring and ranking; the sorted list of answers (presented in the context of their respective summaries) is displayed to the user.
		The answers for temporal and wh-adverb (when, where) queries are likely to occur inside prepositional phrases, so we raise the score for answers that occur under a prepositional phrase.
		Question classification methods analyze a question in order to determine what type of information is being requested so that the system may better recognize an answer.
	www10.org /cdrom/papers/120/index.html (7806 words)

	Zhiping Zheng: Developing a Web-based Question Answering System
		If the question language is not English, The module will send the original question and language information to AltaVista's translation tool BabelFish, and obtain the question that has been translated into English.
		TREC 8's 200 questions were used to evaluate AnswerBus's question answering performance and also compare its performance to that of four other similar systems.
		It provides the numbers of correct answers in the systems' top five and top one answers, the standard NIST scores, the maximal, minimal and average response times measured in seconds, standard deviation of response times, and the average lengths of returned answers.
	www2002.org /CDROM/poster/203 (1370 words)

	Language Computer - Question Answering
		Casual questioneers who ask simple factual questions; employees who need quick answers on company procedures or benefits; consumers who look for specific product features or prices; research analysts who collect specific information about the market; children doing research for homework; will all benefit from free, open searches.
		Open-domain Question Answering is a complex task that encompasses many natural language processing, information retrieval, and artificial intelligence techniques.
		The inherent difficulties in finding answers to open-domain questions pose serious technical challenges, and, as our awards history shows, we not only identified these challenges, but we were also recognized for solving them in the best way.
	www.languagecomputer.com /technology/question_answering (395 words)

	LREC 2002 Workshop
		The primary purpose of this workshop will be to refine a roadmap (www-nlpir.nist.gov/projects/duc/papers/ qa.Roadmap-paper_v2.doc) for question answering applications and the methods for the creation and evaluation of resources for the next decade in support of these systems.
		The workshop will be a mix of short presentations and facilitated sessions with the intent of joint articulation of grand challenge problems and identification of a strategy for facilitating the creation of question answering resources and evaluation strategies.
		The agenda will consist of two working sessions, the first focused on the creation of a question answering roadmap and the second addressing resources required to achieve milestones on the roadmap.
	www.lrec-conf.org /lrec2002/lrec/wksh/QuestionAnswering.html (843 words)

	Language Computer - Question Answering
		Recent developments in enterprise knowledge management have made it clear that novel and sophisticated methods of automatically answering natural language questions are at the core of managing and exploiting information inside and outside the enterprise, within and across industries.
		Question Answering systems (QA) operate on heterogeneous data, providing information captured in meetings or presentations, from enterprise databases, textual documents or email/phone communications.
		Our Question Answering systems can be easily integrated with various knowledge management and portal resources to work within different business domains, such as business intelligence, expertise locator, online automated technical support.
	www.languagecomputer.com /solutions/question_answering (193 words)

	A Question Answering System Supported by Information Extraction - Srihari, Li (ResearchIndex)
		It shows: (i) Named Entity tagging is an important component for QA, (ii) an NL shallow parser provides a structural basis for questions, and (iii) high-level domain independent IE can result in a QA breakthrough.
		has often categorized questions by question word alone or by a mixture of question word and the semantic class of the answer
		answering has categorized questions by question word or by a mixture of question word and the semantic class of the answer
	citeseer.ist.psu.edu /srihari00question.html (423 words)

	National Question Answering Service — NHS Connecting for Health (Site not responding. Last check: 2007-11-04)
		Evidence shows that prompt answers to clinical questions related to individual patients provide an effective and efficient method of education and professional development.
		Answers to frequently asked questions, based on current knowledge, can be delivered by individual consultants and, when sufficiently based not only on evidence but also on experience, incorporated in the Map of Medicine and in laboratory and imaging request forms.
		The need for individual consultants to be personally involved and relate to nurses and general practitioners in primary care will be systematically evaluated in a small number of specialties, and a project board will be set up, working through the NHS Confederation and the Royal College of Physicians' Informatics Unit.
	www.connectingforhealth.nhs.uk /delivery/serviceimplementation/nks/nqas (403 words)

	What is the best management of male orgasm related headache? : NLH Question Answering Service
		If this is the first visit to the site we recommend you read "About the NLH Question Answering Service".
		A 2002 copy of GP (18th March) answered the question “Can a headache which comes on near orgasm be the marker of a serious neurological condition?”
		The NLH Question Answering Service aims to answer questions quickly, it is not a systematic review.
	www.clinicalanswers.nhs.uk /index.cfm?question=480 (863 words)

	Language Computer - Question Answering
		Internet Answer - A new way to search the Internet, where free questions are powered by concise answers.
		News Answer - A new way to search for daily news, where free questions bring direct answers, for even fresher news.
		Archive Answer - A new way to benefit from archived information, where free questions find clear answers.
	www.languagecomputer.com /demos/question_answering/index.html (154 words)

	QASTIIR - Question Answering System Through Intelligent Information Retrieval
		The statistical component is an IR system (SIRS), based on the well known SMART system ([Salton]) and responsible for handling the large text corpora and fast retrieval of documents, their paragraphs and sentences containing the query terms in high frequencies.
		The final outcome of the processing is a semantic representation of the query together with semantic representations of all of the answer candidates retrieved earlier by SIRS.
		Integrating Statistical and Linguistic Approaches in Building Intelligent Question Answering Systems”, presented at SSGRR Winter 2002 International Conference on Advances in Infrastructure for e-Business, e-Education, e-Science, and e-Medicine on the Internet (in L’Aquilla, Italy).
	www.tcnj.edu /~mmmartin/QASTIIR.html (2374 words)

	University of Canberra : Academic Skills Program : Answering the Question
		You might hand in an intelligent, beautifully-written, beautifully-presented assignment, by the due date; but if it doesn’t answer the question, it will fail.
		You do this by analysing the question, by noting special instructions, and by keeping to the word limit.
		Once you have isolated the limiting words in your assignment question, you can direct your reading and note-taking to that topic only, thus saving yourself a lot of time.
	www.canberra.edu.au /studyskills/writing/answering (863 words)

	Steven Winikoff: Question Answering Links
		The general idea is to be able to answer questions written in English, by finding the answer in a collection of documents (which may be web pages or plain text).
		This is commonly done by examining words in the question (for example, "who is" suggests that the answer will be a name, "how many" suggests that it will be a number, etc.).
		This has the disadvantage of being less general than open-domain systems, which can answer questions on any topic at all; on the other hand, it also allows the exploitation of a priori knowledge about the given domain, hopefully leading to better performance within that domain.
	alcor.concordia.ca /~smw/home/qa.html (956 words)

	Special Topics : Question Answering Systems
		A goal is the construction of systems, which can identify the answers to a natural-language question from a large quantity of on-line text documents.
		In contrast to information retrieval systems which supply a quantity of documents as a result of a simple, word-based search, QA systems are capable of identifying the exact passages in the text of relevant documents which represent the concrete answer.
		In addition, there are no restrictions concerning the subject of the natural-language questions.
	www.tcnj.edu /~mmmartin/CMSC485/CMSC485.html (367 words)

	The START Natural Language System (Site not responding. Last check: 2007-11-04)
		The START Natural Language System is a software system designed to answer questions that are posed to it in natural language.
		START parses incoming questions, matches the queries created from the parse trees against its knowledge base and presents the appropriate information segments to the user.
		START was first connected to the World Wide Web in December, 1993, and in its several forms has to date answered millions of questions from users around the world.
	www.ai.mit.edu /projects/infolab/start-system.html (292 words)

	VISL - Question Answering
		We believe, however, that rule based or hybrid methods may go further than statistical methods alone, and that there is a need for language-specific systems in the area.
		Experimentally, VISL-style grammatical analysis has thus been used for both the identification of question patterns and the mark-up of source data for searching, using Constraint Grammar parsers like PALAVRAS (Portuguese) or DanGram (Danish).
		Currently, an academic pilote project for Portuguese is under way, while a Danish system is being developed commercially by Aminova Dialogue Systems and GrammarSoft.
	visl.sdu.dk /QA.html (148 words)

	Open-Domain Question Answering on the World Wide Web
		There is a list of questions and answers, e.g.
		For some questions, the answer is far less likely to be found in the same wordings:
		For some questions, our collection might contain thousands of documents containing the answer, for others, it might only contain one (or none).
	tcc.itc.it /research/textec/topics/question-answering/Tut-Bucholtz.html (825 words)

	The START Natural Language Question Answering System
		START, the world's first Web-based question answering system, has been on-line and continuously operating since December, 1993.
		Currently, the system can answer millions of English questions about places (e.g., cities, countries, lakes, coordinates, weather, maps, demographics, political and economic systems), movies (e.g., titles, actors, directors), people (e.g., birth dates, biographies), dictionary definitions, and much, much more.
		Below is a list of some of the things START knows about, with example questions.
	www.ai.mit.edu /projects/infolab (230 words)

	Multilingual Question Answering at CLEF (Site not responding. Last check: 2007-11-04)
		Question Answering (QA) systems are of great interest to the Language Engineering community because they combine Information Retrieval and Natural Language Processing within the same task.
		QA systems receive natural language queries (and not keywords) as input, process large unstructured document collections, and return precise answers (and not documents) as output.
		The NIST TREC QA tracks (this year is the seventh round) have stimulated progress in QA state-of-the-art, establishing widely accepted and standardized evaluation measures and requirements.
	clef-qa.itc.it (157 words)

Try your search on: Qwika (all wikis)