-
Stoykova, V.; Petkova, E.: Automatic extraction of mathematical terms for precalculus (2012)
0.00
0.0014588641 = product of:
0.033553872 = sum of:
0.033553872 = sum of:
0.010999122 = weight(_text_:1 in 156) [ClassicSimilarity], result of:
0.010999122 = score(doc=156,freq=2.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.18998542 = fieldWeight in 156, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.0546875 = fieldNorm(doc=156)
0.02255475 = weight(_text_:29 in 156) [ClassicSimilarity], result of:
0.02255475 = score(doc=156,freq=2.0), product of:
0.08290443 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.023567878 = queryNorm
0.27205724 = fieldWeight in 156, 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=156)
0.04347826 = coord(1/23)
- Date
- 29. 5.2012 10:17:08
- Source
- Procedia Technology. 1(2012), S.464-468
-
Griffiths, T.L.; Steyvers, M.: ¬A probabilistic approach to semantic representation (2002)
0.00
7.9247786E-4 = product of:
0.01822699 = sum of:
0.01822699 = product of:
0.03645398 = sum of:
0.03645398 = weight(_text_:29 in 3671) [ClassicSimilarity], result of:
0.03645398 = score(doc=3671,freq=4.0), product of:
0.08290443 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.023567878 = queryNorm
0.43971092 = fieldWeight in 3671, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.0625 = fieldNorm(doc=3671)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Date
- 29. 6.2015 14:55:01
29. 6.2015 16:09:05
-
Rindflesch, T.C.; Aronson, A.R.: Semantic processing in information retrieval (1993)
0.00
4.903207E-4 = product of:
0.011277375 = sum of:
0.011277375 = product of:
0.02255475 = sum of:
0.02255475 = weight(_text_:29 in 4121) [ClassicSimilarity], result of:
0.02255475 = score(doc=4121,freq=2.0), product of:
0.08290443 = queryWeight, product of:
3.5176873 = idf(docFreq=3565, maxDocs=44218)
0.023567878 = queryNorm
0.27205724 = fieldWeight in 4121, 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=4121)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Date
- 29. 6.2015 14:51:28
-
Zadeh, B.Q.; Handschuh, S.: ¬The ACL RD-TEC : a dataset for benchmarking terminology extraction and classification in computational linguistics (2014)
0.00
3.779547E-4 = product of:
0.008692958 = sum of:
0.008692958 = product of:
0.017385917 = sum of:
0.017385917 = weight(_text_:international in 2803) [ClassicSimilarity], result of:
0.017385917 = score(doc=2803,freq=2.0), product of:
0.078619614 = queryWeight, product of:
3.33588 = idf(docFreq=4276, maxDocs=44218)
0.023567878 = queryNorm
0.22113968 = fieldWeight in 2803, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.33588 = idf(docFreq=4276, maxDocs=44218)
0.046875 = fieldNorm(doc=2803)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Source
- Proceedings of the 4th International Workshop on Computational Terminology, Dublin, Ireland, August 23 2014. COLING 2014. Eds.: Patrick Drouin et al., Dublin, Ireland, 2014-08-23 [https://www.deri.ie/sites/default/files/publications/the-acl-rd-tec.pdf]
-
Shree, P.: ¬The journey of Open AI GPT models (2020)
0.00
3.5498835E-4 = product of:
0.008164732 = sum of:
0.008164732 = product of:
0.016329464 = sum of:
0.016329464 = weight(_text_:1 in 869) [ClassicSimilarity], result of:
0.016329464 = score(doc=869,freq=6.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.28205526 = fieldWeight in 869, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.046875 = fieldNorm(doc=869)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Abstract
- Generative Pre-trained Transformer (GPT) models by OpenAI have taken natural language processing (NLP) community by storm by introducing very powerful language models. These models can perform various NLP tasks like question answering, textual entailment, text summarisation etc. without any supervised training. These language models need very few to no examples to understand the tasks and perform equivalent or even better than the state-of-the-art models trained in supervised fashion. In this article we will cover the journey of these models and understand how they have evolved over a period of 2 years. 1. Discussion of GPT-1 paper (Improving Language Understanding by Generative Pre-training). 2. Discussion of GPT-2 paper (Language Models are unsupervised multitask learners) and its subsequent improvements over GPT-1. 3. Discussion of GPT-3 paper (Language models are few shot learners) and the improvements which have made it one of the most powerful models NLP has seen till date. This article assumes familiarity with the basics of NLP terminologies and transformer architecture.
-
Dias, G.: Multiword unit hybrid extraction (o.J.)
0.00
3.381545E-4 = product of:
0.0077775535 = sum of:
0.0077775535 = product of:
0.015555107 = sum of:
0.015555107 = weight(_text_:1 in 643) [ClassicSimilarity], result of:
0.015555107 = score(doc=643,freq=4.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.26867998 = fieldWeight in 643, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.0546875 = fieldNorm(doc=643)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Abstract
- This paper describes an original hybrid system that extracts multiword unit candidates from part-of-speech tagged corpora. While classical hybrid systems manually define local part-of-speech patterns that lead to the identification of well-known multiword units (mainly compound nouns), our solution automatically identifies relevant syntactical patterns from the corpus. Word statistics are then combined with the endogenously acquired linguistic information in order to extract the most relevant sequences of words. As a result, (1) human intervention is avoided providing total flexibility of use of the system and (2) different multiword units like phrasal verbs, adverbial locutions and prepositional locutions may be identified. The system has been tested on the Brown Corpus leading to encouraging results
- Date
- 1. 3.2013 14:41:57
-
Wordhoard (o.J.)
0.00
2.3911135E-4 = product of:
0.005499561 = sum of:
0.005499561 = product of:
0.010999122 = sum of:
0.010999122 = weight(_text_:1 in 3922) [ClassicSimilarity], result of:
0.010999122 = score(doc=3922,freq=2.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.18998542 = fieldWeight in 3922, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.0546875 = fieldNorm(doc=3922)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Date
- 1. 3.2013 14:36:36
-
Chowdhury, A.; Mccabe, M.C.: Improving information retrieval systems using part of speech tagging (1993)
0.00
2.0495258E-4 = product of:
0.0047139092 = sum of:
0.0047139092 = product of:
0.0094278185 = sum of:
0.0094278185 = weight(_text_:1 in 1061) [ClassicSimilarity], result of:
0.0094278185 = score(doc=1061,freq=2.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.16284466 = fieldWeight in 1061, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.046875 = fieldNorm(doc=1061)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Abstract
- The object of Information Retrieval is to retrieve all relevant documents for a user query and only those relevant documents. Much research has focused on achieving this objective with little regard for storage overhead or performance. In the paper we evaluate the use of Part of Speech Tagging to improve, the index storage overhead and general speed of the system with only a minimal reduction to precision recall measurements. We tagged 500Mbs of the Los Angeles Times 1990 and 1989 document collection provided by TREC for parts of speech. We then experimented to find the most relevant part of speech to index. We show that 90% of precision recall is achieved with 40% of the document collections terms. We also show that this is a improvement in overhead with only a 1% reduction in precision recall.
-
Radford, A.; Narasimhan, K.; Salimans, T.; Sutskever, I.: Improving language understanding by Generative Pre-Training
0.00
2.0495258E-4 = product of:
0.0047139092 = sum of:
0.0047139092 = product of:
0.0094278185 = sum of:
0.0094278185 = weight(_text_:1 in 870) [ClassicSimilarity], result of:
0.0094278185 = score(doc=870,freq=2.0), product of:
0.057894554 = queryWeight, product of:
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.023567878 = queryNorm
0.16284466 = fieldWeight in 870, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.4565027 = idf(docFreq=10304, maxDocs=44218)
0.046875 = fieldNorm(doc=870)
0.5 = coord(1/2)
0.04347826 = coord(1/23)
- Object
- GPT-1
