-
Dorr, B.J.: Large-scale dictionary construction for foreign language tutoring and interlingual machine translation (1997)
0.01
0.005155518 = product of:
0.020622073 = sum of:
0.012270111 = product of:
0.03681033 = sum of:
0.03681033 = weight(_text_:problem in 3244) [ClassicSimilarity], result of:
0.03681033 = score(doc=3244,freq=2.0), product of:
0.13082431 = queryWeight, product of:
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.030822188 = queryNorm
0.28137225 = fieldWeight in 3244, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.046875 = fieldNorm(doc=3244)
0.33333334 = coord(1/3)
0.008351962 = product of:
0.025055885 = sum of:
0.025055885 = weight(_text_:22 in 3244) [ClassicSimilarity], result of:
0.025055885 = score(doc=3244,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.23214069 = fieldWeight in 3244, 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=3244)
0.33333334 = coord(1/3)
0.25 = coord(2/8)
- Abstract
- Describes techniques for automatic construction of dictionaries for use in large-scale foreign language tutoring (FLT) and interlingual machine translation (MT) systems. The dictionaries are based on a language independent representation called lexical conceptual structure (LCS). Demonstrates that synonymous verb senses share distribution patterns. Shows how the syntax-semantics relation can be used to develop a lexical acquisition approach that contributes both toward the enrichment of existing online resources and toward the development of lexicons containing more complete information than is provided in any of these resources alone. Describes the structure of the LCS and shows how this representation is used in FLT and MT. Focuses on the problem of building LCS dictionaries for large-scale FLT and MT. Describes authoring tools for manual and semi-automatic construction of LCS dictionaries. Presents an approach that uses linguistic techniques for building word definitions automatically. The techniques have been implemented as part of a set of lixicon-development tools used in the MILT FLT project
- Date
- 31. 7.1996 9:22:19
-
Melby, A.: Some notes on 'The proper place of men and machines in language translation' (1997)
0.00
0.00489409 = product of:
0.03915272 = sum of:
0.03915272 = product of:
0.05872908 = sum of:
0.029497212 = weight(_text_:29 in 330) [ClassicSimilarity], result of:
0.029497212 = score(doc=330,freq=2.0), product of:
0.108422816 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.030822188 = queryNorm
0.27205724 = fieldWeight in 330, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.0546875 = fieldNorm(doc=330)
0.029231867 = weight(_text_:22 in 330) [ClassicSimilarity], result of:
0.029231867 = score(doc=330,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.2708308 = fieldWeight in 330, 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=330)
0.6666667 = coord(2/3)
0.125 = coord(1/8)
- Date
- 31. 7.1996 9:22:19
- Source
- Machine translation. 12(1997) nos.1/2, S.29-34
-
Proszeky, G.: Language technology tools in the translator's practice (1999)
0.00
0.0024581011 = product of:
0.01966481 = sum of:
0.01966481 = product of:
0.058994424 = sum of:
0.058994424 = weight(_text_:29 in 6873) [ClassicSimilarity], result of:
0.058994424 = score(doc=6873,freq=2.0), product of:
0.108422816 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.030822188 = queryNorm
0.5441145 = fieldWeight in 6873, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.109375 = fieldNorm(doc=6873)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 30. 3.2002 18:29:40
-
McMahon, J.G.; Smith, F.J.: Improved statistical language model performance with automatic generated word hierarchies (1996)
0.00
0.002435989 = product of:
0.019487912 = sum of:
0.019487912 = product of:
0.058463734 = sum of:
0.058463734 = weight(_text_:22 in 3164) [ClassicSimilarity], result of:
0.058463734 = score(doc=3164,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.5416616 = fieldWeight in 3164, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.109375 = fieldNorm(doc=3164)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Source
- Computational linguistics. 22(1996) no.2, S.217-248
-
Ruge, G.: ¬A spreading activation network for automatic generation of thesaurus relationships (1991)
0.00
0.002435989 = product of:
0.019487912 = sum of:
0.019487912 = product of:
0.058463734 = sum of:
0.058463734 = weight(_text_:22 in 4506) [ClassicSimilarity], result of:
0.058463734 = score(doc=4506,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.5416616 = fieldWeight in 4506, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.109375 = fieldNorm(doc=4506)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 8.10.2000 11:52:22
-
Somers, H.: Example-based machine translation : Review article (1999)
0.00
0.002435989 = product of:
0.019487912 = sum of:
0.019487912 = product of:
0.058463734 = sum of:
0.058463734 = weight(_text_:22 in 6672) [ClassicSimilarity], result of:
0.058463734 = score(doc=6672,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.5416616 = fieldWeight in 6672, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.109375 = fieldNorm(doc=6672)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 31. 7.1996 9:22:19
-
New tools for human translators (1997)
0.00
0.002435989 = product of:
0.019487912 = sum of:
0.019487912 = product of:
0.058463734 = sum of:
0.058463734 = weight(_text_:22 in 1179) [ClassicSimilarity], result of:
0.058463734 = score(doc=1179,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.5416616 = fieldWeight in 1179, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.109375 = fieldNorm(doc=1179)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 31. 7.1996 9:22:19
-
Baayen, R.H.; Lieber, H.: Word frequency distributions and lexical semantics (1997)
0.00
0.002435989 = product of:
0.019487912 = sum of:
0.019487912 = product of:
0.058463734 = sum of:
0.058463734 = weight(_text_:22 in 3117) [ClassicSimilarity], result of:
0.058463734 = score(doc=3117,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.5416616 = fieldWeight in 3117, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.109375 = fieldNorm(doc=3117)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 28. 2.1999 10:48:22
-
Rahmstorf, G.: Information retrieval using conceptual representations of phrases (1994)
0.00
0.0021690698 = product of:
0.017352559 = sum of:
0.017352559 = product of:
0.052057672 = sum of:
0.052057672 = weight(_text_:problem in 7862) [ClassicSimilarity], result of:
0.052057672 = score(doc=7862,freq=4.0), product of:
0.13082431 = queryWeight, product of:
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.030822188 = queryNorm
0.39792046 = fieldWeight in 7862, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.046875 = fieldNorm(doc=7862)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Abstract
- The information retrieval problem is described starting from an analysis of the concepts 'user's information request' and 'information offerings of texts'. It is shown that natural language phrases are a more adequate medium for expressing information requests and information offerings than character string based query and indexing languages complemented by Boolean oprators. The phrases must be represented as concepts to reach a language invariant level for rule based relevance analysis. The special type of representation called advanced thesaurus is used for the semantic representation of natural language phrases and for relevance processing. The analysis of the retrieval problem leads to a symmetric system structure
-
Byrne, C.C.; McCracken, S.A.: ¬An adaptive thesaurus employing semantic distance, relational inheritance and nominal compound interpretation for linguistic support of information retrieval (1999)
0.00
0.0020879905 = product of:
0.016703924 = sum of:
0.016703924 = product of:
0.05011177 = sum of:
0.05011177 = weight(_text_:22 in 4483) [ClassicSimilarity], result of:
0.05011177 = score(doc=4483,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.46428138 = fieldWeight in 4483, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.09375 = fieldNorm(doc=4483)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 15. 3.2000 10:22:37
-
Stede, M.: Lexicalization in natural language generation : a survey (1994/95)
0.00
0.0020450184 = product of:
0.016360147 = sum of:
0.016360147 = product of:
0.04908044 = sum of:
0.04908044 = weight(_text_:problem in 1913) [ClassicSimilarity], result of:
0.04908044 = score(doc=1913,freq=2.0), product of:
0.13082431 = queryWeight, product of:
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.030822188 = queryNorm
0.375163 = fieldWeight in 1913, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.0625 = fieldNorm(doc=1913)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Abstract
- In natural language generation, a meaning representation of some kind is successively transformed into a sentence or a text. Naturally, a central subtask of this problem is the choice of words, or lexicalization. Proposes 4 major issues that determine how a generator tackles lexicalization, and surveys the contributions that research have made to them. Identifies open problems, and sketches a possible direction for research
-
Hodgson, J.P.E.: Knowledge representation and language in AI (1991)
0.00
0.0018075579 = product of:
0.014460463 = sum of:
0.014460463 = product of:
0.04338139 = sum of:
0.04338139 = weight(_text_:problem in 1529) [ClassicSimilarity], result of:
0.04338139 = score(doc=1529,freq=4.0), product of:
0.13082431 = queryWeight, product of:
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.030822188 = queryNorm
0.33160037 = fieldWeight in 1529, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.0390625 = fieldNorm(doc=1529)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Abstract
- The aim of this book is to highlight the relationship between knowledge representation and language in artificial intelligence, and in particular on the way in which the choice of representation influences the language used to discuss a problem - and vice versa. Opening with a discussion of knowledge representation methods, and following this with a look at reasoning methods, the author begins to make his case for the intimate relationship between language and representation. He shows how each representation method fits particularly well with some reasoning methods and less so with others, using specific languages as examples. The question of representation change, an important and complex issue about which very little is known, is addressed. Dr Hodgson gathers together recent work on problem solving, showing how, in some cases, it has been possible to use representation changes to recast problems into a language that makes them easier to solve. The author maintains throughout that the relationships that this book explores lie at the heart of the construction of large systems, examining a number of the current large AI systems from the viewpoint of representation and language to prove his point.
-
Czejdo. B.D.; Tucci, R.P.: ¬A dataflow graphical language for database applications (1994)
0.00
0.0017557865 = product of:
0.014046292 = sum of:
0.014046292 = product of:
0.042138875 = sum of:
0.042138875 = weight(_text_:29 in 559) [ClassicSimilarity], result of:
0.042138875 = score(doc=559,freq=2.0), product of:
0.108422816 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.030822188 = queryNorm
0.38865322 = fieldWeight in 559, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.078125 = fieldNorm(doc=559)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 20.10.2000 13:29:46
-
Whitelock, P.; Kilby, K.: Linguistic and computational techniques in machine translation system design : 2nd ed (1995)
0.00
0.0017557865 = product of:
0.014046292 = sum of:
0.014046292 = product of:
0.042138875 = sum of:
0.042138875 = weight(_text_:29 in 1750) [ClassicSimilarity], result of:
0.042138875 = score(doc=1750,freq=2.0), product of:
0.108422816 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.030822188 = queryNorm
0.38865322 = fieldWeight in 1750, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.078125 = fieldNorm(doc=1750)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 29. 3.1996 18:28:09
-
Hutchins, J.: From first conception to first demonstration : the nascent years of machine translation, 1947-1954. A chronology (1997)
0.00
0.0017399922 = product of:
0.013919937 = sum of:
0.013919937 = product of:
0.04175981 = sum of:
0.04175981 = weight(_text_:22 in 1463) [ClassicSimilarity], result of:
0.04175981 = score(doc=1463,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.38690117 = fieldWeight in 1463, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.078125 = fieldNorm(doc=1463)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 31. 7.1996 9:22:19
-
Sebastiani, F.: ¬A tutorial an automated text categorisation (1999)
0.00
0.0015337638 = product of:
0.012270111 = sum of:
0.012270111 = product of:
0.03681033 = sum of:
0.03681033 = weight(_text_:problem in 3390) [ClassicSimilarity], result of:
0.03681033 = score(doc=3390,freq=2.0), product of:
0.13082431 = queryWeight, product of:
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.030822188 = queryNorm
0.28137225 = fieldWeight in 3390, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.244485 = idf(docFreq=1723, maxDocs=44218)
0.046875 = fieldNorm(doc=3390)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Abstract
- The automated categorisation (or classification) of texts into topical categories has a long history, dating back at least to 1960. Until the late '80s, the dominant approach to the problem involved knowledge-engineering automatic categorisers, i.e. manually building a set of rules encoding expert knowledge an how to classify documents. In the '90s, with the booming production and availability of on-line documents, automated text categorisation has witnessed an increased and renewed interest. A newer paradigm based an machine learning has superseded the previous approach. Within this paradigm, a general inductive process automatically builds a classifier by "learning", from a set of previously classified documents, the characteristics of one or more categories; the advantages are a very good effectiveness, a considerable savings in terms of expert manpower, and domain independence. In this tutorial we look at the main approaches that have been taken towards automatic text categorisation within the general machine learning paradigm. Issues of document indexing, classifier construction, and classifier evaluation, will be touched upon.
-
Chiba, K.; Kyojima, M.: Document transformation based on syntax-directed free translation (1995)
0.00
0.0014046291 = product of:
0.011237033 = sum of:
0.011237033 = product of:
0.033711098 = sum of:
0.033711098 = weight(_text_:29 in 4069) [ClassicSimilarity], result of:
0.033711098 = score(doc=4069,freq=2.0), product of:
0.108422816 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.030822188 = queryNorm
0.31092256 = fieldWeight in 4069, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.0625 = fieldNorm(doc=4069)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Source
- Electronic publishing. 8(1995) no.1, S.15-29
-
Wanner, L.: Lexical choice in text generation and machine translation (1996)
0.00
0.0013919937 = product of:
0.01113595 = sum of:
0.01113595 = product of:
0.03340785 = sum of:
0.03340785 = weight(_text_:22 in 8521) [ClassicSimilarity], result of:
0.03340785 = score(doc=8521,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.30952093 = fieldWeight in 8521, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=8521)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 31. 7.1996 9:22:19
-
Riloff, E.: ¬An empirical study of automated dictionary construction for information extraction in three domains (1996)
0.00
0.0013919937 = product of:
0.01113595 = sum of:
0.01113595 = product of:
0.03340785 = sum of:
0.03340785 = weight(_text_:22 in 6752) [ClassicSimilarity], result of:
0.03340785 = score(doc=6752,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.30952093 = fieldWeight in 6752, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=6752)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 6. 3.1997 16:22:15
-
Basili, R.; Pazienza, M.T.; Velardi, P.: ¬An empirical symbolic approach to natural language processing (1996)
0.00
0.0013919937 = product of:
0.01113595 = sum of:
0.01113595 = product of:
0.03340785 = sum of:
0.03340785 = weight(_text_:22 in 6753) [ClassicSimilarity], result of:
0.03340785 = score(doc=6753,freq=2.0), product of:
0.10793405 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030822188 = queryNorm
0.30952093 = fieldWeight in 6753, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=6753)
0.33333334 = coord(1/3)
0.125 = coord(1/8)
- Date
- 6. 3.1997 16:22:15
