Search (62 results, page 2 of 4)

  • × theme_ss:"Computerlinguistik"
  • × type_ss:"el"
  1. Brown, T.B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; Agarwal, S.; Herbert-Voss, A.; Krueger, G.; Henighan, T.; Child, R.; Ramesh, A.; Ziegler, D.M.; Wu, J.; Winter, C.; Hesse, C.; Chen, M.; Sigler, E.; Litwin, M.; Gray, S.; Chess, B.; Clark, J.; Berner, C.; McCandlish, S.; Radford, A.; Sutskever, I.; Amodei, D.: Language models are few-shot learners (2020) 0.01 
    0.006294866 = product of:
  0.028326897 = sum of:
    0.011975031 = weight(_text_:of in 872) [ClassicSimilarity], result of:
      0.011975031 = score(doc=872,freq=16.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.19546966 = fieldWeight in 872, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03125 = fieldNorm(doc=872)
    0.016351866 = weight(_text_:systems in 872) [ClassicSimilarity], result of:
      0.016351866 = score(doc=872,freq=2.0), product of:
        0.12039685 = queryWeight, product of:
          3.0731742 = idf(docFreq=5561, maxDocs=44218)
          0.03917671 = queryNorm
        0.1358164 = fieldWeight in 872, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0731742 = idf(docFreq=5561, maxDocs=44218)
          0.03125 = fieldNorm(doc=872)
  0.22222222 = coord(2/9)
    Abstract
    Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.
  2. Menge-Sonnentag, R.: Google veröffentlicht einen Parser für natürliche Sprache (2016) 0.00 
    0.003027667 = product of:
  0.027249003 = sum of:
    0.027249003 = weight(_text_:software in 2941) [ClassicSimilarity], result of:
      0.027249003 = score(doc=2941,freq=2.0), product of:
        0.15541996 = queryWeight, product of:
          3.9671519 = idf(docFreq=2274, maxDocs=44218)
          0.03917671 = queryNorm
        0.17532499 = fieldWeight in 2941, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.9671519 = idf(docFreq=2274, maxDocs=44218)
          0.03125 = fieldNorm(doc=2941)
  0.11111111 = coord(1/9)
    Abstract
    SyntaxNet zerlegt Sätze in ihre grammatikalischen Bestandteile und bestimmt die syntaktischen Beziehungen der Wörter untereinander. Das Framework ist Open Source und als TensorFlow Model implementiert. Ein Parser für natürliche Sprache ist eine Software, die Sätze in ihre grammatikalischen Bestandteile zerlegt. Diese Zerlegung ist notwendig, damit Computer Befehle verstehen oder Texte übersetzen können. Die digitalen Helfer wie Microsofts Cortana, Apples Siri und Google Now verwenden Parser, um Sätze wie "Stell den Wecker auf 5 Uhr!" richtig umzusetzen. SyntaxNet ist ein solcher Parser, den Google als TensorFlow Model veröffentlicht hat. Entwickler können eigene Modelle erstellen, und SnytaxNet bringt einen vortrainierten Parser für die englische Sprache mit, den seine Macher Parsey McParseface genannt haben.
  3. Ramisch, C.; Schreiner, P.; Idiart, M.; Villavicencio, A.: ¬An evaluation of methods for the extraction of multiword expressions (20xx) 0.00 
    0.002661118 = product of:
  0.023950063 = sum of:
    0.023950063 = weight(_text_:of in 962) [ClassicSimilarity], result of:
      0.023950063 = score(doc=962,freq=16.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.39093933 = fieldWeight in 962, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0625 = fieldNorm(doc=962)
  0.11111111 = coord(1/9)
    Abstract
    This paper focuses on the evaluation of some methods for the automatic acquisition of Multiword Expressions (MWEs). First we investigate the hypothesis that MWEs can be detected solely by the distinct statistical properties of their component words, regardless of their type, comparing 3 statistical measures: Mutual Information, Chi**2 and Permutation Entropy. Moreover, we also look at the impact that the addition of type-specific linguistic information has on the performance of these methods.
  4. Artemenko, O.; Shramko, M.: Entwicklung eines Werkzeugs zur Sprachidentifikation in mono- und multilingualen Texten (2005) 0.00 
    0.0026492085 = product of:
  0.023842877 = sum of:
    0.023842877 = weight(_text_:software in 572) [ClassicSimilarity], result of:
      0.023842877 = score(doc=572,freq=2.0), product of:
        0.15541996 = queryWeight, product of:
          3.9671519 = idf(docFreq=2274, maxDocs=44218)
          0.03917671 = queryNorm
        0.15340936 = fieldWeight in 572, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.9671519 = idf(docFreq=2274, maxDocs=44218)
          0.02734375 = fieldNorm(doc=572)
  0.11111111 = coord(1/9)
    Abstract
    Mit der Verbreitung des Internets vermehrt sich die Menge der im World Wide Web verfügbaren Dokumente. Die Gewährleistung eines effizienten Zugangs zu gewünschten Informationen für die Internetbenutzer wird zu einer großen Herausforderung an die moderne Informationsgesellschaft. Eine Vielzahl von Werkzeugen wird bereits eingesetzt, um den Nutzern die Orientierung in der wachsenden Informationsflut zu erleichtern. Allerdings stellt die enorme Menge an unstrukturierten und verteilten Informationen nicht die einzige Schwierigkeit dar, die bei der Entwicklung von Werkzeugen dieser Art zu bewältigen ist. Die zunehmende Vielsprachigkeit von Web-Inhalten resultiert in dem Bedarf an Sprachidentifikations-Software, die Sprache/en von elektronischen Dokumenten zwecks gezielter Weiterverarbeitung identifiziert. Solche Sprachidentifizierer können beispielsweise effektiv im Bereich des Multilingualen Information Retrieval eingesetzt werden, da auf den Sprachidentifikationsergebnissen Prozesse der automatischen Indexbildung wie Stemming, Stoppwörterextraktion etc. aufbauen. In der vorliegenden Arbeit wird das neue System "LangIdent" zur Sprachidentifikation von elektronischen Textdokumenten vorgestellt, das in erster Linie für Lehre und Forschung an der Universität Hildesheim verwendet werden soll. "LangIdent" enthält eine Auswahl von gängigen Algorithmen zu der monolingualen Sprachidentifikation, die durch den Benutzer interaktiv ausgewählt und eingestellt werden können. Zusätzlich wurde im System ein neuer Algorithmus implementiert, der die Identifikation von Sprachen, in denen ein multilinguales Dokument verfasst ist, ermöglicht. Die Identifikation beschränkt sich nicht nur auf eine Aufzählung von gefundenen Sprachen, vielmehr wird der Text in monolinguale Abschnitte aufgeteilt, jeweils mit der Angabe der identifizierten Sprache.
  5. Bager, J.: ¬Die Text-KI ChatGPT schreibt Fachtexte, Prosa, Gedichte und Programmcode (2023) 0.00 
    0.0023590683 = product of:
  0.021231614 = sum of:
    0.021231614 = product of:
      0.042463228 = sum of:
        0.042463228 = weight(_text_:22 in 835) [ClassicSimilarity], result of:
          0.042463228 = score(doc=835,freq=2.0), product of:
            0.13719016 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03917671 = queryNorm
            0.30952093 = fieldWeight in 835, 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=835)
      0.5 = coord(1/2)
  0.11111111 = coord(1/9)
    Date
    29.12.2022 18:22:55
  6. Rieger, F.: Lügende Computer (2023) 0.00 
    0.0023590683 = product of:
  0.021231614 = sum of:
    0.021231614 = product of:
      0.042463228 = sum of:
        0.042463228 = weight(_text_:22 in 912) [ClassicSimilarity], result of:
          0.042463228 = score(doc=912,freq=2.0), product of:
            0.13719016 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03917671 = queryNorm
            0.30952093 = fieldWeight in 912, 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=912)
      0.5 = coord(1/2)
  0.11111111 = coord(1/9)
    Date
    16. 3.2023 19:22:55
  7. Kiela, D.; Clark, S.: Detecting compositionality of multi-word expressions using nearest neighbours in vector space models (2013) 0.00 
    0.002304596 = product of:
  0.020741362 = sum of:
    0.020741362 = weight(_text_:of in 1161) [ClassicSimilarity], result of:
      0.020741362 = score(doc=1161,freq=12.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.33856338 = fieldWeight in 1161, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0625 = fieldNorm(doc=1161)
  0.11111111 = coord(1/9)
    Abstract
    We present a novel unsupervised approach to detecting the compositionality of multi-word expressions. We compute the compositionality of a phrase through substituting the constituent words with their "neighbours" in a semantic vector space and averaging over the distance between the original phrase and the substituted neighbour phrases. Several methods of obtaining neighbours are presented. The results are compared to existing supervised results and achieve state-of-the-art performance on a verb-object dataset of human compositionality ratings.
  8. Sprachtechnologie : ein Überblick (2012) 0.00 
    0.0022710927 = product of:
  0.020439833 = sum of:
    0.020439833 = weight(_text_:systems in 1750) [ClassicSimilarity], result of:
      0.020439833 = score(doc=1750,freq=2.0), product of:
        0.12039685 = queryWeight, product of:
          3.0731742 = idf(docFreq=5561, maxDocs=44218)
          0.03917671 = queryNorm
        0.1697705 = fieldWeight in 1750, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0731742 = idf(docFreq=5561, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1750)
  0.11111111 = coord(1/9)
    Abstract
    Seit mehr als einem halben Jahrhundert existieren ernsthafte und ernst zu nehmende Versuche, menschliche Sprache maschinell zu verarbeiten. Maschinelle Übersetzung oder "natürliche" Dialoge mit Computern gehören zu den ersten Ideen, die den Bereich der späteren Computerlinguistik oder Sprachtechnologie abgesteckt und deren Vorhaben geleitet haben. Heute ist dieser auch maschinelle Sprachverarbeitung (natural language processing, NLP) genannte Bereich stark ausdiversifiziert: Durch die rapide Entwicklung der Informatik ist vieles vorher Unvorstellbare Realität (z. B. automatische Telefonauskunft), einiges früher Unmögliche immerhin möglich geworden (z. B. Handhelds mit Sprachein- und -ausgabe als digitale persönliche (Informations-)Assistenten). Es gibt verschiedene Anwendungen der Computerlinguistik, von denen einige den Sprung in die kommerzielle Nutzung geschafft haben (z. B. Diktiersysteme, Textklassifikation, maschinelle Übersetzung). Immer noch wird an natürlichsprachlichen Systemen (natural language systems, NLS) verschiedenster Funktionalität (z. B. zur Beantwortung beliebiger Fragen oder zur Generierung komplexer Texte) intensiv geforscht, auch wenn die hoch gesteckten Ziele von einst längst nicht erreicht sind (und deshalb entsprechend "heruntergefahren" wurden). Wo die maschinelle Sprachverarbeitung heute steht, ist allerdings angesichts der vielfältigen Aktivitäten in der Computerlinguistik und Sprachtechnologie weder offensichtlich noch leicht in Erfahrung zu bringen (für Studierende des Fachs und erst recht für Laien). Ein Ziel dieses Buches ist, es, die aktuelle Literaturlage in dieser Hinsicht zu verbessern, indem spezifisch systembezogene Aspekte der Computerlinguistik als Überblick über die Sprachtechnologie zusammengetragen werden.
  9. Altmann, E.G.; Cristadoro, G.; Esposti, M.D.: On the origin of long-range correlations in texts (2012) 0.00 
    0.0022314154 = product of:
  0.020082738 = sum of:
    0.020082738 = weight(_text_:of in 330) [ClassicSimilarity], result of:
      0.020082738 = score(doc=330,freq=20.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.32781258 = fieldWeight in 330, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=330)
  0.11111111 = coord(1/9)
    Abstract
    The complexity of human interactions with social and natural phenomena is mirrored in the way we describe our experiences through natural language. In order to retain and convey such a high dimensional information, the statistical properties of our linguistic output has to be highly correlated in time. An example are the robust observations, still largely not understood, of correlations on arbitrary long scales in literary texts. In this paper we explain how long-range correlations flow from highly structured linguistic levels down to the building blocks of a text (words, letters, etc..). By combining calculations and data analysis we show that correlations take form of a bursty sequence of events once we approach the semantically relevant topics of the text. The mechanisms we identify are fairly general and can be equally applied to other hierarchical settings.
    Source
    Proceedings of the National Academy of Sciences, 2. Juli 2012. DOI: 10.1073/pnas.1117723109
  10. Shree, P.: ¬The journey of Open AI GPT models (2020) 0.00 
    0.0022314154 = product of:
  0.020082738 = sum of:
    0.020082738 = weight(_text_:of in 869) [ClassicSimilarity], result of:
      0.020082738 = score(doc=869,freq=20.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.32781258 = fieldWeight in 869, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=869)
  0.11111111 = coord(1/9)
    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.
    Source
    https://medium.com/walmartglobaltech/the-journey-of-open-ai-gpt-models-32d95b7b7fb2
  11. Radford, A.; Narasimhan, K.; Salimans, T.; Sutskever, I.: Improving language understanding by Generative Pre-Training 0.00 
    0.0021169065 = product of:
  0.019052157 = sum of:
    0.019052157 = weight(_text_:of in 870) [ClassicSimilarity], result of:
      0.019052157 = score(doc=870,freq=18.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.3109903 = fieldWeight in 870, product of:
          4.2426405 = tf(freq=18.0), with freq of:
            18.0 = termFreq=18.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=870)
  0.11111111 = coord(1/9)
    Abstract
    Natural language understanding comprises a wide range of diverse tasks such as textual entailment, question answering, semantic similarity assessment, and document classification. Although large unlabeled text corpora are abundant, labeled data for learning these specific tasks is scarce, making it challenging for discriminatively trained models to perform adequately. We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task. In contrast to previous approaches, we make use of task-aware input transformations during fine-tuning to achieve effective transfer while requiring minimal changes to the model architecture. We demonstrate the effectiveness of our approach on a wide range of benchmarks for natural language understanding. Our general task-agnostic model outperforms discriminatively trained models that use architectures specifically crafted for each task, significantly improving upon the state of the art in 9 out of the 12 tasks studied. For instance, we achieve absolute improvements of 8.9% on commonsense reasoning (Stories Cloze Test), 5.7% on question answering (RACE), and 1.5% on textual entailment (MultiNLI).
  12. Bird, S.; Dale, R.; Dorr, B.; Gibson, B.; Joseph, M.; Kan, M.-Y.; Lee, D.; Powley, B.; Radev, D.; Tan, Y.F.: ¬The ACL Anthology Reference Corpus : a reference dataset for bibliographic research in computational linguistics (2008) 0.00 
    0.0021037988 = product of:
  0.018934188 = sum of:
    0.018934188 = weight(_text_:of in 2804) [ClassicSimilarity], result of:
      0.018934188 = score(doc=2804,freq=40.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.3090647 = fieldWeight in 2804, product of:
          6.3245554 = tf(freq=40.0), with freq of:
            40.0 = termFreq=40.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03125 = fieldNorm(doc=2804)
  0.11111111 = coord(1/9)
    Abstract
    The ACL Anthology is a digital archive of conference and journal papers in natural language processing and computational linguistics. Its primary purpose is to serve as a reference repository of research results, but we believe that it can also be an object of study and a platform for research in its own right. We describe an enriched and standardized reference corpus derived from the ACL Anthology that can be used for research in scholarly document processing. This corpus, which we call the ACL Anthology Reference Corpus (ACL ARC), brings together the recent activities of a number of research groups around the world. Our goal is to make the corpus widely available, and to encourage other researchers to use it as a standard testbed for experiments in both bibliographic and bibliometric research.
    Content
    Vgl. auch: Automatic Term Recognition (ATR) is a research task that deals with the identification of domain-specific terms. Terms, in simple words, are textual realization of significant concepts in an expertise domain. Additionally, domain-specific terms may be classified into a number of categories, in which each category represents a significant concept. A term classification task is often defined on top of an ATR procedure to perform such categorization. For instance, in the biomedical domain, terms can be classified as drugs, proteins, and genes. This is a reference dataset for terminology extraction and classification research in computational linguistics. It is a set of manually annotated terms in English language that are extracted from the ACL Anthology Reference Corpus (ACL ARC). The ACL ARC is a canonicalised and frozen subset of scientific publications in the domain of Human Language Technologies (HLT). It consists of 10,921 articles from 1965 to 2006. The dataset, called ACL RD-TEC, is comprised of more than 69,000 candidate terms that are manually annotated as valid and invalid terms. Furthermore, valid terms are classified as technology and non-technology terms. Technology terms refer to a method, process, or in general a technological concept in the domain of HLT, e.g. machine translation, word sense disambiguation, and language modelling. On the other hand, non-technology terms refer to important concepts other than technological; examples of such terms in the domain of HLT are multilingual lexicon, corpora, word sense, and language model. The dataset is created to serve as a gold standard for the comparison of the algorithms of term recognition and classification. [http://catalog.elra.info/product_info.php?products_id=1236].
    Source
    Proceedings of Language Resources and Evaluation Conference (LREC 08). Marrakesh, Morocco, May [http://acl-arc.comp.nus.edu.sg/lrec08.pdf]
  13. Harari, Y.N.: ¬[Yuval-Noah-Harari-argues-that] AI has hacked the operating system of human civilisation (2023) 0.00 
    0.0020369943 = product of:
  0.018332949 = sum of:
    0.018332949 = weight(_text_:of in 953) [ClassicSimilarity], result of:
      0.018332949 = score(doc=953,freq=6.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.2992506 = fieldWeight in 953, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.078125 = fieldNorm(doc=953)
  0.11111111 = coord(1/9)
    Abstract
    Storytelling computers will change the course of human history, says the historian and philosopher.
    Source
    https://www.economist.com/by-invitation/2023/04/28/yuval-noah-harari-argues-that-ai-has-hacked-the-operating-system-of-human-civilisation?giftId=6982bba3-94bc-441d-9153-6d42468817ad
  14. Wordhoard (o.J.) 0.00 
    0.0020165213 = product of:
  0.018148692 = sum of:
    0.018148692 = weight(_text_:of in 3922) [ClassicSimilarity], result of:
      0.018148692 = score(doc=3922,freq=12.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.29624295 = fieldWeight in 3922, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=3922)
  0.11111111 = coord(1/9)
    Abstract
    WordHoard defines a multiword unit as a special type of collocate in which the component words comprise a meaningful phrase. For example, "Knight of the Round Table" is a meaningful multiword unit or phrase. WordHoard uses the notion of a pseudo-bigram to generalize the computation of bigram (two word) statistical measures to phrases (n-grams) longer than two words, and to allow comparisons of these measures for phrases with different word counts. WordHoard applies the localmaxs algorithm of Silva et al. to the pseudo-bigrams to identify potential compositional phrases that "stand out" in a text. WordHoard can also filter two and three word phrases using the word class filters suggested by Justeson and Katz.
  15. Rindflesch, T.C.; Aronson, A.R.: Semantic processing in information retrieval (1993) 0.00 
    0.0020165213 = product of:
  0.018148692 = sum of:
    0.018148692 = weight(_text_:of in 4121) [ClassicSimilarity], result of:
      0.018148692 = score(doc=4121,freq=12.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.29624295 = fieldWeight in 4121, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=4121)
  0.11111111 = coord(1/9)
    Abstract
    Intuition suggests that one way to enhance the information retrieval process would be the use of phrases to characterize the contents of text. A number of researchers, however, have noted that phrases alone do not improve retrieval effectiveness. In this paper we briefly review the use of phrases in information retrieval and then suggest extensions to this paradigm using semantic information. We claim that semantic processing, which can be viewed as expressing relations between the concepts represented by phrases, will in fact enhance retrieval effectiveness. The availability of the UMLS® domain model, which we exploit extensively, significantly contributes to the feasibility of this processing.
  16. WordHoard: finding multiword units (20??) 0.00 
    0.0020165213 = product of:
  0.018148692 = sum of:
    0.018148692 = weight(_text_:of in 1123) [ClassicSimilarity], result of:
      0.018148692 = score(doc=1123,freq=12.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.29624295 = fieldWeight in 1123, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1123)
  0.11111111 = coord(1/9)
    Abstract
    WordHoard defines a multiword unit as a special type of collocate in which the component words comprise a meaningful phrase. For example, "Knight of the Round Table" is a meaningful multiword unit or phrase. WordHoard uses the notion of a pseudo-bigram to generalize the computation of bigram (two word) statistical measures to phrases (n-grams) longer than two words, and to allow comparisons of these measures for phrases with different word counts. WordHoard applies the localmaxs algorithm of Silva et al. to the pseudo-bigrams to identify potential compositional phrases that "stand out" in a text. WordHoard can also filter two and three word phrases using the word class filters suggested by Justeson and Katz.
  17. Sebastiani, F.: ¬A tutorial an automated text categorisation (1999) 0.00 
    0.0019958385 = product of:
  0.017962547 = sum of:
    0.017962547 = weight(_text_:of in 3390) [ClassicSimilarity], result of:
      0.017962547 = score(doc=3390,freq=16.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.2932045 = fieldWeight in 3390, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=3390)
  0.11111111 = coord(1/9)
    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.
    Content
    Aus: Proceedings of THAI-99, European Symposium on Telematics, Hypermedia and Artificial Intelligence
  18. Snajder, J.; Almic, P.: Modeling semantic compositionality of Croatian multiword expressions (2015) 0.00 
    0.0019958385 = product of:
  0.017962547 = sum of:
    0.017962547 = weight(_text_:of in 2920) [ClassicSimilarity], result of:
      0.017962547 = score(doc=2920,freq=16.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.2932045 = fieldWeight in 2920, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=2920)
  0.11111111 = coord(1/9)
    Abstract
    A distinguishing feature of many multiword expressions (MWEs) is their semantic non-compositionality. Determining the semantic compositionality of MWEs is important for many natural language processing tasks. We address the task of modeling semantic compositionality of Croatian MWEs. We adopt a composition-based approach within the distributional semantics framework. We build and evaluate models based on Latent Semantic Analysis and the recently proposed neural network-based Skip-gram model, and experiment with different composition functions. We show that the compositionality scores predicted by the Skip-gram additive models correlate well with human judgments (=0.50). When framed as a classification task, the model achieves an accuracy of 0.64.
    Content
    Vgl. unter: http://takelab.fer.hr/data/cromwesc/. The dataset is available from here: TakeLab-CroMWEsc.tar.gz. The archive contains one file, which contains a list of 200 Croatian multiword expressions annotated with semantic compositionality scores. Twenty expressions were annotated by 24 annotators (denoted by "*") and the rest of them were annotated by 6 annotators. Besides median, we provide mode, mean, and standard deviation for each expression. Consult the above mentioned paper for details.
  19. Lund, B.D.: ¬A brief review of ChatGPT : its value and the underlying GPT technology (2023) 0.00 
    0.0019958385 = product of:
  0.017962547 = sum of:
    0.017962547 = weight(_text_:of in 873) [ClassicSimilarity], result of:
      0.017962547 = score(doc=873,freq=16.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.2932045 = fieldWeight in 873, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=873)
  0.11111111 = coord(1/9)
    Abstract
    In this review paper, ChatGPT, a public tool developed by OpenAI that utilizes GPT technology to fulfill a range of text-based requests is examined. ChatGPT is a sophisticated chatbot capable of understanding and interpreting user requests, generating appropriate responses in nearly natural human language, and completing advanced tasks such as writing thank you letters and addressing productivity issues. The details of how ChatGPT works, as well as the potential impacts of this technology on various industries, are discussed. The concept of Generative Pre-Trained Transformer (GPT), the language model on which ChatGPT is based, is also explored, as well as the process of unsupervised pretraining and supervised fine-tuning that is used to refine the GPT algorithm. A letter written by ChatGPT to a colleague from Iran is presented as an example of the chatbot's capabilities.
  20. Griffiths, T.L.; Steyvers, M.: ¬A probabilistic approach to semantic representation (2002) 0.00 
    0.0018816947 = product of:
  0.016935252 = sum of:
    0.016935252 = weight(_text_:of in 3671) [ClassicSimilarity], result of:
      0.016935252 = score(doc=3671,freq=8.0), product of:
        0.061262865 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.03917671 = queryNorm
        0.27643585 = fieldWeight in 3671, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0625 = fieldNorm(doc=3671)
  0.11111111 = coord(1/9)
    Abstract
    Semantic networks produced from human data have statistical properties that cannot be easily captured by spatial representations. We explore a probabilistic approach to semantic representation that explicitly models the probability with which words occurin diffrent contexts, and hence captures the probabilistic relationships between words. We show that this representation has statistical properties consistent with the large-scale structure of semantic networks constructed by humans, and trace the origins of these properties.
    Content
    Paper, Proceedings of the 24th Annual Conference of the Cognitive Science Society. Vgl. auch: https://cocosci.berkeley.edu/publications.php?author=Steyvers,%20M.

Authors

Years

Languages

  • e 44
  • d 16
  • el 1
  • More… Less…

Types

  • a 39
  • p 5
  • x 2
  • b 1
  • m 1
  • More… Less…

Themes