Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "natural language processing" wg kryterium: Wszystkie pola

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 67
Tytuł:
Benchmarking high performance architectures with natural language processing algorithms
Benchmarking architektur wysokiej wydajności algorytmami przetwarzania języka naturalnego
Autorzy:
Kuta, M.
Kitowski, J.
Powiązania:
https://bibliotekanauki.pl/articles/305469.pdf
Data publikacji:
2011
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
benchmarking
tagowanie częściami mowy
klasteryzacja dokumentów
przetwarzanie języka naturalnego
architektury wysokiej wydajności
part-of-speech tagging
document clustering
natural language processing
high performance architectures
Opis:
Natural Language Processing algorithms are resource demanding, especially when tuning to inflective language like Polish is needed. The paper presents time and memory requirements of part of speech tagging and clustering algorithms applied to two corpora of the Polish language. The algorithms are benchmarked on three high performance platforms of different architectures. Additionally sequential versions and OpenMP implementations of clustering algorithms were compared.
Algorytmy przetwarzania języka naturalnego mają duże zapotrzebowanie na zasoby komputerowe, szczególnie gdy wymagane jest dostosowanie algorytmu do języka fleksyjnego jakim jest np. język polski. Artykuł przedstawia wymagania czasowe i pamięciowe algorytmów tagowania częściami mowy oraz algorytmów klasteryzacji zastosowanych do dwóch korpusów języka polskiego. Dokonano benchmarkingu algorytmów na trzech platformach wysokiej wydajności reprezentujących różne architektury. Dodatkowo porównano wersję sekwencyjną oraz implementacje OpenMP algorytmów klasteryzacji.
Źródło:
Computer Science; 2011, 12; 19-31
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Sémantique lexicale et corpus : l’étude du lexique transdisciplinaire des écrits scientifiques
Autorzy:
Tutin, Agnès
Powiązania:
https://bibliotekanauki.pl/articles/605411.pdf
Data publikacji:
2008
Wydawca:
Uniwersytet Marii Curie-Skłodowskiej. Wydawnictwo Uniwersytetu Marii Curie-Skłodowskiej
Tematy:
corpus linguistics
natural language processing
Opis:
This paper deals with a corpus-based linguistic study in lexical semantics. Our topic is the general scientific lexicon, the cross-disciplinary lexicon peculiar to the academic genre. We show how the use of a large corpus enables to develop an inventory of this vocabulary and present the first semantic treatments performed with the help of the corpus, with a first experiment in natural language processing..
Źródło:
Lublin Studies in Modern Languages and Literature; 2008, 32; 242-260
0137-4699
Pojawia się w:
Lublin Studies in Modern Languages and Literature
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Traitement automatique de la polysémie
Machine-made treatment of polysemy
Autorzy:
Gross, Gaston
Powiązania:
https://bibliotekanauki.pl/articles/1048808.pdf
Data publikacji:
2015-01-01
Wydawca:
Uniwersytet im. Adama Mickiewicza w Poznaniu
Tematy:
polysemy
natural language processing
lexicon-grammar
Opis:
It has been an empirical fact that almost all the words are polysemous. A standard dictionary such as the Petit Robert lists 60,000 entries which correspond to 300,000 meanings. Thus, in this particular dictionary one word is paired with five different senses on average. Moreover, what is being dealt with here is no more than a general reference work, designed for a daily use. It contains only most frequent and general items, but disregards all other available meanings. In what follows, contextual properties will be demonstrated to be able to set apart each instance of polysemy, thus offering an effectual tool likely to do away with ambiguities.
Źródło:
Studia Romanica Posnaniensia; 2015, 42, 1; 15-33
0137-2475
2084-4158
Pojawia się w:
Studia Romanica Posnaniensia
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Fantinuoli, Claudio (Hg.) (2018): Interpreting and technology. (Translation and Multilingual Natural Language Processing 11). Berlin: Language Science Press. 149 S.
Autorzy:
Ustaszewski, Michael
Powiązania:
https://bibliotekanauki.pl/articles/1191732.pdf
Data publikacji:
2020
Wydawca:
Uniwersytet Wrocławski. Oficyna Wydawnicza ATUT – Wrocławskie Wydawnictwo Oświatowe
Źródło:
Studia Translatorica; 2020, 11; 212-218
2084-3321
2657-4802
Pojawia się w:
Studia Translatorica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Specialized fully automatic machine translation system delivering high quality of translated texts
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/1943201.pdf
Data publikacji:
2009
Wydawca:
Politechnika Gdańska
Tematy:
natural language processing
machine translation
translation patterns
Opis:
The paper concerns machine translation systems that form a discipline of computer science and are aimed at writing computer programs that are able to translate text between natural languages. In the paper the author argues that it is not possible to build a machine translation system that would be able to translate any kind of documents with a sufficiently high quality. Instead, the author proposes a specialized machine translation system the aim of which is to translate financial reports concerning the global currency exchange market – forex. For the purpose of building the above mentioned system, the author has proposed his own machine translation method of translation patterns. The translation patterns allow transferring the translation process from the level of single words to the level of words chunks. The translation patterns play a very important role in the case of such an inflectional language as Polish because they make it possible to choose the correct form of Polish translation of foreign phrases depending whether they perform the verb or object function in the sentence. The high quality of the specialized machine translation system developed by the author was proved with many experiments the results of which are demonstrated in the paper. The quality of translation is so high that the Polish translations of English reports from the global currency exchange market can be published on Web pages without any additional changes. Thus, it is possible to totally eliminate the human translator from the process of translation of texts which are highly stereotypical and oriented to a selected and narrow domain.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2009, 13, 4; 347-354
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The Implementation of the example-based machine translation technique for French-to-Polish automatic translation system
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/1986914.pdf
Data publikacji:
2002
Wydawca:
Politechnika Gdańska
Tematy:
natural language processing
computational linguistics
machine translation
Opis:
High-quality machine translation between human languages has for a long time been an unattainable dream for many computer scientists involved in this fascinating and interdisciplinary field of computer application. The developed quite recently example-based machine translation technique seems to be a serious alternative to the existing automatic translation techniques. In the paper the usage of the example based machine translation technique for the development of system which would be able to translate an unrestricted French text into Polish is proposed. The new approach to the example-based machine translation technique that takes into account the peculiarity of the Polish grammar is developed. The obtained primary results of the development of the proposed system seem to be very promising and appear to be a step made in the right direction towards a fully-automatic high quality French-into-Polish machine translation system for unrestricted text.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2002, 6, 3; 523-544
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of linguistic cues in the analysis of language of hate groups
Autorzy:
Balcerzak, B.
Jaworski, W.
Powiązania:
https://bibliotekanauki.pl/articles/952938.pdf
Data publikacji:
2015
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
hate speech
natural language processing
propaganda
machine learning
Opis:
Hate speech and fringe ideologies are social phenomena that thrive on-line. Members of the political and religious fringe are able to propagate their ideas via the Internet with less effort than in traditional media. In this article, we attempt to use linguistic cues such as the occurrence of certain parts of speech in order to distinguish the language of fringe groups from strictly informative sources. The aim of this research is to provide a preliminary model for identifying deceptive materials online. Examples of these would include aggressive marketing and hate speech. For the sake of this paper, we aim to focus on the political aspect. Our research has shown that information about sentence length and the occurrence of adjectives and adverbs can provide information for the identification of differences between the language of fringe political groups and mainstream media.
Źródło:
Computer Science; 2015, 16 (2); 145-156
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Compressing sentiment analysis CNN models for efficient hardware processing
Autorzy:
Wróbel, Krzysztof
Karwatowski, Michał
Wielgosz, Maciej
Pietroń, Marcin
Wiatr, Kazimierz
Powiązania:
https://bibliotekanauki.pl/articles/305234.pdf
Data publikacji:
2020
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
natural language processing
convolutional neural networks
FPGA
compression
Opis:
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after their creation, they were applied to other domains, including natural language processing (NLP). Nowadays, solutions based on artificial intelligence appear on mobile devices and embedded systems, which places constraints on memory and power consumption, among others. Due to CNN memory and computing requirements, it is necessary to compress them in order to be mapped to the hardware. This paper presents the results of the compression of efficient CNNs for sentiment analysis. The main steps involve pruning and quantization. The process of mapping the compressed network to an FPGA and the results of this implementation are described. The conducted simulations showed that the 5-bit width is enough to ensure no drop in accuracy when compared to the floating-point version of the network. Additionally, the memory footprint was significantly reduced (between 85 and 93% as compared to the original model).
Źródło:
Computer Science; 2020, 21 (1); 25-41
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Retrieval and interpretation of textual geolocalized information based on semantic geolocalized relations
Autorzy:
Korczyński, W.
Powiązania:
https://bibliotekanauki.pl/articles/305820.pdf
Data publikacji:
2015
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
geolocalization
geolocalized dictionary
geolocalized relations
natural language processing
Opis:
This paper describes a method for geolocalized information retrieval from natural language text and its interpretation by assigning it geographic coordinates. Proof-of-concept implementation is discussed, along with a geolocalized dictionary stored in a PostGIS/PostgreSQL spatial relational database. The discussed research focuses on the strongly inflectional Polish language; hence, additional complexity had to be taken into account. The presented method has been evaluated with the use of diverse metrics.
Źródło:
Computer Science; 2015, 16 (4); 395-414
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Knowledge graphs effectiveness in Neural Machine Translation improvement
Autorzy:
Ahmadnia, Benyamin
Dorr, Bonnie J.
Kordjamshidi, Parisa
Powiązania:
https://bibliotekanauki.pl/articles/1839251.pdf
Data publikacji:
2020
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
natural language processing
neural machine translation
knowledge graph representation
Opis:
Maintaining semantic relations between words during the translation process yields more accurate target-language output from Neural Machine Translation (NMT). Although difficult to achieve from training data alone, it is possible to leverage Knowledge Graphs (KGs) to retain source-language semantic relations in the corresponding target-language translation. The core idea is to use KG entity relations as embedding constraints to improve the mapping from source to target. This paper describes two embedding constraints, both of which employ Entity Linking (EL)—assigning a unique identity to entities—to associate words in training sentences with those in the KG: (1) a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG; and (2) a bilingual embedding constraint that forces entity relations in the source-language to be carried over to the corresponding entities in the target-language translation. The method is evaluated for English-Spanish translation exploiting Freebase as a source of knowledge. Our experimental results demonstrate that exploiting KG information not only decreases the number of unknown words in the translation but also improves translation quality
Źródło:
Computer Science; 2020, 21 (3); 299-318
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Cluo: web-scale text mining system for open source intelligence purposes
Autorzy:
Maciołek, P.
Dobrowolski, G.
Powiązania:
https://bibliotekanauki.pl/articles/305361.pdf
Data publikacji:
2013
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
text mining
big data
OSINT
natural language processing
monitoring
Opis:
The amount of textual information published on the Internet is considered to be in billions of web pages, blog posts, comments, social media updates and others. Analyzing such quantities of data requires high level of distribution – both data and computing. This is especially true in case of complex algorithms, often used in text mining tasks. The paper presents a prototype implementation of CLUO – an Open Source Intelligence (OSINT) system, which extracts and analyzes significant quantities of openly available information.
Źródło:
Computer Science; 2013, 14 (1); 45-62
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An English neural network that learns texts, finds hidden knowledge, and answers questions
Autorzy:
Ke, Y.
Hagiwara, M.
Powiązania:
https://bibliotekanauki.pl/articles/91771.pdf
Data publikacji:
2017
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
natural language processing
neural network
question answering
natural language understanding
Opis:
In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2017, 7, 4; 229-242
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A blackboard system for generating poetry
Autorzy:
Misztal-Radecka, J.
Indurkhya, B.
Powiązania:
https://bibliotekanauki.pl/articles/305325.pdf
Data publikacji:
2016
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
poetry generation
computational creativity
natural language processing
multi-agent system
Opis:
We present a system to generate poems based on the information extracted from input text such as blog posts. Our design uses the blackboard architecture, in which independent specialized modules cooperate during the generation process by sharing a common workspace known as the blackboard. Each module is responsible for a particular task while generating poetry. Our implementation incorporates modules that retrieve information from the input text, generate new ideas, or select the best partial solutions. These distinct modules (experts) are implemented as diverse computational units that make use of lexical resources, grammar models, sentiment-analyzing tools, and languageprocessing algorithms. A control module is responsible for scheduling actions on the blackboard. We argue that the blackboard architecture is a promising way of simulating creative processes because of its flexibility and compliance with the Global Workspace Theory of mind. The main contribution of this work is the design and prototype implementation of an extensible platform for a poetry-generating system that may be further extended by incorporating new experts as well as some existing poetrygenerating systems as parts of the blackboard architecture. We claim that this design provides a powerful tool for combining many of the existing efforts in the domain of automatic poetry generation.
Źródło:
Computer Science; 2016, 17 (2); 265-294
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Text summarizing in Polish
Streszczanie tekstu w języku polskim
Autorzy:
Branny, E.
Gajęcki, M.
Powiązania:
https://bibliotekanauki.pl/articles/305824.pdf
Data publikacji:
2005
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
przetwarzanie języka naturalnego
streszczanie tekstu
natural language processing
text summarizing
Opis:
The aim of this article is to describe an existing implementation of a text summarizer for Polish, to analyze the results and propose the possibilities of further development. The problem of text summarizing has been already addressed by science but until now there has been no implementation designed for Polish. The implemented algorithm is based on existing developments in the field but it also includes some improvements. It has been optimized for newspaper texts ranging from approx. 10 to 50 sentences. Evaluation has shown that it works better than known generic summarization tools when applied to Polish.
Celem artykułu jest zaprezentowanie algorytmu streszczającego teksty w języku polskim. Mimo istnienia algorytmów streszczających teksty, brak jest algorytmów dedykowanych dla języka polskiego. Przedstawiony algorytm bazuje na istniejących algorytmach streszczania tekstu, ale zawiera kilka ulepszeń. Algorytm jest przeznaczony dla streszczania tekstów prasowych liczących od 10 do 50 zdań. Przeprowadzone testy pokazują, że algorytm działa lepiej od znanych algorytmów zastosowanych dla języka polskiego.
Źródło:
Computer Science; 2005, 7; 31-48
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Swarm algorithms for NLP : the case of limited training data
Autorzy:
Tambouratzis, George
Vassiliou, Marina
Powiązania:
https://bibliotekanauki.pl/articles/1396739.pdf
Data publikacji:
2019
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
particle swarm optimisation
natural language processing
text phrasing
machine translation
Opis:
The present article describes a novel phrasing model which can be used for segmenting sentences of unconstrained text into syntactically-defined phrases. This model is based on the notion of attraction and repulsion forces between adjacent words. Each of these forces is weighed appropriately by system parameters, the values of which are optimised via particle swarm optimisation. This approach is designed to be language-independent and is tested here for different languages. The phrasing model’s performance is assessed per se, by calculating the segmentation accuracy against a golden segmentation. Operational testing also involves integrating the model to a phrase-based Machine Translation (MT) system and measuring the translation quality when the phrasing model is used to segment input text into phrases. Experiments show that the performance of this approach is comparable to other leading segmentation methods and that it exceeds that of baseline systems.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 3; 219-234
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 67

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies