Search (6 results, page 1 of 1)

0.09615815 = product of:
  0.14423722 = sum of:
    0.06973162 = weight(_text_:search in 3455) [ClassicSimilarity], result of:
      0.06973162 = score(doc=3455,freq=6.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.39907667 = fieldWeight in 3455, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.046875 = fieldNorm(doc=3455)
    0.074505605 = product of:
      0.14901121 = sum of:
        0.14901121 = weight(_text_:engines in 3455) [ClassicSimilarity], result of:
          0.14901121 = score(doc=3455,freq=6.0), product of:
            0.25542772 = queryWeight, product of:
              5.080822 = idf(docFreq=746, maxDocs=44218)
              0.05027291 = queryNorm
            0.58337915 = fieldWeight in 3455, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              5.080822 = idf(docFreq=746, maxDocs=44218)
              0.046875 = fieldNorm(doc=3455)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

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.

0.029588005 = product of:
  0.08876401 = sum of:
    0.08876401 = weight(_text_:search in 4575) [ClassicSimilarity], result of:
      0.08876401 = score(doc=4575,freq=14.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.5079997 = fieldWeight in 4575, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4575)
  0.33333334 = coord(1/3)

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.

0.025304725 = product of:
  0.075914174 = sum of:
    0.075914174 = weight(_text_:search in 2590) [ClassicSimilarity], result of:
      0.075914174 = score(doc=2590,freq=4.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.43445963 = fieldWeight in 2590, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.0625 = fieldNorm(doc=2590)
  0.33333334 = coord(1/3)

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

0.013419857 = product of:
  0.04025957 = sum of:
    0.04025957 = weight(_text_:search in 3094) [ClassicSimilarity], result of:
      0.04025957 = score(doc=3094,freq=2.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.230407 = fieldWeight in 3094, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.046875 = fieldNorm(doc=3094)
  0.33333334 = coord(1/3)

Abstract

The paper addresses the issue of how online natural language question answering, based on deep semantic analysis, may compete with currently popular keyword search, open domain information retrieval systems, covering a horizontal domain. We suggest the multiagent question answering approach, where each domain is represented by an agent which tries to answer questions taking into account its specific knowledge. The meta-agent controls the cooperation between question answering agents and chooses the most relevant answer(s). We argue that multiagent question answering is optimal in terms of access to business and financial knowledge, flexibility in query phrasing, and efficiency and usability of advice. The knowledge and advice encoded in the system are initially prepared by domain experts. We analyze the commercial application of multiagent question answering and the robustness of the meta-agent. The paper suggests that a multiagent architecture is optimal when a real world question answering domain combines a number of vertical ones to form a horizontal domain.

0.011183213 = product of:
  0.03354964 = sum of:
    0.03354964 = weight(_text_:search in 873) [ClassicSimilarity], result of:
      0.03354964 = score(doc=873,freq=2.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.19200584 = fieldWeight in 873, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.0390625 = fieldNorm(doc=873)
  0.33333334 = coord(1/3)

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

0.0068112854 = product of:
  0.020433856 = sum of:
    0.020433856 = product of:
      0.040867712 = sum of:
        0.040867712 = weight(_text_:22 in 764) [ClassicSimilarity], result of:
          0.040867712 = score(doc=764,freq=2.0), product of:
            0.17604718 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.05027291 = 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)
  0.33333334 = coord(1/3)

Date

22. 9.1997 19:16:05