-
Yang, L.; Chen, H.; Li, Z.; Ding, X.; Wu, X.: Give us the facts : enhancing Large Language Models with knowledge graphs for fact-aware language modeling (2024)
0.68
0.67756915 = sum of:
0.55744135 = product of:
1.1148827 = sum of:
0.4472907 = weight(_text_:3a in 2337) [ClassicSimilarity], result of:
0.4472907 = score(doc=2337,freq=12.0), product of:
0.3914924 = queryWeight, product of:
8.443371 = idf(docFreq=25, maxDocs=44421)
0.046366837 = queryNorm
1.1425271 = fieldWeight in 2337, product of:
3.4641016 = tf(freq=12.0), with freq of:
12.0 = termFreq=12.0
8.443371 = idf(docFreq=25, maxDocs=44421)
0.0390625 = fieldNorm(doc=2337)
0.66759205 = weight(_text_:2c in 2337) [ClassicSimilarity], result of:
0.66759205 = score(doc=2337,freq=12.0), product of:
0.47828194 = queryWeight, product of:
10.315173 = idf(docFreq=3, maxDocs=44421)
0.046366837 = queryNorm
1.3958127 = fieldWeight in 2337, product of:
3.4641016 = tf(freq=12.0), with freq of:
12.0 = termFreq=12.0
10.315173 = idf(docFreq=3, maxDocs=44421)
0.0390625 = fieldNorm(doc=2337)
0.5 = coord(2/4)
0.12012777 = sum of:
0.0068116095 = weight(_text_:a in 2337) [ClassicSimilarity], result of:
0.0068116095 = score(doc=2337,freq=8.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.12740123 = fieldWeight in 2337, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.0390625 = fieldNorm(doc=2337)
0.113316156 = weight(_text_:22 in 2337) [ClassicSimilarity], result of:
0.113316156 = score(doc=2337,freq=26.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.6976949 = fieldWeight in 2337, product of:
5.0990195 = tf(freq=26.0), with freq of:
26.0 = termFreq=26.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.0390625 = fieldNorm(doc=2337)
- Abstract
- Recently, ChatGPT, a representative large language model (LLM), has gained considerable attention. Due to their powerful emergent abilities, recent LLMs are considered as a possible alternative to structured knowledge bases like knowledge graphs (KGs). However, while LLMs are proficient at learning probabilistic language patterns and engaging in conversations with humans, they, like previous smaller pre-trained language models (PLMs), still have difficulty in recalling facts while generating knowledge-grounded contents. To overcome these limitations, researchers have proposed enhancing data-driven PLMs with knowledge-based KGs to incorporate explicit factual knowledge into PLMs, thus improving their performance in generating texts requiring factual knowledge and providing more informed responses to user queries. This paper reviews the studies on enhancing PLMs with KGs, detailing existing knowledge graph enhanced pre-trained language models (KGPLMs) as well as their applications. Inspired by existing studies on KGPLM, this paper proposes enhancing LLMs with KGs by developing knowledge graph-enhanced large language models (KGLLMs). KGLLM provides a solution to enhance LLMs' factual reasoning ability, opening up new avenues for LLM research.
- Content
- Vgl.: https://www.researchgate.net/publication/377869034_Give_Us_the_Facts_Enhancing_Large_Language_Models_with_Knowledge_Graphs_for_Fact-aware_Language_Modeling?_ftx_i=%7B%22rId%22%3A%22e115c0eb-6213-41e0-82a2-95c6efa3329c%22%2C%22tId%22%3A%22PB%3A377869034%22%2C%22p%22%3A0%2C%22iT%22%3A%22click-publication-title%22%2C%22mV%22%3A%220.0.1%22%2C%22mN%22%3A%22FTXMoreLikeThesePublications-rt%22%2C%22rSc%22%3A%22MoreLikeThesePublications%22%7D&_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6InByb2ZpbGUiLCJwYWdlIjoiaG9tZSIsInByZXZpb3VzUGFnZSI6InByb2ZpbGUiLCJwb3NpdGlvbiI6InBhZ2VDb250ZW50In19..
- Type
- a
-
Hotho, A.; Bloehdorn, S.: Data Mining 2004 : Text classification by boosting weak learners based on terms and concepts (2004)
0.10
0.10066952 = sum of:
0.054781698 = product of:
0.21912679 = sum of:
0.21912679 = weight(_text_:3a in 1562) [ClassicSimilarity], result of:
0.21912679 = score(doc=1562,freq=2.0), product of:
0.3914924 = queryWeight, product of:
8.443371 = idf(docFreq=25, maxDocs=44421)
0.046366837 = queryNorm
0.5597217 = fieldWeight in 1562, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
8.443371 = idf(docFreq=25, maxDocs=44421)
0.046875 = fieldNorm(doc=1562)
0.25 = coord(1/4)
0.045887824 = sum of:
0.008173932 = weight(_text_:a in 1562) [ClassicSimilarity], result of:
0.008173932 = score(doc=1562,freq=8.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.15288149 = fieldWeight in 1562, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046875 = fieldNorm(doc=1562)
0.037713893 = weight(_text_:22 in 1562) [ClassicSimilarity], result of:
0.037713893 = score(doc=1562,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.23220688 = fieldWeight in 1562, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046875 = fieldNorm(doc=1562)
- Abstract
- Document representations for text classification are typically based on the classical Bag-Of-Words paradigm. This approach comes with deficiencies that motivate the integration of features on a higher semantic level than single words. In this paper we propose an enhancement of the classical document representation through concepts extracted from background knowledge. Boosting is used for actual classification. Experimental evaluations on two well known text corpora support our approach through consistent improvement of the results.
- Content
- Vgl.: http://www.google.de/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CEAQFjAA&url=http%3A%2F%2Fciteseerx.ist.psu.edu%2Fviewdoc%2Fdownload%3Fdoi%3D10.1.1.91.4940%26rep%3Drep1%26type%3Dpdf&ei=dOXrUMeIDYHDtQahsIGACg&usg=AFQjCNHFWVh6gNPvnOrOS9R3rkrXCNVD-A&sig2=5I2F5evRfMnsttSgFF9g7Q&bvm=bv.1357316858,d.Yms.
- Date
- 8. 1.2013 10:22:32
- Type
- a
-
Noever, D.; Ciolino, M.: ¬The Turing deception (2022)
0.06
0.059351064 = sum of:
0.054781698 = product of:
0.21912679 = sum of:
0.21912679 = weight(_text_:3a in 1863) [ClassicSimilarity], result of:
0.21912679 = score(doc=1863,freq=2.0), product of:
0.3914924 = queryWeight, product of:
8.443371 = idf(docFreq=25, maxDocs=44421)
0.046366837 = queryNorm
0.5597217 = fieldWeight in 1863, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
8.443371 = idf(docFreq=25, maxDocs=44421)
0.046875 = fieldNorm(doc=1863)
0.25 = coord(1/4)
0.004569367 = product of:
0.009138734 = sum of:
0.009138734 = weight(_text_:a in 1863) [ClassicSimilarity], result of:
0.009138734 = score(doc=1863,freq=10.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.1709267 = fieldWeight in 1863, product of:
3.1622777 = tf(freq=10.0), with freq of:
10.0 = termFreq=10.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046875 = fieldNorm(doc=1863)
0.5 = coord(1/2)
- Abstract
- This research revisits the classic Turing test and compares recent large language models such as ChatGPT for their abilities to reproduce human-level comprehension and compelling text generation. Two task challenges- summary and question answering- prompt ChatGPT to produce original content (98-99%) from a single text entry and sequential questions initially posed by Turing in 1950. We score the original and generated content against the OpenAI GPT-2 Output Detector from 2019, and establish multiple cases where the generated content proves original and undetectable (98%). The question of a machine fooling a human judge recedes in this work relative to the question of "how would one prove it?" The original contribution of the work presents a metric and simple grammatical set for understanding the writing mechanics of chatbots in evaluating their readability and statistical clarity, engagement, delivery, overall quality, and plagiarism risks. While Turing's original prose scores at least 14% below the machine-generated output, whether an algorithm displays hints of Turing's true initial thoughts (the "Lovelace 2.0" test) remains unanswerable.
- Source
- https%3A%2F%2Farxiv.org%2Fabs%2F2212.06721&usg=AOvVaw3i_9pZm9y_dQWoHi6uv0EN
- Type
- a
-
Warner, A.J.: Natural language processing (1987)
0.06
0.055734478 = product of:
0.111468956 = sum of:
0.111468956 = sum of:
0.010898576 = weight(_text_:a in 337) [ClassicSimilarity], result of:
0.010898576 = score(doc=337,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.20384198 = fieldWeight in 337, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.125 = fieldNorm(doc=337)
0.10057038 = weight(_text_:22 in 337) [ClassicSimilarity], result of:
0.10057038 = score(doc=337,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.61921835 = fieldWeight in 337, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.125 = fieldNorm(doc=337)
0.5 = coord(1/2)
- Source
- Annual review of information science and technology. 22(1987), S.79-108
- Type
- a
-
Ruge, G.: ¬A spreading activation network for automatic generation of thesaurus relationships (1991)
0.05
0.05225818 = product of:
0.10451636 = sum of:
0.10451636 = sum of:
0.016517276 = weight(_text_:a in 4505) [ClassicSimilarity], result of:
0.016517276 = score(doc=4505,freq=6.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.3089316 = fieldWeight in 4505, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=4505)
0.08799908 = weight(_text_:22 in 4505) [ClassicSimilarity], result of:
0.08799908 = score(doc=4505,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 4505, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=4505)
0.5 = coord(1/2)
- Date
- 8.10.2000 11:52:22
- Source
- Library science with a slant to documentation. 28(1991) no.4, S.125-130
- Type
- a
-
McMahon, J.G.; Smith, F.J.: Improved statistical language model performance with automatic generated word hierarchies (1996)
0.05
0.048767667 = product of:
0.097535335 = sum of:
0.097535335 = sum of:
0.009536254 = weight(_text_:a in 3163) [ClassicSimilarity], result of:
0.009536254 = score(doc=3163,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.17836174 = fieldWeight in 3163, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=3163)
0.08799908 = weight(_text_:22 in 3163) [ClassicSimilarity], result of:
0.08799908 = score(doc=3163,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 3163, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=3163)
0.5 = coord(1/2)
- Source
- Computational linguistics. 22(1996) no.2, S.217-248
- Type
- a
-
Somers, H.: Example-based machine translation : Review article (1999)
0.05
0.048767667 = product of:
0.097535335 = sum of:
0.097535335 = sum of:
0.009536254 = weight(_text_:a in 6671) [ClassicSimilarity], result of:
0.009536254 = score(doc=6671,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.17836174 = fieldWeight in 6671, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=6671)
0.08799908 = weight(_text_:22 in 6671) [ClassicSimilarity], result of:
0.08799908 = score(doc=6671,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 6671, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=6671)
0.5 = coord(1/2)
- Date
- 31. 7.1996 9:22:19
- Type
- a
-
New tools for human translators (1997)
0.05
0.048767667 = product of:
0.097535335 = sum of:
0.097535335 = sum of:
0.009536254 = weight(_text_:a in 2179) [ClassicSimilarity], result of:
0.009536254 = score(doc=2179,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.17836174 = fieldWeight in 2179, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=2179)
0.08799908 = weight(_text_:22 in 2179) [ClassicSimilarity], result of:
0.08799908 = score(doc=2179,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 2179, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=2179)
0.5 = coord(1/2)
- Abstract
- A special issue devoted to the theme of new tools for human tranlators
- Date
- 31. 7.1996 9:22:19
-
Baayen, R.H.; Lieber, H.: Word frequency distributions and lexical semantics (1997)
0.05
0.048767667 = product of:
0.097535335 = sum of:
0.097535335 = sum of:
0.009536254 = weight(_text_:a in 4117) [ClassicSimilarity], result of:
0.009536254 = score(doc=4117,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.17836174 = fieldWeight in 4117, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=4117)
0.08799908 = weight(_text_:22 in 4117) [ClassicSimilarity], result of:
0.08799908 = score(doc=4117,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 4117, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=4117)
0.5 = coord(1/2)
- Date
- 28. 2.1999 10:48:22
- Type
- a
-
¬Der Student aus dem Computer (2023)
0.05
0.048767667 = product of:
0.097535335 = sum of:
0.097535335 = sum of:
0.009536254 = weight(_text_:a in 2081) [ClassicSimilarity], result of:
0.009536254 = score(doc=2081,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.17836174 = fieldWeight in 2081, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.109375 = fieldNorm(doc=2081)
0.08799908 = weight(_text_:22 in 2081) [ClassicSimilarity], result of:
0.08799908 = score(doc=2081,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.54181606 = fieldWeight in 2081, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.109375 = fieldNorm(doc=2081)
0.5 = coord(1/2)
- Date
- 27. 1.2023 16:22:55
- Type
- a
-
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)
0.04
0.04180086 = product of:
0.08360172 = sum of:
0.08360172 = sum of:
0.008173932 = weight(_text_:a in 5483) [ClassicSimilarity], result of:
0.008173932 = score(doc=5483,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.15288149 = fieldWeight in 5483, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.09375 = fieldNorm(doc=5483)
0.075427786 = weight(_text_:22 in 5483) [ClassicSimilarity], result of:
0.075427786 = score(doc=5483,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.46441376 = fieldWeight in 5483, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.09375 = fieldNorm(doc=5483)
0.5 = coord(1/2)
- Date
- 15. 3.2000 10:22:37
- Type
- a
-
Boleda, G.; Evert, S.: Multiword expressions : a pain in the neck of lexical semantics (2009)
0.04
0.04180086 = product of:
0.08360172 = sum of:
0.08360172 = sum of:
0.008173932 = weight(_text_:a in 5888) [ClassicSimilarity], result of:
0.008173932 = score(doc=5888,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.15288149 = fieldWeight in 5888, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.09375 = fieldNorm(doc=5888)
0.075427786 = weight(_text_:22 in 5888) [ClassicSimilarity], result of:
0.075427786 = score(doc=5888,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.46441376 = fieldWeight in 5888, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.09375 = fieldNorm(doc=5888)
0.5 = coord(1/2)
- Date
- 1. 3.2013 14:56:22
-
Monnerjahn, P.: Vorsprung ohne Technik : Übersetzen: Computer und Qualität (2000)
0.04
0.04180086 = product of:
0.08360172 = sum of:
0.08360172 = sum of:
0.008173932 = weight(_text_:a in 6429) [ClassicSimilarity], result of:
0.008173932 = score(doc=6429,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.15288149 = fieldWeight in 6429, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.09375 = fieldNorm(doc=6429)
0.075427786 = weight(_text_:22 in 6429) [ClassicSimilarity], result of:
0.075427786 = score(doc=6429,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.46441376 = fieldWeight in 6429, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.09375 = fieldNorm(doc=6429)
0.5 = coord(1/2)
- Source
- c't. 2000, H.22, S.230-231
- Type
- a
-
Hutchins, J.: From first conception to first demonstration : the nascent years of machine translation, 1947-1954. A chronology (1997)
0.04
0.03732727 = product of:
0.07465454 = sum of:
0.07465454 = sum of:
0.011798055 = weight(_text_:a in 2463) [ClassicSimilarity], result of:
0.011798055 = score(doc=2463,freq=6.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.22066543 = fieldWeight in 2463, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.078125 = fieldNorm(doc=2463)
0.06285649 = weight(_text_:22 in 2463) [ClassicSimilarity], result of:
0.06285649 = score(doc=2463,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.38701147 = fieldWeight in 2463, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.078125 = fieldNorm(doc=2463)
0.5 = coord(1/2)
- Abstract
- Chronicles the early history of applying electronic computers to the task of translating natural languages, from the 1st suggestions by Warren Weaver in Mar 1947 to the 1st demonstration of a working, if limited, program in Jan 1954
- Date
- 31. 7.1996 9:22:19
- Type
- a
-
Lezius, W.; Rapp, R.; Wettler, M.: ¬A morphology-system and part-of-speech tagger for German (1996)
0.04
0.03624478 = product of:
0.07248956 = sum of:
0.07248956 = sum of:
0.009633072 = weight(_text_:a in 2693) [ClassicSimilarity], result of:
0.009633072 = score(doc=2693,freq=4.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.18017256 = fieldWeight in 2693, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.078125 = fieldNorm(doc=2693)
0.06285649 = weight(_text_:22 in 2693) [ClassicSimilarity], result of:
0.06285649 = score(doc=2693,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.38701147 = fieldWeight in 2693, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.078125 = fieldNorm(doc=2693)
0.5 = coord(1/2)
- Date
- 22. 3.2015 9:37:18
- Type
- a
-
Kuhlmann, U.; Monnerjahn, P.: Sprache auf Knopfdruck : Sieben automatische Übersetzungsprogramme im Test (2000)
0.03
0.03483405 = product of:
0.0696681 = sum of:
0.0696681 = sum of:
0.0068116095 = weight(_text_:a in 6428) [ClassicSimilarity], result of:
0.0068116095 = score(doc=6428,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.12740123 = fieldWeight in 6428, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.078125 = fieldNorm(doc=6428)
0.06285649 = weight(_text_:22 in 6428) [ClassicSimilarity], result of:
0.06285649 = score(doc=6428,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.38701147 = fieldWeight in 6428, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.078125 = fieldNorm(doc=6428)
0.5 = coord(1/2)
- Source
- c't. 2000, H.22, S.220-229
- Type
- a
-
Basili, R.; Pazienza, M.T.; Velardi, P.: ¬An empirical symbolic approach to natural language processing (1996)
0.03
0.030591883 = product of:
0.061183766 = sum of:
0.061183766 = sum of:
0.010898576 = weight(_text_:a in 6821) [ClassicSimilarity], result of:
0.010898576 = score(doc=6821,freq=8.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.20384198 = fieldWeight in 6821, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.0625 = fieldNorm(doc=6821)
0.05028519 = weight(_text_:22 in 6821) [ClassicSimilarity], result of:
0.05028519 = score(doc=6821,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.30960917 = fieldWeight in 6821, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.0625 = fieldNorm(doc=6821)
0.5 = coord(1/2)
- Abstract
- Describes and evaluates the results of a large scale lexical learning system, ARISTO-LEX, that uses a combination of probabilisitc and knowledge based methods for the acquisition of selectional restrictions of words in sublanguages. Presents experimental data obtained from different corpora in different doamins and languages, and shows that the acquired lexical data not only have practical applications in natural language processing, but they are useful for a comparative analysis of sublanguages
- Date
- 6. 3.1997 16:22:15
- Type
- a
-
Riloff, E.: ¬An empirical study of automated dictionary construction for information extraction in three domains (1996)
0.03
0.028995823 = product of:
0.057991646 = sum of:
0.057991646 = sum of:
0.0077064573 = weight(_text_:a in 6820) [ClassicSimilarity], result of:
0.0077064573 = score(doc=6820,freq=4.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.14413805 = fieldWeight in 6820, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.0625 = fieldNorm(doc=6820)
0.05028519 = weight(_text_:22 in 6820) [ClassicSimilarity], result of:
0.05028519 = score(doc=6820,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.30960917 = fieldWeight in 6820, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.0625 = fieldNorm(doc=6820)
0.5 = coord(1/2)
- Abstract
- AutoSlog is a system that addresses the knowledge engineering bottleneck for information extraction. AutoSlog automatically creates domain specific dictionaries for information extraction, given an appropriate training corpus. Describes experiments with AutoSlog in terrorism, joint ventures and microelectronics domains. Compares the performance of AutoSlog across the 3 domains, discusses the lessons learned and presents results from 2 experiments which demonstrate that novice users can generate effective dictionaries using AutoSlog
- Date
- 6. 3.1997 16:22:15
- Type
- a
-
Haas, S.W.: Natural language processing : toward large-scale, robust systems (1996)
0.03
0.028995823 = product of:
0.057991646 = sum of:
0.057991646 = sum of:
0.0077064573 = weight(_text_:a in 484) [ClassicSimilarity], result of:
0.0077064573 = score(doc=484,freq=4.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.14413805 = fieldWeight in 484, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.0625 = fieldNorm(doc=484)
0.05028519 = weight(_text_:22 in 484) [ClassicSimilarity], result of:
0.05028519 = score(doc=484,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.30960917 = fieldWeight in 484, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.0625 = fieldNorm(doc=484)
0.5 = coord(1/2)
- Abstract
- State of the art review of natural language processing updating an earlier review published in ARIST 22(1987). Discusses important developments that have allowed for significant advances in the field of natural language processing: materials and resources; knowledge based systems and statistical approaches; and a strong emphasis on evaluation. Reviews some natural language processing applications and common problems still awaiting solution. Considers closely related applications such as language generation and th egeneration phase of machine translation which face the same problems as natural language processing. Covers natural language methodologies for information retrieval only briefly
- Type
- a
-
Wanner, L.: Lexical choice in text generation and machine translation (1996)
0.03
0.027867239 = product of:
0.055734478 = sum of:
0.055734478 = sum of:
0.005449288 = weight(_text_:a in 135) [ClassicSimilarity], result of:
0.005449288 = score(doc=135,freq=2.0), product of:
0.053465806 = queryWeight, product of:
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.046366837 = queryNorm
0.10192099 = fieldWeight in 135, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.1531044 = idf(docFreq=38114, maxDocs=44421)
0.0625 = fieldNorm(doc=135)
0.05028519 = weight(_text_:22 in 135) [ClassicSimilarity], result of:
0.05028519 = score(doc=135,freq=2.0), product of:
0.16241506 = queryWeight, product of:
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.046366837 = queryNorm
0.30960917 = fieldWeight in 135, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5028281 = idf(docFreq=3635, maxDocs=44421)
0.0625 = fieldNorm(doc=135)
0.5 = coord(1/2)
- Date
- 31. 7.1996 9:22:19
- Type
- a
