Search (56 results, page 1 of 3)

0.039563164 = product of:
  0.059344746 = sum of:
    0.016919931 = weight(_text_:of in 4888) [ClassicSimilarity], result of:
      0.016919931 = score(doc=4888,freq=2.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.20732689 = fieldWeight in 4888, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.09375 = fieldNorm(doc=4888)
    0.042424813 = product of:
      0.084849626 = sum of:
        0.084849626 = weight(_text_:22 in 4888) [ClassicSimilarity], result of:
          0.084849626 = score(doc=4888,freq=2.0), product of:
            0.18275474 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.05218836 = queryNorm
            0.46428138 = fieldWeight in 4888, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=4888)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Date

1. 3.2013 14:56:22

0.029811531 = product of:
  0.044717297 = sum of:
    0.023928396 = weight(_text_:of in 2697) [ClassicSimilarity], result of:
      0.023928396 = score(doc=2697,freq=16.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.2932045 = fieldWeight in 2697, 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=2697)
    0.020788899 = product of:
      0.041577797 = sum of:
        0.041577797 = weight(_text_:science in 2697) [ClassicSimilarity], result of:
          0.041577797 = score(doc=2697,freq=6.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.30244917 = fieldWeight in 2697, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.046875 = fieldNorm(doc=2697)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

Text mining and natural language processing are fast growing areas of research, with numerous applications in business, science and creative industries. This paper presents TextFlows, a web-based text mining and natural language processing platform supporting workflow construction, sharing and execution. The platform enables visual construction of text mining workflows through a web browser, and the execution of the constructed workflows on a processing cloud. This makes TextFlows an adaptable infrastructure for the construction and sharing of text processing workflows, which can be reused in various applications. The paper presents the implemented text mining and language processing modules, and describes some precomposed workflows. Their features are demonstrated on three use cases: comparison of document classifiers and of different part-of-speech taggers on a text categorization problem, and outlier detection in document corpora.

Content

Vgl.: http://www.sciencedirect.com/science/article/pii/S0167642316000113. Vgl. auch: http://textflows.org.

Source

Science of computer programming. In Press, 2016

0.025708806 = product of:
  0.038563207 = sum of:
    0.02255991 = weight(_text_:of in 3671) [ClassicSimilarity], result of:
      0.02255991 = score(doc=3671,freq=8.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
    0.0160033 = product of:
      0.0320066 = sum of:
        0.0320066 = weight(_text_:science in 3671) [ClassicSimilarity], result of:
          0.0320066 = score(doc=3671,freq=2.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.23282544 = fieldWeight in 3671, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.0625 = fieldNorm(doc=3671)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

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.

0.024048528 = product of:
  0.03607279 = sum of:
    0.022069903 = weight(_text_:of in 267) [ClassicSimilarity], result of:
      0.022069903 = score(doc=267,freq=10.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.2704316 = fieldWeight in 267, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=267)
    0.0140028875 = product of:
      0.028005775 = sum of:
        0.028005775 = weight(_text_:science in 267) [ClassicSimilarity], result of:
          0.028005775 = score(doc=267,freq=2.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.20372227 = fieldWeight in 267, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.0546875 = fieldNorm(doc=267)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

Domain ontologies facilitate the organization, sharing and reuse of domain knowledge, and enable various vertical domain applications to operate successfully. Most methods for automatically constructing ontologies focus on taxonomic relations, such as is-kind-of and is- part-of relations. However, much of the domain-specific semantics is ignored. This work proposes a semi-unsupervised approach for extracting semantic relations from domain-specific text documents. The approach effectively utilizes text mining and existing taxonomic relations in domain ontologies to discover candidate keywords that can represent semantic relations. A preliminary experiment on the natural science domain (Taiwan K9 education) indicates that the proposed method yields valuable recommendations. This work enriches domain ontologies by adding distilled semantics.

Source

Journal of Intelligent Information Systems

0.02305096 = product of:
  0.03457644 = sum of:
    0.024674902 = weight(_text_:of in 923) [ClassicSimilarity], result of:
      0.024674902 = score(doc=923,freq=50.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.3023517 = fieldWeight in 923, product of:
          7.071068 = tf(freq=50.0), with freq of:
            50.0 = termFreq=50.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.02734375 = fieldNorm(doc=923)
    0.009901537 = product of:
      0.019803073 = sum of:
        0.019803073 = weight(_text_:science in 923) [ClassicSimilarity], result of:
          0.019803073 = score(doc=923,freq=4.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.1440534 = fieldWeight in 923, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.02734375 = fieldNorm(doc=923)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

"I still don't know what to think about GPT-4, the new large language model (LLM) from OpenAI. On the one hand it is a remarkable product that easily passes the Turing test. If you ask it questions, via the ChatGPT interface, GPT-4 can easily produce fluid sentences largely indistinguishable from those a person might write. But on the other hand, amid the exceptional levels of hype and anticipation, it's hard to know where GPT-4 and other LLMs truly fit in the larger project of making machines intelligent.
They might appear intelligent, but LLMs are nothing of the sort. They don't understand the meanings of the words they are using, nor the concepts expressed within the sentences they create. When asked how to bring a cow back to life, earlier versions of ChatGPT, for example, which ran on a souped-up version of GPT-3, would confidently provide a list of instructions. So-called hallucinations like this happen because language models have no concept of what a "cow" is or that "death" is a non-reversible state of being. LLMs do not have minds that can think about objects in the world and how they relate to each other. All they "know" is how likely it is that some sets of words will follow other sets of words, having calculated those probabilities from their training data. To make sense of all this, I spoke with Gary Marcus, an emeritus professor of psychology and neural science at New York University, for "Babbage", our science and technology podcast. Last year, as the world was transfixed by the sudden appearance of ChatGPT, he made some fascinating predictions about GPT-4.
He doesn't dismiss the potential of LLMs to become useful assistants in all sorts of ways-Google and Microsoft have already announced that they will be integrating LLMs into their search and office productivity software. But he talked me through some of his criticisms of the technology's apparent capabilities. At the heart of Dr Marcus's thoughtful critique is an attempt to put LLMs into proper context. Deep learning, the underlying technology that makes LLMs work, is only one piece of the puzzle in the quest for machine intelligence. To reach the level of artificial general intelligence (AGI) that many tech companies strive for-i.e. machines that can plan, reason and solve problems in the way human brains can-they will need to deploy a suite of other AI techniques. These include, for example, the kind of "symbolic AI" that was popular before artificial neural networks and deep learning became all the rage.
People use symbols to think about the world: if I say the words "cat", "house" or "aeroplane", you know instantly what I mean. Symbols can also be used to describe the way things are behaving (running, falling, flying) or they can represent how things should behave in relation to each other (a "+" means add the numbers before and after). Symbolic AI is a way to embed this human knowledge and reasoning into computer systems. Though the idea has been around for decades, it fell by the wayside a few years ago as deep learning-buoyed by the sudden easy availability of lots of training data and cheap computing power-became more fashionable. In the near future at least, there's no doubt people will find LLMs useful. But whether they represent a critical step on the path towards AGI, or rather just an intriguing detour, remains to be seen."

0.02203243 = product of:
  0.033048645 = sum of:
    0.02314711 = weight(_text_:of in 1536) [ClassicSimilarity], result of:
      0.02314711 = score(doc=1536,freq=44.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.28363106 = fieldWeight in 1536, product of:
          6.6332498 = tf(freq=44.0), with freq of:
            44.0 = termFreq=44.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.02734375 = fieldNorm(doc=1536)
    0.009901537 = product of:
      0.019803073 = sum of:
        0.019803073 = weight(_text_:science in 1536) [ClassicSimilarity], result of:
          0.019803073 = score(doc=1536,freq=4.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.1440534 = fieldWeight in 1536, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.02734375 = fieldNorm(doc=1536)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

Multiword expressions (MWEs) are lexical items that can be decomposed into single words and display lexical, syntactic, semantic, pragmatic and/or statistical idiosyncrasy (Sag et al., 2002; Kim, 2008; Calzolari et al., 2002). The proper treatment of multiword expressions such as rock 'n' roll and make a decision is essential for many natural language processing (NLP) applications like information extraction and retrieval, terminology extraction and machine translation, and it is important to identify multiword expressions in context. For example, in machine translation we must know that MWEs form one semantic unit, hence their parts should not be translated separately. For this, multiword expressions should be identified first in the text to be translated. The chief aim of this thesis is to develop machine learning-based approaches for the automatic detection of different types of multiword expressions in English and Hungarian natural language texts. In our investigations, we pay attention to the characteristics of different types of multiword expressions such as nominal compounds, multiword named entities and light verb constructions, and we apply novel methods to identify MWEs in raw texts. In the thesis it will be demonstrated that nominal compounds and multiword amed entities may require a similar approach for their automatic detection as they behave in the same way from a linguistic point of view. Furthermore, it will be shown that the automatic detection of light verb constructions can be carried out using two effective machine learning-based approaches.
In this thesis, we focused on the automatic detection of multiword expressions in natural language texts. On the basis of the main contributions, we can argue that: - Supervised machine learning methods can be successfully applied for the automatic detection of different types of multiword expressions in natural language texts. - Machine learning-based multiword expression detection can be successfully carried out for English as well as for Hungarian. - Our supervised machine learning-based model was successfully applied to the automatic detection of nominal compounds from English raw texts. - We developed a Wikipedia-based dictionary labeling method to automatically detect English nominal compounds. - A prior knowledge of nominal compounds can enhance Named Entity Recognition, while previously identified named entities can assist the nominal compound identification process. - The machine learning-based method can also provide acceptable results when it was trained on an automatically generated silver standard corpus. - As named entities form one semantic unit and may consist of more than one word and function as a noun, we can treat them in a similar way to nominal compounds. - Our sequence labelling-based tool can be successfully applied for identifying verbal light verb constructions in two typologically different languages, namely English and Hungarian. - Domain adaptation techniques may help diminish the distance between domains in the automatic detection of light verb constructions. - Our syntax-based method can be successfully applied for the full-coverage identification of light verb constructions. As a first step, a data-driven candidate extraction method can be utilized. After, a machine learning approach that makes use of an extended and rich feature set selects LVCs among extracted candidates. - When a precise syntactic parser is available for the actual domain, the full-coverage identification can be performed better. In other cases, the usage of the sequence labeling method is recommended.

Imprint

Szeged : University of Szeged, Faculty of Science and Informatics, Doctoral School of Computer Science

0.020732109 = product of:
  0.03109816 = sum of:
    0.017095273 = weight(_text_:of in 156) [ClassicSimilarity], result of:
      0.017095273 = score(doc=156,freq=6.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.20947541 = fieldWeight in 156, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=156)
    0.0140028875 = product of:
      0.028005775 = sum of:
        0.028005775 = weight(_text_:science in 156) [ClassicSimilarity], result of:
          0.028005775 = score(doc=156,freq=2.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.20372227 = fieldWeight in 156, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.0546875 = fieldNorm(doc=156)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

In this work, we present the results of research for evaluating a methodology for extracting mathematical terms for precalculus using the techniques for semantically-oriented statistical search. We use the corpus-based approach and the combination of different statistically-based techniques for extracting keywords, collocations and co-occurrences incorporated in the Sketch Engine software. We evaluate the collocations candidate terms for the basic concept function(s) and approve the related methodology by precalculus domain conceptual terms definitions. Finally, we offer a conceptual terms hierarchical representation and discuss the results with respect to their possible applications.

Content

Beitrag für: First World Conference on Innovation and Computer Sciences (INSODE 2011). Vgl.: http://www.sciencedirect.com/science/article/pii/S221201731200103X.

0.010634843 = product of:
  0.03190453 = sum of:
    0.03190453 = weight(_text_:of in 962) [ClassicSimilarity], result of:
      0.03190453 = score(doc=962,freq=16.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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.

0.010306511 = product of:
  0.015459767 = sum of:
    0.00945853 = weight(_text_:of in 3385) [ClassicSimilarity], result of:
      0.00945853 = score(doc=3385,freq=10.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.11589926 = fieldWeight in 3385, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0234375 = fieldNorm(doc=3385)
    0.0060012373 = product of:
      0.012002475 = sum of:
        0.012002475 = weight(_text_:science in 3385) [ClassicSimilarity], result of:
          0.012002475 = score(doc=3385,freq=2.0), product of:
            0.13747036 = queryWeight, product of:
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.05218836 = queryNorm
            0.08730954 = fieldWeight in 3385, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.6341193 = idf(docFreq=8627, maxDocs=44218)
              0.0234375 = fieldNorm(doc=3385)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Content

Mit einem bereits zuvor von Paul Vitanyi und anderen entwickeltem Verfahren, das den Zusammenhang von Objekten misst (normalized information distance - NID ), kann die Nähe zwischen bestimmten Objekten (Bilder, Worte, Muster, Intervalle, Genome, Programme etc.) anhand aller Eigenschaften analysiert und aufgrund der dominanten gemeinsamen Eigenschaft bestimmt werden. Ähnlich können auch die allgemein verwendeten, nicht unbedingt "wahren" Bedeutungen von Namen mit der Google-Suche erschlossen werden. 'At this moment one database stands out as the pinnacle of computer-accessible human knowledge and the most inclusive summary of statistical information: the Google search engine. There can be no doubt that Google has already enabled science to accelerate tremendously and revolutionized the research process. It has dominated the attention of internet users for years, and has recently attracted substantial attention of many Wall Street investors, even reshaping their ideas of company financing.' (Paul Vitanyi und Rudi Cilibrasi) Gibt man ein Wort ein wie beispielsweise "Pferd", erhält man bei Google 4.310.000 indexierte Seiten. Für "Reiter" sind es 3.400.000 Seiten. Kombiniert man beide Begriffe, werden noch 315.000 Seiten erfasst. Für das gemeinsame Auftreten beispielsweise von "Pferd" und "Bart" werden zwar noch immer erstaunliche 67.100 Seiten aufgeführt, aber man sieht schon, dass "Pferd" und "Reiter" enger zusammen hängen. Daraus ergibt sich eine bestimmte Wahrscheinlichkeit für das gemeinsame Auftreten von Begriffen. Aus dieser Häufigkeit, die sich im Vergleich mit der maximalen Menge (5.000.000.000) an indexierten Seiten ergibt, haben die beiden Wissenschaftler eine statistische Größe entwickelt, die sie "normalised Google distance" (NGD) nennen und die normalerweise zwischen 0 und 1 liegt. Je geringer NGD ist, desto enger hängen zwei Begriffe zusammen. "Das ist eine automatische Bedeutungsgenerierung", sagt Vitanyi gegenüber dern New Scientist (4). "Das könnte gut eine Möglichkeit darstellen, einen Computer Dinge verstehen und halbintelligent handeln zu lassen." Werden solche Suchen immer wieder durchgeführt, lässt sich eine Karte für die Verbindungen von Worten erstellen. Und aus dieser Karte wiederum kann ein Computer, so die Hoffnung, auch die Bedeutung der einzelnen Worte in unterschiedlichen natürlichen Sprachen und Kontexten erfassen. So habe man über einige Suchen realisiert, dass ein Computer zwischen Farben und Zahlen unterscheiden, holländische Maler aus dem 17. Jahrhundert und Notfälle sowie Fast-Notfälle auseinander halten oder elektrische oder religiöse Begriffe verstehen könne. Überdies habe eine einfache automatische Übersetzung Englisch-Spanisch bewerkstelligt werden können. Auf diese Weise ließe sich auch, so hoffen die Wissenschaftler, die Bedeutung von Worten erlernen, könne man Spracherkennung verbessern oder ein semantisches Web erstellen und natürlich endlich eine bessere automatische Übersetzung von einer Sprache in die andere realisieren.

0.0094277365 = product of:
  0.028283209 = sum of:
    0.028283209 = product of:
      0.056566417 = sum of:
        0.056566417 = weight(_text_:22 in 1490) [ClassicSimilarity], result of:
          0.056566417 = score(doc=1490,freq=2.0), product of:
            0.18275474 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.05218836 = queryNorm
            0.30952093 = fieldWeight in 1490, 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=1490)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

22. 3.2015 9:30:24

0.0094277365 = product of:
  0.028283209 = sum of:
    0.028283209 = product of:
      0.056566417 = sum of:
        0.056566417 = weight(_text_:22 in 835) [ClassicSimilarity], result of:
          0.056566417 = score(doc=835,freq=2.0), product of:
            0.18275474 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.05218836 = 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)
  0.33333334 = coord(1/3)

Date

29.12.2022 18:22:55

0.0094277365 = product of:
  0.028283209 = sum of:
    0.028283209 = product of:
      0.056566417 = sum of:
        0.056566417 = weight(_text_:22 in 912) [ClassicSimilarity], result of:
          0.056566417 = score(doc=912,freq=2.0), product of:
            0.18275474 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.05218836 = 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)
  0.33333334 = coord(1/3)

Date

16. 3.2023 19:22:55

0.0092100445 = product of:
  0.027630134 = sum of:
    0.027630134 = weight(_text_:of in 1161) [ClassicSimilarity], result of:
      0.027630134 = score(doc=1161,freq=12.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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.

0.008917587 = product of:
  0.02675276 = sum of:
    0.02675276 = weight(_text_:of in 330) [ClassicSimilarity], result of:
      0.02675276 = score(doc=330,freq=20.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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

0.008917587 = product of:
  0.02675276 = sum of:
    0.02675276 = weight(_text_:of in 1061) [ClassicSimilarity], result of:
      0.02675276 = score(doc=1061,freq=20.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.32781258 = fieldWeight in 1061, 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=1061)
  0.33333334 = coord(1/3)

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.

0.008917587 = product of:
  0.02675276 = sum of:
    0.02675276 = weight(_text_:of in 869) [ClassicSimilarity], result of:
      0.02675276 = score(doc=869,freq=20.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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

0.008459966 = product of:
  0.025379896 = sum of:
    0.025379896 = weight(_text_:of in 870) [ClassicSimilarity], result of:
      0.025379896 = score(doc=870,freq=18.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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).

0.008459966 = product of:
  0.025379896 = sum of:
    0.025379896 = weight(_text_:of in 871) [ClassicSimilarity], result of:
      0.025379896 = score(doc=871,freq=18.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = queryNorm
        0.3109903 = fieldWeight in 871, 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=871)
  0.33333334 = coord(1/3)

Abstract

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on task-specific datasets. We demonstrate that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText. When conditioned on a document plus questions, the answers generated by the language model reach 55 F1 on the CoQA dataset - matching or exceeding the performance of 3 out of 4 baseline systems without using the 127,000+ training examples. The capacity of the language model is essential to the success of zero-shot task transfer and increasing it improves performance in a log-linear fashion across tasks. Our largest model, GPT-2, is a 1.5B parameter Transformer that achieves state of the art results on 7 out of 8 tested language modeling datasets in a zero-shot setting but still underfits WebText. Samples from the model reflect these improvements and contain coherent paragraphs of text. These findings suggest a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.

0.0084075825 = product of:
  0.025222747 = sum of:
    0.025222747 = weight(_text_:of in 2804) [ClassicSimilarity], result of:
      0.025222747 = score(doc=2804,freq=40.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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]

0.008140607 = product of:
  0.02442182 = sum of:
    0.02442182 = weight(_text_:of in 953) [ClassicSimilarity], result of:
      0.02442182 = score(doc=953,freq=6.0), product of:
        0.08160993 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.05218836 = 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)
  0.33333334 = coord(1/3)

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