Search (12 results, page 1 of 1)

0.0174208 = product of:
  0.0348416 = sum of:
    0.015624823 = weight(_text_:for in 764) [ClassicSimilarity], result of:
      0.015624823 = score(doc=764,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.17601961 = fieldWeight in 764, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=764)
    0.019216778 = product of:
      0.038433556 = sum of:
        0.038433556 = weight(_text_:22 in 764) [ClassicSimilarity], result of:
          0.038433556 = score(doc=764,freq=2.0), product of:
            0.16556148 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.047278564 = 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)
  0.5 = coord(2/4)

Abstract

Explores the interaction of textual and photographic information in an integrated text and image database environment and describes 3 different applications involving the exploitation of linguistic context in vision. Describes the practical application of these ideas in working systems. PICTION uses captions to identify human faces in a photograph, wile Show&Tell is a multimedia system for semi automatic image annotation. The system combines advances in speech recognition, natural language processing and image understanding to assist in image annotation and enhance image retrieval capabilities. Presents an extension of this work to video annotation and retrieval

Date

22. 9.1997 19:16:05

0.006510343 = product of:
  0.026041372 = sum of:
    0.026041372 = weight(_text_:for in 873) [ClassicSimilarity], result of:
      0.026041372 = score(doc=873,freq=16.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.29336601 = fieldWeight in 873, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0390625 = fieldNorm(doc=873)
  0.25 = coord(1/4)

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

Source

Journal of the American Society for Information Science. 49(1998) no.7, S.619-632

0.0063788076 = product of:
  0.02551523 = sum of:
    0.02551523 = weight(_text_:for in 2590) [ClassicSimilarity], result of:
      0.02551523 = score(doc=2590,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.28743884 = fieldWeight in 2590, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=2590)
  0.25 = coord(1/4)

Abstract

Knowledge of conversation theory and speech act assists us to understand how people search for information. Dialogue embodies meanings and intentionalities, and represents epistemic inquiry. There are implications for the information-processing model of cognitive psychology. Question formulation (erotetics) and turn-taking play important roles in eliciting information, while discourse analysis furnishes us with information about people's categorising, recall, and semantic skills

0.0061762533 = product of:
  0.024705013 = sum of:
    0.024705013 = weight(_text_:for in 5045) [ClassicSimilarity], result of:
      0.024705013 = score(doc=5045,freq=10.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.27831143 = fieldWeight in 5045, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=5045)
  0.25 = coord(1/4)

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."

Source

Journal of the American Society for Information Science and Technology. 57(2006) no.7, S.851-861

0.0055814567 = product of:
  0.022325827 = sum of:
    0.022325827 = weight(_text_:for in 1951) [ClassicSimilarity], result of:
      0.022325827 = score(doc=1951,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.25150898 = fieldWeight in 1951, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1951)
  0.25 = coord(1/4)

Abstract

Describes experiments in the retrieval of spoken documents in multimedia systems. Speech documents pose a particular problem for retrieval since their words as well as contents are unknown. Addresses this problem, for a video mail application, by combining state of the art speech recognition with established document retrieval technologies so as to provide an effective and efficient retrieval tool. Tests with a small spoken message collection show that retrieval precision for the spoken file can reach 90% of that obtained when the same file is used, as a benchmark, in text transcription form

0.0055814567 = product of:
  0.022325827 = sum of:
    0.022325827 = weight(_text_:for in 3465) [ClassicSimilarity], result of:
      0.022325827 = score(doc=3465,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.25150898 = fieldWeight in 3465, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0546875 = fieldNorm(doc=3465)
  0.25 = coord(1/4)

Abstract

Recent work in automatic question answering has called for question taxonomies as a critical component of the process of machine understanding of questions. There is a long tradition of classifying questions in library reference services, and digital reference services have a strong need for automation to support scalability. Digital reference and question answering systems have the potential to arrive at a highly fruitful symbiosis. To move towards this goal, an extensive review was conducted of bodies of literature from several fields that deal with questions, to identify question taxonomies that exist in these bodies of literature. In the course of this review, five question taxonomies were identified, at four levels of linguistic analysis.

Source

Journal of the American Society for Information Science and Technology. 56(2005) no.7, S.715-728

0.0039062058 = product of:
  0.015624823 = sum of:
    0.015624823 = weight(_text_:for in 5263) [ClassicSimilarity], result of:
      0.015624823 = score(doc=5263,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.17601961 = fieldWeight in 5263, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=5263)
  0.25 = coord(1/4)

Abstract

Natrual language document retrieval queries from the Thomas Cooper Library, South Carolina Univ. were analysed in oder to investigate the frequency of various types of ill-formed input, such as spelling errors, cooccurrence violations, conjunctions, ellipsis, and missing or incorrect punctuation. Users were requested to write out their requests for information in complete sentences on the form normally used by the library. The primary reason for analysing ill-formed inputs was to determine whether there is a significant need to study ill-formed inputs in detail. Results indicated that most of the queries were sentence fragments and that many of them contained some type of ill-formed input. Conjunctions caused the most problems. The next most serious problem was caused by punctuation errors. Spelling errors occured in a small number of queries. The remaining types of ill-formed input considered, allipsis and cooccurrence violations, were not found in the queries

0.0039062058 = product of:
  0.015624823 = sum of:
    0.015624823 = weight(_text_:for in 3455) [ClassicSimilarity], result of:
      0.015624823 = score(doc=3455,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.17601961 = fieldWeight in 3455, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=3455)
  0.25 = coord(1/4)

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.

Source

Journal of the American Society for Information Science and Technology. 56(2005) no.6, S.571-583

0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 7224) [ClassicSimilarity], result of:
      0.014731225 = score(doc=7224,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 7224, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=7224)
  0.25 = coord(1/4)

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

0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 3883) [ClassicSimilarity], result of:
      0.014731225 = score(doc=3883,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 3883, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=3883)
  0.25 = coord(1/4)

0.0032551715 = product of:
  0.013020686 = sum of:
    0.013020686 = weight(_text_:for in 4575) [ClassicSimilarity], result of:
      0.013020686 = score(doc=4575,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.14668301 = fieldWeight in 4575, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4575)
  0.25 = coord(1/4)

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.

Source

Journal of the American Society for Information Science and Technology. 56(2005) no.13, S.1377-1393

0.0027621046 = product of:
  0.0110484185 = sum of:
    0.0110484185 = weight(_text_:for in 1850) [ClassicSimilarity], result of:
      0.0110484185 = score(doc=1850,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.12446466 = fieldWeight in 1850, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=1850)
  0.25 = coord(1/4)

Abstract

Answering open-domain factual questions requires Natural Language processing for refining document selection and answer identification. With our system QALC, we have participated in the Question Answering track of the TREC8, TREC9 and TREC10 evaluations. QALC performs an analysis of documents relying an multiword term searches and their linguistic variation both to minimize the number of documents selected and to provide additional clues when comparing question and sentence representations. This comparison process also makes use of the results of a syntactic parsing of the questions and Named Entity recognition functionalities. Answer extraction relies an the application of syntactic patterns chosen according to the kind of information that is sought, and categorized depending an the syntactic form of the question. These patterns allow QALC to handle nicely linguistic variations at the answer level.