-
Radev, D.; Fan, W.; Qu, H.; Wu, H.; Grewal, A.: Probabilistic question answering on the Web (2005)
0.01
0.011304739 = product of:
0.056523696 = sum of:
0.056523696 = weight(_text_:web in 3455) [ClassicSimilarity], result of:
0.056523696 = score(doc=3455,freq=6.0), product of:
0.1508442 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046221454 = queryNorm
0.37471575 = fieldWeight in 3455, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046875 = fieldNorm(doc=3455)
0.2 = coord(1/5)
- Abstract
- Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage extraction, phrase extraction, and answer ranking. In this article, we describe some probabilistic approaches to the last three of these stages. We show how our techniques apply to a number of existing search engines, and we also present results contrasting three different methods for question answering. Our algorithm, probabilistic phrase reranking (PPR), uses proximity and question type features and achieves a total reciprocal document rank of .20 an the TREC8 corpus. Our techniques have been implemented as a Web-accessible system, called NSIR.
-
Jensen, N.: Evaluierung von mehrsprachigem Web-Retrieval : Experimente mit dem EuroGOV-Korpus im Rahmen des Cross Language Evaluation Forum (CLEF) (2006)
0.01
0.011304739 = product of:
0.056523696 = sum of:
0.056523696 = weight(_text_:web in 5964) [ClassicSimilarity], result of:
0.056523696 = score(doc=5964,freq=6.0), product of:
0.1508442 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046221454 = queryNorm
0.37471575 = fieldWeight in 5964, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046875 = fieldNorm(doc=5964)
0.2 = coord(1/5)
- Abstract
- Der vorliegende Artikel beschreibt die Experimente der Universität Hildesheim im Rahmen des ersten Web Track der CLEF-Initiative (WebCLEF) im Jahr 2005. Bei der Teilnahme konnten Erfahrungen mit einem multilingualen Web-Korpus (EuroGOV) bei der Vorverarbeitung, der Topic- bzw. Query-Entwicklung, bei sprachunabhängigen Indexierungsmethoden und multilingualen Retrieval-Strategien gesammelt werden. Aufgrund des großen Um-fangs des Korpus und der zeitlichen Einschränkungen wurden multilinguale Indizes aufgebaut. Der Artikel beschreibt die Vorgehensweise bei der Teilnahme der Universität Hildesheim und die Ergebnisse der offiziell eingereichten sowie weiterer Experimente. Für den Multilingual Task konnte das beste Ergebnis in CLEF erzielt werden.
-
Kruschwitz, U.; AI-Bakour, H.: Users want more sophisticated search assistants : results of a task-based evaluation (2005)
0.01
0.005438995 = product of:
0.027194975 = sum of:
0.027194975 = weight(_text_:web in 4575) [ClassicSimilarity], result of:
0.027194975 = score(doc=4575,freq=2.0), product of:
0.1508442 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046221454 = queryNorm
0.18028519 = fieldWeight in 4575, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0390625 = fieldNorm(doc=4575)
0.2 = coord(1/5)
- Abstract
- The Web provides a massive knowledge source, as do intranets and other electronic document collections. However, much of that knowledge is encoded implicitly and cannot be applied directly without processing into some more appropriate structures. Searching, browsing, question answering, for example, could all benefit from domain-specific knowledge contained in the documents, and in applications such as simple search we do not actually need very "deep" knowledge structures such as ontologies, but we can get a long way with a model of the domain that consists of term hierarchies. We combine domain knowledge automatically acquired by exploiting the documents' markup structure with knowledge extracted an the fly to assist a user with ad hoc search requests. Such a search system can suggest query modification options derived from the actual data and thus guide a user through the space of documents. This article gives a detailed account of a task-based evaluation that compares a search system that uses the outlined domain knowledge with a standard search system. We found that users do use the query modification suggestions proposed by the system. The main conclusion we can draw from this evaluation, however, is that users prefer a system that can suggest query modifications over a standard search engine, which simply presents a ranked list of documents. Most interestingly, we observe this user preference despite the fact that the baseline system even performs slightly better under certain criteria.
-
Srihari, R.K.: Using speech input for image interpretation, annotation, and retrieval (1997)
0.00
0.0037574214 = product of:
0.018787106 = sum of:
0.018787106 = product of:
0.037574213 = sum of:
0.037574213 = weight(_text_:22 in 764) [ClassicSimilarity], result of:
0.037574213 = score(doc=764,freq=2.0), product of:
0.16185966 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.046221454 = queryNorm
0.23214069 = fieldWeight in 764, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.046875 = fieldNorm(doc=764)
0.5 = coord(1/2)
0.2 = coord(1/5)
- Date
- 22. 9.1997 19:16:05
-
Lange, H.R.: Speech synthesis and speech recognition : tomorrow's human-computer interface? (1993)
0.00
0.0033253485 = product of:
0.016626742 = sum of:
0.016626742 = product of:
0.033253483 = sum of:
0.033253483 = weight(_text_:research in 7224) [ClassicSimilarity], result of:
0.033253483 = score(doc=7224,freq=2.0), product of:
0.13186905 = queryWeight, product of:
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.046221454 = queryNorm
0.2521705 = fieldWeight in 7224, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.0625 = fieldNorm(doc=7224)
0.5 = coord(1/2)
0.2 = coord(1/5)
- Abstract
- State of the art review of techniques which employ speech as the human-computer interface focusing on current research, implementation and potential for 2 of the speech technologies: speech synthesis, or speech output from the computer; and speech recognition, or speech input to the computer. Provides an introduction to the subject, discusses speech synthesis and speech recognition, examines library applications and looks to future use and development of these technologies
-
Lin, J.; Katz, B.: Building a reusable test collection for question answering (2006)
0.00
0.0024940113 = product of:
0.012470056 = sum of:
0.012470056 = product of:
0.024940113 = sum of:
0.024940113 = weight(_text_:research in 5045) [ClassicSimilarity], result of:
0.024940113 = score(doc=5045,freq=2.0), product of:
0.13186905 = queryWeight, product of:
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.046221454 = queryNorm
0.18912788 = fieldWeight in 5045, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.046875 = fieldNorm(doc=5045)
0.5 = coord(1/2)
0.2 = coord(1/5)
- Abstract
- In contrast to traditional information retrieval systems, which return ranked lists of documents that users must manually browse through, a question answering system attempts to directly answer natural language questions posed by the user. Although such systems possess language-processing capabilities, they still rely on traditional document retrieval techniques to generate an initial candidate set of documents. In this article, the authors argue that document retrieval for question answering represents a task different from retrieving documents in response to more general retrospective information needs. Thus, to guide future system development, specialized question answering test collections must be constructed. They show that the current evaluation resources have major shortcomings; to remedy the situation, they have manually created a small, reusable question answering test collection for research purposes. In this article they describe their methodology for building this test collection and discuss issues they encountered regarding the notion of "answer correctness."
-
Wittbrock, M.J.; Hauptmann, A.G.: Speech recognition for a digital video library (1998)
0.00
0.002078343 = product of:
0.010391714 = sum of:
0.010391714 = product of:
0.020783428 = sum of:
0.020783428 = weight(_text_:research in 873) [ClassicSimilarity], result of:
0.020783428 = score(doc=873,freq=2.0), product of:
0.13186905 = queryWeight, product of:
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.046221454 = queryNorm
0.15760657 = fieldWeight in 873, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.8529835 = idf(docFreq=6931, maxDocs=44218)
0.0390625 = fieldNorm(doc=873)
0.5 = coord(1/2)
0.2 = coord(1/5)
- Abstract
- The standard method for making the full content of audio and video material searchable is to annotate it with human-generated meta-data that describes the content in a way that search can understand, as is done in the creation of multimedia CD-ROMs. However, for the huge amounts of data that could usefully be included in digital video and audio libraries, the cost of producing the meta-data is prohibitive. In the Informedia Digital Video Library, the production of the meta-data supporting the library interface is automated using techniques derived from artificial intelligence (AI) research. By applying speech recognition together with natural language processing, information retrieval, and image analysis, an interface has been prduced that helps users locate the information they want, and navigate or browse the digital video library more effectively. Specific interface components include automatc titles, filmstrips, video skims, word location marking, and representative frames for shots. Both the user interface and the information retrieval engine within Informedia are designed for use with automatically derived meta-data, much of which depends on speech recognition for its production. Some experimental information retrieval results will be given, supporting a basic premise of the Informedia project: That speech recognition generated transcripts can make multimedia material searchable. The Informedia project emphasizes the integration of speech recognition, image processing, natural language processing, and information retrieval to compensate for deficiencies in these individual technologies
