-
Jensen, N.: Evaluierung von mehrsprachigem Web-Retrieval : Experimente mit dem EuroGOV-Korpus im Rahmen des Cross Language Evaluation Forum (CLEF) (2006)
0.01
0.010080026 = product of:
0.07560019 = sum of:
0.036906876 = weight(_text_:evaluation in 5964) [ClassicSimilarity], result of:
0.036906876 = score(doc=5964,freq=2.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.278072 = fieldWeight in 5964, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.046875 = fieldNorm(doc=5964)
0.038693316 = weight(_text_:web in 5964) [ClassicSimilarity], result of:
0.038693316 = score(doc=5964,freq=6.0), product of:
0.10326045 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.031640913 = 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)
0.13333334 = coord(2/15)
- 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
0.009584909 = product of:
0.071886815 = sum of:
0.053270485 = weight(_text_:evaluation in 4575) [ClassicSimilarity], result of:
0.053270485 = score(doc=4575,freq=6.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.40136236 = fieldWeight in 4575, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.0390625 = fieldNorm(doc=4575)
0.01861633 = weight(_text_:web in 4575) [ClassicSimilarity], result of:
0.01861633 = score(doc=4575,freq=2.0), product of:
0.10326045 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.031640913 = 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)
0.13333334 = coord(2/15)
- 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.
-
Rösener, C.: ¬Die Stecknadel im Heuhaufen : Natürlichsprachlicher Zugang zu Volltextdatenbanken (2005)
0.01
0.006807589 = product of:
0.051056914 = sum of:
0.029049365 = product of:
0.05809873 = sum of:
0.05809873 = weight(_text_:recherche in 548) [ClassicSimilarity], result of:
0.05809873 = score(doc=548,freq=4.0), product of:
0.17150146 = queryWeight, product of:
5.4202437 = idf(docFreq=531, maxDocs=44218)
0.031640913 = queryNorm
0.33876523 = fieldWeight in 548, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
5.4202437 = idf(docFreq=531, maxDocs=44218)
0.03125 = fieldNorm(doc=548)
0.5 = coord(1/2)
0.02200755 = weight(_text_:software in 548) [ClassicSimilarity], result of:
0.02200755 = score(doc=548,freq=2.0), product of:
0.12552431 = queryWeight, product of:
3.9671519 = idf(docFreq=2274, maxDocs=44218)
0.031640913 = queryNorm
0.17532499 = fieldWeight in 548, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.9671519 = idf(docFreq=2274, maxDocs=44218)
0.03125 = fieldNorm(doc=548)
0.13333334 = coord(2/15)
- Content
- Enthält die Kapitel: 2: Wissensrepräsentation 2.1 Deklarative Wissensrepräsentation 2.2 Klassifikationen des BMM 2.3 Thesauri und Ontologien: existierende kommerzielle Software 2.4 Erstellung eines Thesaurus im Rahmen des LeWi-Projektes 3: Analysekomponenten 3.1 Sprachliche Phänomene in der maschinellen Textanalyse 3.2 Analysekomponenten: Lösungen und Forschungsansätze 3.3 Die Analysekomponenten im LeWi-Projekt 4: Information Retrieval 4.1 Grundlagen des Information Retrieval 4.2 Automatische Indexierungsmethoden und -verfahren 4.3 Automatische Indexierung des BMM im Rahmen des LeWi-Projektes 4.4 Suchstrategien und Suchablauf im LeWi-Kontext
- RSWK
- Brockhaus-Enzyklopädie / Multimedia / Recherche
- Subject
- Brockhaus-Enzyklopädie / Multimedia / Recherche
-
Strötgen, R.; Mandl, T.; Schneider, R.: Entwicklung und Evaluierung eines Question Answering Systems im Rahmen des Cross Language Evaluation Forum (CLEF) (2006)
0.01
0.0062088794 = product of:
0.046566594 = sum of:
0.009659718 = product of:
0.019319436 = sum of:
0.019319436 = weight(_text_:online in 5981) [ClassicSimilarity], result of:
0.019319436 = score(doc=5981,freq=2.0), product of:
0.096027054 = queryWeight, product of:
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.031640913 = queryNorm
0.20118743 = fieldWeight in 5981, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.046875 = fieldNorm(doc=5981)
0.5 = coord(1/2)
0.036906876 = weight(_text_:evaluation in 5981) [ClassicSimilarity], result of:
0.036906876 = score(doc=5981,freq=2.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.278072 = fieldWeight in 5981, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.046875 = fieldNorm(doc=5981)
0.13333334 = coord(2/15)
- Abstract
- Question Answering Systeme versuchen, zu konkreten Fragen eine korrekte Antwort zu liefern. Dazu durchsuchen sie einen Dokumentenbestand und extrahieren einen Bruchteil eines Dokuments. Dieser Beitrag beschreibt die Entwicklung eines modularen Systems zum multilingualen Question Answering. Die Strategie bei der Entwicklung zielte auf eine schnellstmögliche Verwendbarkeit eines modularen Systems, das auf viele frei verfügbare Ressourcen zugreift. Das System integriert Module zur Erkennung von Eigennamen, zu Indexierung und Retrieval, elektronische Wörterbücher, Online-Übersetzungswerkzeuge sowie Textkorpora zu Trainings- und Testzwecken und implementiert eigene Ansätze zu den Bereichen der Frage- und AntwortTaxonomien, zum Passagenretrieval und zum Ranking alternativer Antworten.
-
Nhongkai, S.N.; Bentz, H.-J.: Bilinguale Suche mittels Konzeptnetzen (2006)
0.01
0.0059607853 = product of:
0.08941177 = sum of:
0.08941177 = weight(_text_:suchmaschine in 3914) [ClassicSimilarity], result of:
0.08941177 = score(doc=3914,freq=2.0), product of:
0.17890577 = queryWeight, product of:
5.6542544 = idf(docFreq=420, maxDocs=44218)
0.031640913 = queryNorm
0.4997702 = fieldWeight in 3914, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
5.6542544 = idf(docFreq=420, maxDocs=44218)
0.0625 = fieldNorm(doc=3914)
0.06666667 = coord(1/15)
- Abstract
- Eine neue Methode der Volltextsuche in bilingualen Textsammlungen wird vorgestellt und anhand eines parallelen Textkorpus (Englisch-Deutsch) geprüft. Die Brücke liefern passende Wortcluster, die aus einer Kookkurrenzanalyse stammen, geliefert von der neuartigen Suchmaschine SENTRAX (Essente Extractor Engine). Diese Cluster repräsentieren Konzepte, die sich in beiden Textsammlungen finden. Die Hypothese ist, dass das Finden mittels solcher Strukturvergleiche erfolgreich möglich ist.
-
Voorhees, E.M.: Question answering in TREC (2005)
0.00
0.004920917 = product of:
0.07381375 = sum of:
0.07381375 = weight(_text_:evaluation in 6487) [ClassicSimilarity], result of:
0.07381375 = score(doc=6487,freq=2.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.556144 = fieldWeight in 6487, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.09375 = fieldNorm(doc=6487)
0.06666667 = coord(1/15)
- Source
- TREC: experiment and evaluation in information retrieval. Ed.: E.M. Voorhees, u. D.K. Harman
-
Burke, R.D.: Question answering from frequently asked question files : experiences with the FAQ Finder System (1997)
0.00
0.003280611 = product of:
0.049209163 = sum of:
0.049209163 = weight(_text_:evaluation in 1191) [ClassicSimilarity], result of:
0.049209163 = score(doc=1191,freq=2.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.37076265 = fieldWeight in 1191, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.0625 = fieldNorm(doc=1191)
0.06666667 = coord(1/15)
- Abstract
- Describes FAQ Finder, a natural language question-answering system that uses files of frequently asked questions as its knowledge base. Unlike information retrieval approaches that rely on a purely lexical metric of similarity between query and document, FAQ Finder uses a semantic knowledge base (Wordnet) to improve its ability to match question and answer. Includes results from an evaluation of the system's performance and shows that a combination of semantic and statistical techniques works better than any single approach
-
Radev, D.; Fan, W.; Qu, H.; Wu, H.; Grewal, A.: Probabilistic question answering on the Web (2005)
0.00
0.0025795544 = product of:
0.038693316 = sum of:
0.038693316 = weight(_text_:web in 3455) [ClassicSimilarity], result of:
0.038693316 = score(doc=3455,freq=6.0), product of:
0.10326045 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.031640913 = 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)
0.06666667 = coord(1/15)
- 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.
-
Lin, J.; Katz, B.: Building a reusable test collection for question answering (2006)
0.00
0.0024604585 = product of:
0.036906876 = sum of:
0.036906876 = weight(_text_:evaluation in 5045) [ClassicSimilarity], result of:
0.036906876 = score(doc=5045,freq=2.0), product of:
0.13272417 = queryWeight, product of:
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.031640913 = queryNorm
0.278072 = fieldWeight in 5045, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.1947007 = idf(docFreq=1811, maxDocs=44218)
0.046875 = fieldNorm(doc=5045)
0.06666667 = coord(1/15)
- 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."
-
Kneedler, W.H.; Sizemore, E.J.: Speech synthesis + online library catalog = "talking catalog" (1993)
0.00
0.0017172833 = product of:
0.025759248 = sum of:
0.025759248 = product of:
0.051518496 = sum of:
0.051518496 = weight(_text_:online in 3781) [ClassicSimilarity], result of:
0.051518496 = score(doc=3781,freq=2.0), product of:
0.096027054 = queryWeight, product of:
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.031640913 = queryNorm
0.5364998 = fieldWeight in 3781, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.125 = fieldNorm(doc=3781)
0.5 = coord(1/2)
0.06666667 = coord(1/15)
-
Peters, B.F.: Online searching using speech as a man / machine interface (1989)
0.00
0.0017172833 = product of:
0.025759248 = sum of:
0.025759248 = product of:
0.051518496 = sum of:
0.051518496 = weight(_text_:online in 4637) [ClassicSimilarity], result of:
0.051518496 = score(doc=4637,freq=2.0), product of:
0.096027054 = queryWeight, product of:
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.031640913 = queryNorm
0.5364998 = fieldWeight in 4637, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.125 = fieldNorm(doc=4637)
0.5 = coord(1/2)
0.06666667 = coord(1/15)
-
Srihari, R.K.: Using speech input for image interpretation, annotation, and retrieval (1997)
0.00
8.573814E-4 = product of:
0.01286072 = sum of:
0.01286072 = product of:
0.02572144 = sum of:
0.02572144 = weight(_text_:22 in 764) [ClassicSimilarity], result of:
0.02572144 = score(doc=764,freq=2.0), product of:
0.110801086 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.031640913 = 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)
0.06666667 = coord(1/15)
- Date
- 22. 9.1997 19:16:05
-
Galitsky, B.: Can many agents answer questions better than one? (2005)
0.00
6.439812E-4 = product of:
0.009659718 = sum of:
0.009659718 = product of:
0.019319436 = sum of:
0.019319436 = weight(_text_:online in 3094) [ClassicSimilarity], result of:
0.019319436 = score(doc=3094,freq=2.0), product of:
0.096027054 = queryWeight, product of:
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.031640913 = queryNorm
0.20118743 = fieldWeight in 3094, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.0349014 = idf(docFreq=5778, maxDocs=44218)
0.046875 = fieldNorm(doc=3094)
0.5 = coord(1/2)
0.06666667 = coord(1/15)
- 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.
