Search (96 results, page 1 of 5)

0.18800877 = product of:
  0.37601754 = sum of:
    0.37601754 = sum of:
      0.32770893 = weight(_text_:translation in 4436) [ClassicSimilarity], result of:
        0.32770893 = score(doc=4436,freq=12.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.94628274 = fieldWeight in 4436, product of:
            3.4641016 = tf(freq=12.0), with freq of:
              12.0 = termFreq=12.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.046875 = fieldNorm(doc=4436)
      0.04830862 = weight(_text_:22 in 4436) [ClassicSimilarity], result of:
        0.04830862 = score(doc=4436,freq=2.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.23214069 = fieldWeight in 4436, 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=4436)
  0.5 = coord(1/2)

Abstract

Language barrier is the major problem that people face in searching for, retrieving, and understanding multilingual collections on the Internet. This paper deals with query translation and document translation in a Chinese-English information retrieval system called MTIR. Bilingual dictionary and monolingual corpus-based approaches are adopted to select suitable tranlated query terms. A machine transliteration algorithm is introduced to resolve proper name searching. We consider several design issues for document translation, including which material is translated, what roles the HTML tags play in translation, what the tradeoff is between the speed performance and the translation performance, and what from the translated result is presented in. About 100.000 Web pages translated in the last 4 months of 1997 are used for quantitative study of online and real-time Web page translation

Date

16. 2.2000 14:22:39

0.14001693 = product of:
  0.28003386 = sum of:
    0.28003386 = sum of:
      0.23172523 = weight(_text_:translation in 1023) [ClassicSimilarity], result of:
        0.23172523 = score(doc=1023,freq=6.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.669123 = fieldWeight in 1023, product of:
            2.4494898 = tf(freq=6.0), with freq of:
              6.0 = termFreq=6.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.046875 = fieldNorm(doc=1023)
      0.04830862 = weight(_text_:22 in 1023) [ClassicSimilarity], result of:
        0.04830862 = score(doc=1023,freq=2.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.23214069 = fieldWeight in 1023, 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=1023)
  0.5 = coord(1/2)

Abstract

Query translation is a viable method for cross-language information retrieval (CLIR), but it suffers from translation ambiguities caused by multiple translations of individual query terms. Previous research has employed various methods for disambiguation, including the method of selecting an individual target query term from multiple candidates by comparing their statistical associations with the candidate translations of other query terms. This paper proposes a new method where we examine all combinations of target query term translations corresponding to the source query terms, instead of looking at the candidates for each query term and selecting the best one at a time. The goodness value for a combination of target query terms is computed based on the association value between each pair of the terms in the combination. We tested our method using the NTCIR-3 English-Korean CLIR test collection. The results show some improvements regardless of the association measures we used.

Date

26.12.2007 20:22:38

0.13854836 = product of:
  0.27709672 = sum of:
    0.27709672 = sum of:
      0.22073665 = weight(_text_:translation in 1080) [ClassicSimilarity], result of:
        0.22073665 = score(doc=1080,freq=4.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.6373927 = fieldWeight in 1080, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.0546875 = fieldNorm(doc=1080)
      0.056360055 = weight(_text_:22 in 1080) [ClassicSimilarity], result of:
        0.056360055 = score(doc=1080,freq=2.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.2708308 = fieldWeight in 1080, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0546875 = fieldNorm(doc=1080)
  0.5 = coord(1/2)

Abstract

Named entities are major constituents of a document but are usually unknown words. This work proposes a systematic way of dealing with formulation, transformation, translation, and transliteration of multilingual-named entities. The rules and similarity matrices for translation and transliteration are learned automatically from parallel-named-entity corpora. The results are applied in cross-language access to collections of images with captions. Experimental results demonstrate that the similarity-based transliteration of named entities is effective, and runs in which transliteration is considered outperform the runs in which it is neglected.

Date

4. 6.2006 19:52:22

0.13161743 = product of:
  0.26323485 = sum of:
    0.26323485 = sum of:
      0.22297767 = weight(_text_:translation in 1022) [ClassicSimilarity], result of:
        0.22297767 = score(doc=1022,freq=8.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.6438638 = fieldWeight in 1022, product of:
            2.828427 = tf(freq=8.0), with freq of:
              8.0 = termFreq=8.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.0390625 = fieldNorm(doc=1022)
      0.040257182 = weight(_text_:22 in 1022) [ClassicSimilarity], result of:
        0.040257182 = score(doc=1022,freq=2.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.19345059 = fieldWeight in 1022, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0390625 = fieldNorm(doc=1022)
  0.5 = coord(1/2)

Abstract

Two probabilistic approaches to cross-lingual retrieval are in wide use today, those based on probabilistic models of relevance, as exemplified by INQUERY, and those based on language modeling. INQUERY, as a query net model, allows the easy incorporation of query operators, including a synonym operator, which has proven to be extremely useful in cross-language information retrieval (CLIR), in an approach often called structured query translation. In contrast, language models incorporate translation probabilities into a unified framework. We compare the two approaches on Arabic and Spanish data sets, using two kinds of bilingual dictionaries--one derived from a conventional dictionary, and one derived from a parallel corpus. We find that structured query processing gives slightly better results when queries are not expanded. On the other hand, when queries are expanded, language modeling gives better results, but only when using a probabilistic dictionary derived from a parallel corpus. We pursue two additional issues inherent in the comparison of structured query processing with language modeling. The first concerns query expansion, and the second is the role of translation probabilities. We compare conventional expansion techniques (pseudo-relevance feedback) with relevance modeling, a new IR approach which fits into the formal framework of language modeling. We find that relevance modeling and pseudo-relevance feedback achieve comparable levels of retrieval and that good translation probabilities confer a small but significant advantage.

Date

26.12.2007 20:22:11

0.10105266 = product of:
  0.20210531 = sum of:
    0.20210531 = sum of:
      0.1337866 = weight(_text_:translation in 1967) [ClassicSimilarity], result of:
        0.1337866 = score(doc=1967,freq=2.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.3863183 = fieldWeight in 1967, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.046875 = fieldNorm(doc=1967)
      0.06831871 = weight(_text_:22 in 1967) [ClassicSimilarity], result of:
        0.06831871 = score(doc=1967,freq=4.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.32829654 = fieldWeight in 1967, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.046875 = fieldNorm(doc=1967)
  0.5 = coord(1/2)

Abstract

This paper reports on the second part of an initiative of the authors on researching classification systems with the conceptual model defined by the Functional Requirements for Subject Authority Data (FRSAD) final report. In an earlier study, the authors explored whether the FRSAD conceptual model could be extended beyond subject authority data to model classification data. The focus of the current study is to determine if classification data modeled using FRSAD can be used to solve real-world discovery problems in multicultural and multilingual contexts. The paper discusses the relationships between entities (same type or different types) in the context of classification systems that involve multiple translations and /or multicultural implementations. Results of two case studies are presented in detail: (a) two instances of the DDC (DDC 22 in English, and the Swedish-English mixed translation of DDC 22), and (b) Chinese Library Classification. The use cases of conceptual models in practice are also discussed.

0.09460142 = product of:
  0.18920285 = sum of:
    0.18920285 = product of:
      0.3784057 = sum of:
        0.3784057 = weight(_text_:translation in 3481) [ClassicSimilarity], result of:
          0.3784057 = score(doc=3481,freq=4.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            1.0926732 = fieldWeight in 3481, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.09375 = fieldNorm(doc=3481)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

0.09460142 = product of:
  0.18920285 = sum of:
    0.18920285 = product of:
      0.3784057 = sum of:
        0.3784057 = weight(_text_:translation in 1606) [ClassicSimilarity], result of:
          0.3784057 = score(doc=1606,freq=16.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            1.0926732 = fieldWeight in 1606, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.046875 = fieldNorm(doc=1606)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article explores how best to use lexical and statistical translation evidence together for cross-language information retrieval (CLIR). Lexical translation evidence is assembled from Wikipedia and from a large machine-readable dictionary, statistical translation evidence is drawn from parallel corpora, and evidence from co-occurrence in the document language provides a basis for limiting the adverse effect of translation ambiguity. Coverage statistics for NII Testbeds and Community for Information Access Research (NTCIR) queries confirm that these resources have complementary strengths. Experiments with translation evidence from a small parallel corpus indicate that even rather rough estimates of translation probabilities can yield further improvements over a strong technique for translation weighting based on using Jensen-Shannon divergence as a term-association measure. Finally, a novel approach to posttranslation query expansion using a random walk over the Wikipedia concept link graph is shown to yield further improvements over alternative techniques for posttranslation query expansion. Evaluation results on the NTCIR-5 English-Korean test collection show statistically significant improvements over strong baselines.

0.08919107 = product of:
  0.17838214 = sum of:
    0.17838214 = product of:
      0.3567643 = sum of:
        0.3567643 = weight(_text_:translation in 4073) [ClassicSimilarity], result of:
          0.3567643 = score(doc=4073,freq=8.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            1.0301821 = fieldWeight in 4073, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.0625 = fieldNorm(doc=4073)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Presents a methodology for extracting information about lexical translation equivalences from the machine readable versions of conventional dictionaries (MRDs), and describes a series of experiments on semi automatic construction of a linked multilingual lexical knowledge base for English, Dutch and Spanish. Discusses the advantage and limitations of using MRDs that this has revealed, and some strategies developed to cover gaps where direct translation can be found

Source

Machine translation. 9(1994/95) nos.3/4, S.183-219

0.084210545 = product of:
  0.16842109 = sum of:
    0.16842109 = sum of:
      0.111488834 = weight(_text_:translation in 1962) [ClassicSimilarity], result of:
        0.111488834 = score(doc=1962,freq=2.0), product of:
          0.34631187 = queryWeight, product of:
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.05942625 = queryNorm
          0.3219319 = fieldWeight in 1962, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.8275905 = idf(docFreq=353, maxDocs=44218)
            0.0390625 = fieldNorm(doc=1962)
      0.056932252 = weight(_text_:22 in 1962) [ClassicSimilarity], result of:
        0.056932252 = score(doc=1962,freq=4.0), product of:
          0.2081006 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.05942625 = queryNorm
          0.27358043 = fieldWeight in 1962, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0390625 = fieldNorm(doc=1962)
  0.5 = coord(1/2)

Abstract

This article reports on the second part of an initiative of the authors on researching classification systems with the conceptual model defined by the Functional Requirements for Subject Authority Data (FRSAD) final report. In an earlier study, the authors explored whether the FRSAD conceptual model could be extended beyond subject authority data to model classification data. The focus of the current study is to determine if classification data modeled using FRSAD can be used to solve real-world discovery problems in multicultural and multilingual contexts. The article discusses the relationships between entities (same type or different types) in the context of classification systems that involve multiple translations and/or multicultural implementations. Results of two case studies are presented in detail: (a) two instances of the Dewey Decimal Classification [DDC] (DDC 22 in English, and the Swedish-English mixed translation of DDC 22), and (b) Chinese Library Classification. The use cases of conceptual models in practice are also discussed.

0.07883452 = product of:
  0.15766904 = sum of:
    0.15766904 = product of:
      0.31533808 = sum of:
        0.31533808 = weight(_text_:translation in 4244) [ClassicSimilarity], result of:
          0.31533808 = score(doc=4244,freq=16.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.910561 = fieldWeight in 4244, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4244)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

As an effective technique for improving retrieval effectiveness, relevance feedback (RF) has been widely studied in both monolingual and translingual information retrieval (TLIR). The studies of RF in TLIR have been focused on query expansion (QE), in which queries are reformulated before and/or after they are translated. However, RF in TLIR actually not only can help select better query terms, but also can enhance query translation by adjusting translation probabilities and even resolving some out-of-vocabulary terms. In this paper, we propose a novel relevance feedback method called translation enhancement (TE), which uses the extracted translation relationships from relevant documents to revise the translation probabilities of query terms and to identify extra available translation alternatives so that the translated queries are more tuned to the current search. We studied TE using pseudo-relevance feedback (PRF) and interactive relevance feedback (IRF). Our results show that TE can significantly improve TLIR with both types of relevance feedback methods, and that the improvement is comparable to that of query expansion. More importantly, the effects of translation enhancement and query expansion are complementary. Their integration can produce further improvement, and makes TLIR more robust for a variety of queries.

0.074788995 = product of:
  0.14957799 = sum of:
    0.14957799 = product of:
      0.29915598 = sum of:
        0.29915598 = weight(_text_:translation in 1425) [ClassicSimilarity], result of:
          0.29915598 = score(doc=1425,freq=10.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.863834 = fieldWeight in 1425, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.046875 = fieldNorm(doc=1425)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

A number of studies have examined the problems of query expansion in monolingual Information Retrieval (IR), and query translation for crosslanguage IR. However, no link has been made between them. This article first shows that query translation is a special case of query expansion. There is also another set of studies an inferential IR. Again, there is no relationship established with query translation or query expansion. The second claim of this article is that logical inference is a general form that covers query expansion and query translation. This analysis provides a unified view of different subareas of IR. We further develop the inferential IR approach in two particular contexts: using fuzzy logic and probability theory. The evaluation formulas obtained are shown to strongly correspond to those used in other IR models. This indicates that inference is indeed the core of advanced IR.

0.068272695 = product of:
  0.13654539 = sum of:
    0.13654539 = product of:
      0.27309078 = sum of:
        0.27309078 = weight(_text_:translation in 5162) [ClassicSimilarity], result of:
          0.27309078 = score(doc=5162,freq=12.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7885689 = fieldWeight in 5162, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5162)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This research investigated conceptual alteration in medical article titles translation between English and Chinese with a twofold purpose: one was to further justify the findings from a pilot study, and the other was to further investigate how the concepts were altered in translation. The research corpus of 800 medical article titles in English and Chinese was selected from two English medical journals and two Chinese medical journals. The analysis was based on the pairing of concepts in English and Chinese and their conceptual similarity/ dissimilarity via translation between English and Chinese. Two kinds of conceptual alteration were discussed: one was apparent conceptual alteration that was obvious with addition or omission of concepts in translation. The other was latent conceptual alteration that was not obvious, and can only be recognized by the differences between the original and translated concepts. The findings from the pilot study were verified with the findings from this research. Additional findings, for example, the addition/omission of single-word and multiword concepts in the general and medical domain and, implicit information vs. explicit information, were also discussed. The findings provided useful insights into future studies on crosslanguage information retrieval via medical translation between English and Chinese, and other languages as well

0.068272695 = product of:
  0.13654539 = sum of:
    0.13654539 = product of:
      0.27309078 = sum of:
        0.27309078 = weight(_text_:translation in 3956) [ClassicSimilarity], result of:
          0.27309078 = score(doc=3956,freq=12.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7885689 = fieldWeight in 3956, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3956)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose - This study aims to focus on the evaluation of systems for the automatic translation of questions destined to translingual question-answer (QA) systems. The efficacy of online translators when performing as tools in QA systems is analysed using a collection of documents in the Spanish language. Design/methodology/approach - Automatic translation is evaluated in terms of the functionality of actual translations produced by three online translators (Google Translator, Promt Translator, and Worldlingo) by means of objective and subjective evaluation measures, and the typology of errors produced was identified. For this purpose, a comparative study of the quality of the translation of factual questions of the CLEF collection of queries was carried out, from German and French to Spanish. Findings - It was observed that the rates of error for the three systems evaluated here are greater in the translations pertaining to the language pair German-Spanish . Promt was identified as the most reliable translator of the three (on average) for the two linguistic combinations evaluated. However, for the Spanish-German pair, a good assessment of the Google online translator was obtained as well. Most errors (46.38 percent) tended to be of a lexical nature, followed by those due to a poor translation of the interrogative particle of the query (31.16 percent). Originality/value - The evaluation methodology applied focuses above all on the finality of the translation. That is, does the resulting question serve as effective input into a translingual QA system? Thus, instead of searching for "perfection", the functionality of the question and its capacity to lead one to an adequate response are appraised. The results obtained contribute to the development of improved translingual QA systems.

0.067586526 = product of:
  0.13517305 = sum of:
    0.13517305 = product of:
      0.2703461 = sum of:
        0.2703461 = weight(_text_:translation in 7430) [ClassicSimilarity], result of:
          0.2703461 = score(doc=7430,freq=6.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.78064346 = fieldWeight in 7430, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.0546875 = fieldNorm(doc=7430)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article describes a framework for cross-language information retrieval that efficiently leverages statistical estimation of translation probabilities. The framework provides a unified perspective into which some earlier work on techniques for cross-language information retrieval based on translation probabilities can be cast. Modeling synonymy and filtering translation probabilities using bidirectional evidence are shown to yield a balance between retrieval effectiveness and query-time (or indexing-time) efficiency that seems well suited large-scale applications. Evaluations with six test collections show consistent improvements over strong baselines.

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 1917) [ClassicSimilarity], result of:
          0.2675732 = score(doc=1917,freq=2.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 1917, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.09375 = fieldNorm(doc=1917)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 5170) [ClassicSimilarity], result of:
          0.2675732 = score(doc=5170,freq=2.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 5170, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.09375 = fieldNorm(doc=5170)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 7409) [ClassicSimilarity], result of:
          0.2675732 = score(doc=7409,freq=8.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 7409, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.046875 = fieldNorm(doc=7409)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Although knowledge based MT systems have the potential to achieve high translation accuracy, each successful application system requires a large amount of hand coded lexical knowledge. Systems like KBMT-89 and its descendants have demonstarted how knowledge based translation can produce good results in technical domains with tractable domain semantics. Nevertheless, the magnitude of the development task for large scale applications with 10s of 1000s of of domain concepts precludes a purely hand crafted approach. The current challenge for the next generation of knowledge based MT systems is to utilize online textual resources and corpus analysis software in order to automate the most laborious aspects of the knowledge acquisition process. This partial automation can in turn maximize the productivity of human knowledge engineers and help to make large scale applications of knowledge based MT an viable approach. Discusses the corpus based knowledge acquisition methodology used in KANT, a knowledge based translation system for multilingual document production. This methodology can be generalized beyond the KANT interlinhua approach for use with any system that requires similar kinds of knowledge

Source

Machine translation. 9(1994/95) nos.3/4, S.251-283

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 3480) [ClassicSimilarity], result of:
          0.2675732 = score(doc=3480,freq=2.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 3480, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.09375 = fieldNorm(doc=3480)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 5050) [ClassicSimilarity], result of:
          0.2675732 = score(doc=5050,freq=8.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 5050, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.046875 = fieldNorm(doc=5050)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Users' cross-lingual queries to a digital library system might be short and the query terms may not be included in a common translation dictionary (unknown terms). In this article, the authors investigate the feasibility of exploiting the Web as the multilingual corpus source to translate unknown query terms for cross-language information retrieval in digital libraries. They propose a Webbased term translation approach to determine effective translations for unknown query terms by mining bilingual search-result pages obtained from a real Web search engine. This approach can enhance the construction of a domain-specific bilingual lexicon and bring multilingual support to a digital library that only has monolingual document collections. Very promising results have been obtained in generating effective translation equivalents for many unknown terms, including proper nouns, technical terms, and Web query terms, and in assisting bilingual lexicon construction for a real digital library system.

0.0668933 = product of:
  0.1337866 = sum of:
    0.1337866 = product of:
      0.2675732 = sum of:
        0.2675732 = weight(_text_:translation in 1025) [ClassicSimilarity], result of:
          0.2675732 = score(doc=1025,freq=8.0), product of:
            0.34631187 = queryWeight, product of:
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.05942625 = queryNorm
            0.7726366 = fieldWeight in 1025, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              5.8275905 = idf(docFreq=353, maxDocs=44218)
              0.046875 = fieldNorm(doc=1025)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Cross-language information retrieval (CLIR) systems allow users to find documents written in different languages from that of their query. Simple knowledge structures such as bilingual term lists have proven to be a remarkably useful basis for bridging that language gap. A broad array of dictionary-based techniques have demonstrated utility, but comparison across techniques has been difficult because evaluation results often span only a limited range of conditions. This article identifies the key issues in dictionary-based CLIR, develops unified frameworks for term selection and term translation that help to explain the relationships among existing techniques, and illustrates the effect of those techniques using four contrasting languages for systematic experiments with a uniform query translation architecture. Key results include identification of a previously unseen dependence of pre- and post-translation expansion on orthographic cognates and development of a query-specific measure for translation fanout that helps to explain the utility of structured query methods.