Search (28 results, page 1 of 2)

  • × year_i:[2020 TO 2030}
  • × theme_ss:"Computerlinguistik"
  1. Noever, D.; Ciolino, M.: ¬The Turing deception (2022) 0.22 
    0.22476827 = product of:
  0.62935114 = sum of:
    0.048411623 = product of:
      0.14523487 = sum of:
        0.14523487 = weight(_text_:3a in 862) [ClassicSimilarity], result of:
          0.14523487 = score(doc=862,freq=2.0), product of:
            0.25841674 = queryWeight, product of:
              8.478011 = idf(docFreq=24, maxDocs=44218)
              0.030480823 = queryNorm
            0.56201804 = fieldWeight in 862, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              8.478011 = idf(docFreq=24, maxDocs=44218)
              0.046875 = fieldNorm(doc=862)
      0.33333334 = coord(1/3)
    0.14523487 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.14523487 = score(doc=862,freq=2.0), product of:
        0.25841674 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.030480823 = queryNorm
        0.56201804 = fieldWeight in 862, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
    0.14523487 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.14523487 = score(doc=862,freq=2.0), product of:
        0.25841674 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.030480823 = queryNorm
        0.56201804 = fieldWeight in 862, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
    0.14523487 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.14523487 = score(doc=862,freq=2.0), product of:
        0.25841674 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.030480823 = queryNorm
        0.56201804 = fieldWeight in 862, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
    0.14523487 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.14523487 = score(doc=862,freq=2.0), product of:
        0.25841674 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.030480823 = queryNorm
        0.56201804 = fieldWeight in 862, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
  0.35714287 = coord(5/14)
    Source
    https%3A%2F%2Farxiv.org%2Fabs%2F2212.06721&usg=AOvVaw3i_9pZm9y_dQWoHi6uv0EN
  2. Aizawa, A.; Kohlhase, M.: Mathematical information retrieval (2021) 0.01 
    0.008238584 = product of:
  0.057670087 = sum of:
    0.014529495 = weight(_text_:information in 667) [ClassicSimilarity], result of:
      0.014529495 = score(doc=667,freq=8.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.27153665 = fieldWeight in 667, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0546875 = fieldNorm(doc=667)
    0.04314059 = weight(_text_:retrieval in 667) [ClassicSimilarity], result of:
      0.04314059 = score(doc=667,freq=8.0), product of:
        0.092201896 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.030480823 = queryNorm
        0.46789268 = fieldWeight in 667, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.0546875 = fieldNorm(doc=667)
  0.14285715 = coord(2/14)
    Abstract
    We present an overview of the NTCIR Math Tasks organized during NTCIR-10, 11, and 12. These tasks are primarily dedicated to techniques for searching mathematical content with formula expressions. In this chapter, we first summarize the task design and introduce test collections generated in the tasks. We also describe the features and main challenges of mathematical information retrieval systems and discuss future perspectives in the field.
    Series
    ¬The Information retrieval series, vol 43
    Source
    Evaluating information retrieval and access tasks. Eds.: Sakai, T., Oard, D., Kando, N. [https://doi.org/10.1007/978-981-15-5554-1_12]
  3. Aydin, Ö.; Karaarslan, E.: OpenAI ChatGPT generated literature review: : digital twin in healthcare (2022) 0.01 
    0.00593579 = product of:
  0.04155053 = sum of:
    0.037399244 = weight(_text_:wide in 851) [ClassicSimilarity], result of:
      0.037399244 = score(doc=851,freq=4.0), product of:
        0.13505316 = queryWeight, product of:
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.030480823 = queryNorm
        0.2769224 = fieldWeight in 851, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.03125 = fieldNorm(doc=851)
    0.004151284 = weight(_text_:information in 851) [ClassicSimilarity], result of:
      0.004151284 = score(doc=851,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.0775819 = fieldWeight in 851, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.03125 = fieldNorm(doc=851)
  0.14285715 = coord(2/14)
    Abstract
    Literature review articles are essential to summarize the related work in the selected field. However, covering all related studies takes too much time and effort. This study questions how Artificial Intelligence can be used in this process. We used ChatGPT to create a literature review article to show the stage of the OpenAI ChatGPT artificial intelligence application. As the subject, the applications of Digital Twin in the health field were chosen. Abstracts of the last three years (2020, 2021 and 2022) papers were obtained from the keyword "Digital twin in healthcare" search results on Google Scholar and paraphrased by ChatGPT. Later on, we asked ChatGPT questions. The results are promising; however, the paraphrased parts had significant matches when checked with the Ithenticate tool. This article is the first attempt to show the compilation and expression of knowledge will be accelerated with the help of artificial intelligence. We are still at the beginning of such advances. The future academic publishing process will require less human effort, which in turn will allow academics to focus on their studies. In future studies, we will monitor citations to this study to evaluate the academic validity of the content produced by the ChatGPT. 1. Introduction OpenAI ChatGPT (ChatGPT, 2022) is a chatbot based on the OpenAI GPT-3 language model. It is designed to generate human-like text responses to user input in a conversational context. OpenAI ChatGPT is trained on a large dataset of human conversations and can be used to create responses to a wide range of topics and prompts. The chatbot can be used for customer service, content creation, and language translation tasks, creating replies in multiple languages. OpenAI ChatGPT is available through the OpenAI API, which allows developers to access and integrate the chatbot into their applications and systems. OpenAI ChatGPT is a variant of the GPT (Generative Pre-trained Transformer) language model developed by OpenAI. It is designed to generate human-like text, allowing it to engage in conversation with users naturally and intuitively. OpenAI ChatGPT is trained on a large dataset of human conversations, allowing it to understand and respond to a wide range of topics and contexts. It can be used in various applications, such as chatbots, customer service agents, and language translation systems. OpenAI ChatGPT is a state-of-the-art language model able to generate coherent and natural text that can be indistinguishable from text written by a human. As an artificial intelligence, ChatGPT may need help to change academic writing practices. However, it can provide information and guidance on ways to improve people's academic writing skills.
  4. Zaitseva, E.M.: Developing linguistic tools of thematic search in library information systems (2023) 0.01 
    0.005909047 = product of:
  0.04136333 = sum of:
    0.014677006 = weight(_text_:information in 1187) [ClassicSimilarity], result of:
      0.014677006 = score(doc=1187,freq=16.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.27429342 = fieldWeight in 1187, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1187)
    0.026686322 = weight(_text_:retrieval in 1187) [ClassicSimilarity], result of:
      0.026686322 = score(doc=1187,freq=6.0), product of:
        0.092201896 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.030480823 = queryNorm
        0.28943354 = fieldWeight in 1187, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1187)
  0.14285715 = coord(2/14)
    Abstract
    Within the R&D program "Information support of research by scientists and specialists on the basis of RNPLS&T Open Archive - the system of scientific knowledge aggregation", the RNPLS&T analyzes the use of linguistic tools of thematic search in the modern library information systems and the prospects for their development. The author defines the key common characteristics of e-catalogs of the largest Russian libraries revealed at the first stage of the analysis. Based on the specified common characteristics and detailed comparison analysis, the author outlines and substantiates the vectors for enhancing search inter faces of e-catalogs. The focus is made on linguistic tools of thematic search in library information systems; the key vectors are suggested: use of thematic search at different search levels with the clear-cut level differentiation; use of combined functionality within thematic search system; implementation of classification search in all e-catalogs; hierarchical representation of classifications; use of the matching systems for classification information retrieval languages, and in the long term classification and verbal information retrieval languages, and various verbal information retrieval languages. The author formulates practical recommendations to improve thematic search in library information systems.
  5. Tao, J.; Zhou, L.; Hickey, K.: Making sense of the black-boxes : toward interpretable text classification using deep learning models (2023) 0.01 
    0.0054636686 = product of:
  0.038245678 = sum of:
    0.033056572 = weight(_text_:wide in 990) [ClassicSimilarity], result of:
      0.033056572 = score(doc=990,freq=2.0), product of:
        0.13505316 = queryWeight, product of:
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.030480823 = queryNorm
        0.24476713 = fieldWeight in 990, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
    0.005189105 = weight(_text_:information in 990) [ClassicSimilarity], result of:
      0.005189105 = score(doc=990,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.09697737 = fieldWeight in 990, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
  0.14285715 = coord(2/14)
    Abstract
    Text classification is a common task in data science. Despite the superior performances of deep learning based models in various text classification tasks, their black-box nature poses significant challenges for wide adoption. The knowledge-to-action framework emphasizes several principles concerning the application and use of knowledge, such as ease-of-use, customization, and feedback. With the guidance of the above principles and the properties of interpretable machine learning, we identify the design requirements for and propose an interpretable deep learning (IDeL) based framework for text classification models. IDeL comprises three main components: feature penetration, instance aggregation, and feature perturbation. We evaluate our implementation of the framework with two distinct case studies: fake news detection and social question categorization. The experiment results provide evidence for the efficacy of IDeL components in enhancing the interpretability of text classification models. Moreover, the findings are generalizable across binary and multi-label, multi-class classification problems. The proposed IDeL framework introduce a unique iField perspective for building trusted models in data science by improving the transparency and access to advanced black-box models.
    Source
    Journal of the Association for Information Science and Technology. 74(2023) no.6, S.685-700
  6. Schaer, P.: Sprachmodelle und neuronale Netze im Information Retrieval (2023) 0.00 
    0.0048606894 = product of:
  0.034024823 = sum of:
    0.007338503 = weight(_text_:information in 799) [ClassicSimilarity], result of:
      0.007338503 = score(doc=799,freq=4.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13714671 = fieldWeight in 799, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=799)
    0.026686322 = weight(_text_:retrieval in 799) [ClassicSimilarity], result of:
      0.026686322 = score(doc=799,freq=6.0), product of:
        0.092201896 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.030480823 = queryNorm
        0.28943354 = fieldWeight in 799, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.0390625 = fieldNorm(doc=799)
  0.14285715 = coord(2/14)
    Abstract
    In den letzten Jahren haben Sprachmodelltechnologien unterschiedlichster Ausprägungen in der Informationswissenschaft Einzug gehalten. Diesen Sprachmodellen, die unter den Bezeichnungen GPT, ELMo oder BERT bekannt sind, ist gemein, dass sie dank sehr großer Webkorpora auf eine Datenbasis zurückgreifen, die bei vorherigen Sprachmodellansätzen undenkbar war. Gleichzeitig setzen diese Modelle auf neuere Entwicklungen des maschinellen Lernens, insbesondere auf künstliche neuronale Netze. Diese Technologien haben auch im Information Retrieval (IR) Fuß gefasst und bereits kurz nach ihrer Einführung sprunghafte, substantielle Leistungssteigerungen erzielt. Neuronale Netze haben in Kombination mit großen vortrainierten Sprachmodellen und kontextualisierten Worteinbettungen geführt. Wurde in vergangenen Jahren immer wieder eine stagnierende Retrievalleistung beklagt, die Leistungssteigerungen nur gegenüber "schwachen Baselines" aufwies, so konnten mit diesen technischen und methodischen Innovationen beeindruckende Leistungssteigerungen in Aufgaben wie dem klassischen Ad-hoc-Retrieval, der maschinellen Übersetzung oder auch dem Question Answering erzielt werden. In diesem Kapitel soll ein kurzer Überblick über die Grundlagen der Sprachmodelle und der NN gegeben werden, um die prinzipiellen Bausteine zu verstehen, die hinter aktuellen Technologien wie ELMo oder BERT stecken, die die Welt des NLP und IR im Moment beherrschen.
  7. Ali, C.B.; Haddad, H.; Slimani, Y.: Multi-word terms selection for information retrieval (2022) 0.00 
    0.0032494082 = product of:
  0.022745857 = sum of:
    0.007338503 = weight(_text_:information in 900) [ClassicSimilarity], result of:
      0.007338503 = score(doc=900,freq=4.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13714671 = fieldWeight in 900, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=900)
    0.015407355 = weight(_text_:retrieval in 900) [ClassicSimilarity], result of:
      0.015407355 = score(doc=900,freq=2.0), product of:
        0.092201896 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.030480823 = queryNorm
        0.16710453 = fieldWeight in 900, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.0390625 = fieldNorm(doc=900)
  0.14285715 = coord(2/14)
    Source
    Information discovery and delivery 51(2022) no.1, S.xx-xx
  8. Morris, V.: Automated language identification of bibliographic resources (2020) 0.00 
    0.002759312 = product of:
  0.019315183 = sum of:
    0.008302568 = weight(_text_:information in 5749) [ClassicSimilarity], result of:
      0.008302568 = score(doc=5749,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.1551638 = fieldWeight in 5749, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0625 = fieldNorm(doc=5749)
    0.011012616 = product of:
      0.033037845 = sum of:
        0.033037845 = weight(_text_:22 in 5749) [ClassicSimilarity], result of:
          0.033037845 = score(doc=5749,freq=2.0), product of:
            0.10673865 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.030480823 = queryNorm
            0.30952093 = fieldWeight in 5749, 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=5749)
      0.33333334 = coord(1/3)
  0.14285715 = coord(2/14)
    Abstract
    This article describes experiments in the use of machine learning techniques at the British Library to assign language codes to catalog records, in order to provide information about the language of content of the resources described. In the first phase of the project, language codes were assigned to 1.15 million records with 99.7% confidence. The automated language identification tools developed will be used to contribute to future enhancement of over 4 million legacy records.
    Date
    2. 3.2020 19:04:22
  9. Luo, L.; Ju, J.; Li, Y.-F.; Haffari, G.; Xiong, B.; Pan, S.: ChatRule: mining logical rules with large language models for knowledge graph reasoning (2023) 0.00 
    0.0017245701 = product of:
  0.0120719895 = sum of:
    0.005189105 = weight(_text_:information in 1171) [ClassicSimilarity], result of:
      0.005189105 = score(doc=1171,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.09697737 = fieldWeight in 1171, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1171)
    0.006882885 = product of:
      0.020648655 = sum of:
        0.020648655 = weight(_text_:22 in 1171) [ClassicSimilarity], result of:
          0.020648655 = score(doc=1171,freq=2.0), product of:
            0.10673865 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.030480823 = queryNorm
            0.19345059 = fieldWeight in 1171, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1171)
      0.33333334 = coord(1/3)
  0.14285715 = coord(2/14)
    Abstract
    Logical rules are essential for uncovering the logical connections between relations, which could improve the reasoning performance and provide interpretable results on knowledge graphs (KGs). Although there have been many efforts to mine meaningful logical rules over KGs, existing methods suffer from the computationally intensive searches over the rule space and a lack of scalability for large-scale KGs. Besides, they often ignore the semantics of relations which is crucial for uncovering logical connections. Recently, large language models (LLMs) have shown impressive performance in the field of natural language processing and various applications, owing to their emergent ability and generalizability. In this paper, we propose a novel framework, ChatRule, unleashing the power of large language models for mining logical rules over knowledge graphs. Specifically, the framework is initiated with an LLM-based rule generator, leveraging both the semantic and structural information of KGs to prompt LLMs to generate logical rules. To refine the generated rules, a rule ranking module estimates the rule quality by incorporating facts from existing KGs. Last, a rule validator harnesses the reasoning ability of LLMs to validate the logical correctness of ranked rules through chain-of-thought reasoning. ChatRule is evaluated on four large-scale KGs, w.r.t. different rule quality metrics and downstream tasks, showing the effectiveness and scalability of our method.
    Date
    23.11.2023 19:07:22
  10. ¬Der Student aus dem Computer (2023) 0.00 
    0.0013765771 = product of:
  0.019272078 = sum of:
    0.019272078 = product of:
      0.05781623 = sum of:
        0.05781623 = weight(_text_:22 in 1079) [ClassicSimilarity], result of:
          0.05781623 = score(doc=1079,freq=2.0), product of:
            0.10673865 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.030480823 = queryNorm
            0.5416616 = fieldWeight in 1079, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.109375 = fieldNorm(doc=1079)
      0.33333334 = coord(1/3)
  0.071428575 = coord(1/14)
    Date
    27. 1.2023 16:22:55
  11. 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) 0.00 
    0.0010247872 = product of:
  0.014347021 = sum of:
    0.014347021 = weight(_text_:web in 872) [ClassicSimilarity], result of:
      0.014347021 = score(doc=872,freq=2.0), product of:
        0.09947448 = queryWeight, product of:
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.030480823 = queryNorm
        0.14422815 = fieldWeight in 872, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.03125 = fieldNorm(doc=872)
  0.071428575 = coord(1/14)
    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.
  12. Bager, J.: ¬Die Text-KI ChatGPT schreibt Fachtexte, Prosa, Gedichte und Programmcode (2023) 0.00 
    7.866154E-4 = product of:
  0.011012616 = sum of:
    0.011012616 = product of:
      0.033037845 = sum of:
        0.033037845 = weight(_text_:22 in 835) [ClassicSimilarity], result of:
          0.033037845 = score(doc=835,freq=2.0), product of:
            0.10673865 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.030480823 = 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)
      0.33333334 = coord(1/3)
  0.071428575 = coord(1/14)
    Date
    29.12.2022 18:22:55
  13. Rieger, F.: Lügende Computer (2023) 0.00 
    7.866154E-4 = product of:
  0.011012616 = sum of:
    0.011012616 = product of:
      0.033037845 = sum of:
        0.033037845 = weight(_text_:22 in 912) [ClassicSimilarity], result of:
          0.033037845 = score(doc=912,freq=2.0), product of:
            0.10673865 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.030480823 = 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)
      0.33333334 = coord(1/3)
  0.071428575 = coord(1/14)
    Date
    16. 3.2023 19:22:55
  14. Xiang, R.; Chersoni, E.; Lu, Q.; Huang, C.-R.; Li, W.; Long, Y.: Lexical data augmentation for sentiment analysis (2021) 0.00 
    5.241788E-4 = product of:
  0.007338503 = sum of:
    0.007338503 = weight(_text_:information in 392) [ClassicSimilarity], result of:
      0.007338503 = score(doc=392,freq=4.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13714671 = fieldWeight in 392, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=392)
  0.071428575 = coord(1/14)
    Abstract
    Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part-of-speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic-based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution-based data augmentation methods, one of which is thesaurus-based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST-2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM-AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well-designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms.
    Source
    Journal of the Association for Information Science and Technology. 72(2021) no.11, S.1432-1447
  15. Andrushchenko, M.; Sandberg, K.; Turunen, R.; Marjanen, J.; Hatavara, M.; Kurunmäki, J.; Nummenmaa, T.; Hyvärinen, M.; Teräs, K.; Peltonen, J.; Nummenmaa, J.: Using parsed and annotated corpora to analyze parliamentarians' talk in Finland (2022) 0.00 
    5.241788E-4 = product of:
  0.007338503 = sum of:
    0.007338503 = weight(_text_:information in 471) [ClassicSimilarity], result of:
      0.007338503 = score(doc=471,freq=4.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13714671 = fieldWeight in 471, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=471)
  0.071428575 = coord(1/14)
    Abstract
    We present a search system for grammatically analyzed corpora of Finnish parliamentary records and interviews with former parliamentarians, annotated with metadata of talk structure and involved parliamentarians, and discuss their use through carefully chosen digital humanities case studies. We first introduce the construction, contents, and principles of use of the corpora. Then we discuss the application of the search system and the corpora to study how politicians talk about power, how ideological terms are used in political speech, and how to identify narratives in the data. All case studies stem from questions in the humanities and the social sciences, but rely on the grammatically parsed corpora in both identifying and quantifying passages of interest. Finally, the paper discusses the role of natural language processing methods for questions in the (digital) humanities. It makes the claim that a digital humanities inquiry of parliamentary speech and interviews with politicians cannot only rely on computational humanities modeling, but needs to accommodate a range of perspectives starting with simple searches, quantitative exploration, and ending with modeling. Furthermore, the digital humanities need a more thorough discussion about how the utilization of tools from information science and technologies alter the research questions posed in the humanities.
    Source
    Journal of the Association for Information Science and Technology. 73(2022) no.2, S.288-302
  16. Suissa, O.; Elmalech, A.; Zhitomirsky-Geffet, M.: Text analysis using deep neural networks in digital humanities and information science (2022) 0.00 
    5.241788E-4 = product of:
  0.007338503 = sum of:
    0.007338503 = weight(_text_:information in 491) [ClassicSimilarity], result of:
      0.007338503 = score(doc=491,freq=4.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13714671 = fieldWeight in 491, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=491)
  0.071428575 = coord(1/14)
    Source
    Journal of the Association for Information Science and Technology. 73(2022) no.2, S.268-287
  17. Weiß, E.-M.: ChatGPT soll es richten : Microsoft baut KI in Suchmaschine Bing ein (2023) 0.00 
    5.189105E-4 = product of:
  0.0072647473 = sum of:
    0.0072647473 = weight(_text_:information in 866) [ClassicSimilarity], result of:
      0.0072647473 = score(doc=866,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.13576832 = fieldWeight in 866, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0546875 = fieldNorm(doc=866)
  0.071428575 = coord(1/14)
    Abstract
    ChatGPT, die künstliche Intelligenz der Stunde, ist von OpenAI entwickelt worden. Und OpenAI ist in der Vergangenheit nicht unerheblich von Microsoft unterstützt worden. Nun geht es ums Profitieren: Die KI soll in die Suchmaschine Bing eingebaut werden, was eine direkte Konkurrenz zu Googles Suchalgorithmen und Intelligenzen bedeutet. Bing war da bislang nicht sonderlich erfolgreich. Wie "The Information" mit Verweis auf zwei Insider berichtet, plant Microsoft, ChatGPT in seine Suchmaschine Bing einzubauen. Bereits im März könnte die neue, intelligente Suche verfügbar sein. Microsoft hatte zuvor auf der hauseigenen Messe Ignite zunächst die Integration des Bildgenerators DALL·E 2 in seine Suchmaschine angekündigt - ohne konkretes Startdatum jedoch. Fragt man ChatGPT selbst, bestätigt der Chatbot seine künftige Aufgabe noch nicht. Weiß aber um potentielle Vorteile.
  18. Azpiazu, I.M.; Soledad Pera, M.: Is cross-lingual readability assessment possible? (2020) 0.00 
    5.1358825E-4 = product of:
  0.0071902354 = sum of:
    0.0071902354 = weight(_text_:information in 5868) [ClassicSimilarity], result of:
      0.0071902354 = score(doc=5868,freq=6.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.1343758 = fieldWeight in 5868, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.03125 = fieldNorm(doc=5868)
  0.071428575 = coord(1/14)
    Abstract
    Most research efforts related to automatic readability assessment focus on the design of strategies that apply to a specific language. These state-of-the-art strategies are highly dependent on linguistic features that best suit the language for which they were intended, constraining their adaptability and making it difficult to determine whether they would remain effective if they were applied to estimate the level of difficulty of texts in other languages. In this article, we present the results of a study designed to determine the feasibility of a cross-lingual readability assessment strategy. For doing so, we first analyzed the most common features used for readability assessment and determined their influence on the readability prediction process of 6 different languages: English, Spanish, Basque, Italian, French, and Catalan. In addition, we developed a cross-lingual readability assessment strategy that serves as a means to empirically explore the potential advantages of employing a single strategy (and set of features) for readability assessment in different languages, including interlanguage prediction agreement and prediction accuracy improvement for low-resource languages.Friend request acceptance and information disclosure constitute 2 important privacy decisions for users to control the flow of their personal information in social network sites (SNSs). These decisions are greatly influenced by contextual characteristics of the request. However, the contextual influence may not be uniform among users with different levels of privacy concerns. In this study, we hypothesize that users with higher privacy concerns may consider contextual factors differently from those with lower privacy concerns. By conducting a scenario-based survey study and structural equation modeling, we verify the interaction effects between privacy concerns and contextual factors. We additionally find that users' perceived risk towards the requester mediates the effect of context and privacy concerns. These results extend our understanding about the cognitive process behind privacy decision making in SNSs. The interaction effects suggest strategies for SNS providers to predict user's friend request acceptance and to customize context-aware privacy decision support based on users' different privacy attitudes.
    Source
    Journal of the Association for Information Science and Technology. 71(2020) no.6, S.644-656
  19. Corbara, S.; Moreo, A.; Sebastiani, F.: Syllabic quantity patterns as rhythmic features for Latin authorship attribution (2023) 0.00 
    4.4478045E-4 = product of:
  0.006226926 = sum of:
    0.006226926 = weight(_text_:information in 846) [ClassicSimilarity], result of:
      0.006226926 = score(doc=846,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.116372846 = fieldWeight in 846, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.046875 = fieldNorm(doc=846)
  0.071428575 = coord(1/14)
    Source
    Journal of the Association for Information Science and Technology. 74(2023) no.1, S.128-141
  20. Lund, B.D.; Wang, T.; Mannuru, N.R.; Nie, B.; Shimray, S.; Wang, Z.: ChatGPT and a new academic reality : artificial Intelligence-written research papers and the ethics of the large language models in scholarly publishing (2023) 0.00 
    4.4478045E-4 = product of:
  0.006226926 = sum of:
    0.006226926 = weight(_text_:information in 943) [ClassicSimilarity], result of:
      0.006226926 = score(doc=943,freq=2.0), product of:
        0.053508412 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.030480823 = queryNorm
        0.116372846 = fieldWeight in 943, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.046875 = fieldNorm(doc=943)
  0.071428575 = coord(1/14)
    Source
    Journal of the Association for Information Science and Technology. 74(2023) no.5, S.570-581

Authors

Languages

  • e 21
  • d 7

Types

Themes