Search (42 results, page 1 of 3)

0.23703793 = product of:
  0.47407585 = sum of:
    0.06558679 = product of:
      0.19676036 = sum of:
        0.19676036 = weight(_text_:3a in 862) [ClassicSimilarity], result of:
          0.19676036 = score(doc=862,freq=2.0), product of:
            0.35009617 = queryWeight, product of:
              8.478011 = idf(docFreq=24, maxDocs=44218)
              0.041294612 = 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)
    0.19676036 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.19676036 = score(doc=862,freq=2.0), product of:
        0.35009617 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.041294612 = 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)
    0.014968331 = weight(_text_:of in 862) [ClassicSimilarity], result of:
      0.014968331 = score(doc=862,freq=10.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.23179851 = fieldWeight in 862, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
    0.19676036 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.19676036 = score(doc=862,freq=2.0), product of:
        0.35009617 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.041294612 = 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)
  0.5 = coord(4/8)

Abstract

This research revisits the classic Turing test and compares recent large language models such as ChatGPT for their abilities to reproduce human-level comprehension and compelling text generation. Two task challenges- summary and question answering- prompt ChatGPT to produce original content (98-99%) from a single text entry and sequential questions initially posed by Turing in 1950. We score the original and generated content against the OpenAI GPT-2 Output Detector from 2019, and establish multiple cases where the generated content proves original and undetectable (98%). The question of a machine fooling a human judge recedes in this work relative to the question of "how would one prove it?" The original contribution of the work presents a metric and simple grammatical set for understanding the writing mechanics of chatbots in evaluating their readability and statistical clarity, engagement, delivery, overall quality, and plagiarism risks. While Turing's original prose scores at least 14% below the machine-generated output, whether an algorithm displays hints of Turing's true initial thoughts (the "Lovelace 2.0" test) remains unanswerable.

Source

https%3A%2F%2Farxiv.org%2Fabs%2F2212.06721&usg=AOvVaw3i_9pZm9y_dQWoHi6uv0EN

0.055401772 = product of:
  0.110803545 = sum of:
    0.036153924 = weight(_text_:retrieval in 1187) [ClassicSimilarity], result of:
      0.036153924 = score(doc=1187,freq=6.0), product of:
        0.124912694 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.041294612 = 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)
    0.04277933 = weight(_text_:use in 1187) [ClassicSimilarity], result of:
      0.04277933 = score(doc=1187,freq=8.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.3383162 = fieldWeight in 1187, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1187)
    0.02231347 = weight(_text_:of in 1187) [ClassicSimilarity], result of:
      0.02231347 = score(doc=1187,freq=32.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.34554482 = fieldWeight in 1187, product of:
          5.656854 = tf(freq=32.0), with freq of:
            32.0 = termFreq=32.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1187)
    0.00955682 = product of:
      0.01911364 = sum of:
        0.01911364 = weight(_text_:on in 1187) [ClassicSimilarity], result of:
          0.01911364 = score(doc=1187,freq=6.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.21044704 = fieldWeight in 1187, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1187)
      0.5 = coord(1/2)
  0.5 = coord(4/8)

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.

0.029424565 = product of:
  0.07846551 = sum of:
    0.03422346 = weight(_text_:use in 5749) [ClassicSimilarity], result of:
      0.03422346 = score(doc=5749,freq=2.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.27065295 = fieldWeight in 5749, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0625 = fieldNorm(doc=5749)
    0.021862645 = weight(_text_:of in 5749) [ClassicSimilarity], result of:
      0.021862645 = score(doc=5749,freq=12.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.33856338 = fieldWeight in 5749, 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=5749)
    0.0223794 = product of:
      0.0447588 = sum of:
        0.0447588 = weight(_text_:22 in 5749) [ClassicSimilarity], result of:
          0.0447588 = score(doc=5749,freq=2.0), product of:
            0.1446067 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.041294612 = 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)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

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

0.021865398 = product of:
  0.058307726 = sum of:
    0.030249555 = weight(_text_:use in 471) [ClassicSimilarity], result of:
      0.030249555 = score(doc=471,freq=4.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.23922569 = fieldWeight in 471, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=471)
    0.01850135 = weight(_text_:of in 471) [ClassicSimilarity], result of:
      0.01850135 = score(doc=471,freq=22.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.28651062 = fieldWeight in 471, product of:
          4.690416 = tf(freq=22.0), with freq of:
            22.0 = termFreq=22.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=471)
    0.00955682 = product of:
      0.01911364 = sum of:
        0.01911364 = weight(_text_:on in 471) [ClassicSimilarity], result of:
          0.01911364 = score(doc=471,freq=6.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.21044704 = fieldWeight in 471, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=471)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

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.

Series

JASIST special issue on digital humanities (DH): C. Methodological innovations, challenges, and new interest in DH

Source

Journal of the Association for Information Science and Technology. 73(2022) no.2, S.288-302

0.02059525 = product of:
  0.082381 = sum of:
    0.019324033 = weight(_text_:of in 953) [ClassicSimilarity], result of:
      0.019324033 = score(doc=953,freq=6.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = 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)
    0.06305697 = product of:
      0.12611394 = sum of:
        0.12611394 = weight(_text_:computers in 953) [ClassicSimilarity], result of:
          0.12611394 = score(doc=953,freq=2.0), product of:
            0.21710795 = queryWeight, product of:
              5.257537 = idf(docFreq=625, maxDocs=44218)
              0.041294612 = queryNorm
            0.58088124 = fieldWeight in 953, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.257537 = idf(docFreq=625, maxDocs=44218)
              0.078125 = fieldNorm(doc=953)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

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

0.017766995 = product of:
  0.047378656 = sum of:
    0.021389665 = weight(_text_:use in 849) [ClassicSimilarity], result of:
      0.021389665 = score(doc=849,freq=2.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.1691581 = fieldWeight in 849, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=849)
    0.012473608 = weight(_text_:of in 849) [ClassicSimilarity], result of:
      0.012473608 = score(doc=849,freq=10.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.19316542 = fieldWeight in 849, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=849)
    0.013515383 = product of:
      0.027030766 = sum of:
        0.027030766 = weight(_text_:on in 849) [ClassicSimilarity], result of:
          0.027030766 = score(doc=849,freq=12.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.29761705 = fieldWeight in 849, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=849)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

Abstract

ChatGPT, a general-purpose conversation chatbot released on November 30, 2022, by OpenAI, is expected to impact every aspect of society. However, the potential impacts of this NLP tool on education remain unknown. Such impact can be enormous as the capacity of ChatGPT may drive changes to educational learning goals, learning activities, and assessment and evaluation practices. This study was conducted by piloting ChatGPT to write an academic paper, titled Artificial Intelligence for Education (see Appendix A). The piloting result suggests that ChatGPT is able to help researchers write a paper that is coherent, (partially) accurate, informative, and systematic. The writing is extremely efficient (2-3 hours) and involves very limited professional knowledge from the author. Drawing upon the user experience, I reflect on the potential impacts of ChatGPT, as well as similar AI tools, on education. The paper concludes by suggesting adjusting learning goals-students should be able to use AI tools to conduct subject-domain tasks and education should focus on improving students' creativity and critical thinking rather than general skills. To accomplish the learning goals, researchers should design AI-involved learning tasks to engage students in solving real-world problems. ChatGPT also raises concerns that students may outsource assessment tasks. This paper concludes that new formats of assessments are needed to focus on creativity and critical thinking that AI cannot substitute.

0.017372584 = product of:
  0.069490336 = sum of:
    0.058445733 = weight(_text_:retrieval in 667) [ClassicSimilarity], result of:
      0.058445733 = score(doc=667,freq=8.0), product of:
        0.124912694 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.041294612 = 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)
    0.011044604 = weight(_text_:of in 667) [ClassicSimilarity], result of:
      0.011044604 = score(doc=667,freq=4.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.17103596 = fieldWeight in 667, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=667)
  0.25 = coord(2/8)

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]

0.016705364 = product of:
  0.04454764 = sum of:
    0.021389665 = weight(_text_:use in 169) [ClassicSimilarity], result of:
      0.021389665 = score(doc=169,freq=2.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.1691581 = fieldWeight in 169, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=169)
    0.017640345 = weight(_text_:of in 169) [ClassicSimilarity], result of:
      0.017640345 = score(doc=169,freq=20.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.27317715 = fieldWeight in 169, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=169)
    0.0055176322 = product of:
      0.0110352645 = sum of:
        0.0110352645 = weight(_text_:on in 169) [ClassicSimilarity], result of:
          0.0110352645 = score(doc=169,freq=2.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.121501654 = fieldWeight in 169, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=169)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

Abstract

Diachronic word embeddings-vector representations of words over time-offer remarkable insights into the evolution of language and provide a tool for quantifying sociocultural change from text documents. Prior work has used such embeddings to identify shifts in the meaning of individual words. However, simply knowing that a word has changed in meaning is insufficient to identify the instances of word usage that convey the historical meaning or the newer meaning. In this study, we link diachronic word embeddings to documents, by situating those documents as leaders or laggards with respect to ongoing semantic changes. Specifically, we propose a novel method to quantify the degree of semantic progressiveness in each word usage, and then show how these usages can be aggregated to obtain scores for each document. We analyze two large collections of documents, representing legal opinions and scientific articles. Documents that are scored as semantically progressive receive a larger number of citations, indicating that they are especially influential. Our work thus provides a new technique for identifying lexical semantic leaders and demonstrates a new link between progressive use of language and influence in a citation network.

Source

Journal of the Association for Information Science and Technology. 72(2021) no.4, S.478-492

0.016077485 = product of:
  0.042873293 = sum of:
    0.020873476 = weight(_text_:retrieval in 900) [ClassicSimilarity], result of:
      0.020873476 = score(doc=900,freq=2.0), product of:
        0.124912694 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.041294612 = 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)
    0.009662016 = weight(_text_:of in 900) [ClassicSimilarity], result of:
      0.009662016 = score(doc=900,freq=6.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.1496253 = fieldWeight in 900, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=900)
    0.012337802 = product of:
      0.024675604 = sum of:
        0.024675604 = weight(_text_:on in 900) [ClassicSimilarity], result of:
          0.024675604 = score(doc=900,freq=10.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.271686 = fieldWeight in 900, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=900)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

Abstract

Purpose A number of approaches and algorithms have been proposed over the years as a basis for automatic indexing. Many of these approaches suffer from precision inefficiency at low recall. The choice of indexing units has a great impact on search system effectiveness. The authors dive beyond simple terms indexing to propose a framework for multi-word terms (MWT) filtering and indexing. Design/methodology/approach In this paper, the authors rely on ranking MWT to filter them, keeping the most effective ones for the indexing process. The proposed model is based on filtering MWT according to their ability to capture the document topic and distinguish between different documents from the same collection. The authors rely on the hypothesis that the best MWT are those that achieve the greatest association degree. The experiments are carried out with English and French languages data sets. Findings The results indicate that this approach achieved precision enhancements at low recall, and it performed better than more advanced models based on terms dependencies. Originality/value Using and testing different association measures to select MWT that best describe the documents to enhance the precision in the first retrieved documents.

0.016006988 = product of:
  0.0426853 = sum of:
    0.021389665 = weight(_text_:use in 491) [ClassicSimilarity], result of:
      0.021389665 = score(doc=491,freq=2.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.1691581 = fieldWeight in 491, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=491)
    0.015778005 = weight(_text_:of in 491) [ClassicSimilarity], result of:
      0.015778005 = score(doc=491,freq=16.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.24433708 = fieldWeight in 491, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=491)
    0.0055176322 = product of:
      0.0110352645 = sum of:
        0.0110352645 = weight(_text_:on in 491) [ClassicSimilarity], result of:
          0.0110352645 = score(doc=491,freq=2.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.121501654 = fieldWeight in 491, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=491)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

Abstract

Combining computational technologies and humanities is an ongoing effort aimed at making resources such as texts, images, audio, video, and other artifacts digitally available, searchable, and analyzable. In recent years, deep neural networks (DNN) dominate the field of automatic text analysis and natural language processing (NLP), in some cases presenting a super-human performance. DNNs are the state-of-the-art machine learning algorithms solving many NLP tasks that are relevant for Digital Humanities (DH) research, such as spell checking, language detection, entity extraction, author detection, question answering, and other tasks. These supervised algorithms learn patterns from a large number of "right" and "wrong" examples and apply them to new examples. However, using DNNs for analyzing the text resources in DH research presents two main challenges: (un)availability of training data and a need for domain adaptation. This paper explores these challenges by analyzing multiple use-cases of DH studies in recent literature and their possible solutions and lays out a practical decision model for DH experts for when and how to choose the appropriate deep learning approaches for their research. Moreover, in this paper, we aim to raise awareness of the benefits of utilizing deep learning models in the DH community.

Series

JASIST special issue on digital humanities (DH): C. Methodological innovations, challenges, and new interest in DH

Source

Journal of the Association for Information Science and Technology. 73(2022) no.2, S.268-287

0.01583315 = product of:
  0.042221732 = sum of:
    0.014972764 = weight(_text_:use in 923) [ClassicSimilarity], result of:
      0.014972764 = score(doc=923,freq=2.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.11841066 = fieldWeight in 923, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.02734375 = fieldNorm(doc=923)
    0.019524286 = weight(_text_:of in 923) [ClassicSimilarity], result of:
      0.019524286 = score(doc=923,freq=50.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = 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)
    0.007724685 = product of:
      0.01544937 = sum of:
        0.01544937 = weight(_text_:on in 923) [ClassicSimilarity], result of:
          0.01544937 = score(doc=923,freq=8.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.17010231 = fieldWeight in 923, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.02734375 = fieldNorm(doc=923)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

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."

0.014447001 = product of:
  0.038525335 = sum of:
    0.0167351 = weight(_text_:of in 1171) [ClassicSimilarity], result of:
      0.0167351 = score(doc=1171,freq=18.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.25915858 = fieldWeight in 1171, product of:
          4.2426405 = tf(freq=18.0), with freq of:
            18.0 = termFreq=18.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1171)
    0.007803111 = product of:
      0.015606222 = sum of:
        0.015606222 = weight(_text_:on in 1171) [ClassicSimilarity], result of:
          0.015606222 = score(doc=1171,freq=4.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.1718293 = fieldWeight in 1171, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1171)
      0.5 = coord(1/2)
    0.013987125 = product of:
      0.02797425 = sum of:
        0.02797425 = weight(_text_:22 in 1171) [ClassicSimilarity], result of:
          0.02797425 = score(doc=1171,freq=2.0), product of:
            0.1446067 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.041294612 = 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)
      0.5 = coord(1/2)
  0.375 = coord(3/8)

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

0.011972475 = product of:
  0.0478899 = sum of:
    0.030249555 = weight(_text_:use in 990) [ClassicSimilarity], result of:
      0.030249555 = score(doc=990,freq=4.0), product of:
        0.12644777 = queryWeight, product of:
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.041294612 = queryNorm
        0.23922569 = fieldWeight in 990, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.0620887 = idf(docFreq=5623, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
    0.017640345 = weight(_text_:of in 990) [ClassicSimilarity], result of:
      0.017640345 = score(doc=990,freq=20.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.27317715 = fieldWeight in 990, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
  0.25 = coord(2/8)

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

0.007800586 = product of:
  0.031202344 = sum of:
    0.016396983 = weight(_text_:of in 846) [ClassicSimilarity], result of:
      0.016396983 = score(doc=846,freq=12.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.25392252 = fieldWeight in 846, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.046875 = fieldNorm(doc=846)
    0.014805362 = product of:
      0.029610723 = sum of:
        0.029610723 = weight(_text_:on in 846) [ClassicSimilarity], result of:
          0.029610723 = score(doc=846,freq=10.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.32602316 = fieldWeight in 846, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.046875 = fieldNorm(doc=846)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

Abstract

It is well known that, within the Latin production of written text, peculiar metric schemes were followed not only in poetic compositions, but also in many prose works. Such metric patterns were based on so-called syllabic quantity, that is, on the length of the involved syllables, and there is substantial evidence suggesting that certain authors had a preference for certain metric patterns over others. In this research we investigate the possibility to employ syllabic quantity as a base for deriving rhythmic features for the task of computational authorship attribution of Latin prose texts. We test the impact of these features on the authorship attribution task when combined with other topic-agnostic features. Our experiments, carried out on three different datasets using support vector machines (SVMs) show that rhythmic features based on syllabic quantity are beneficial in discriminating among Latin prose authors.

Source

Journal of the Association for Information Science and Technology. 74(2023) no.1, S.128-141

0.007790436 = product of:
  0.031161744 = sum of:
    0.021604925 = weight(_text_:of in 159) [ClassicSimilarity], result of:
      0.021604925 = score(doc=159,freq=30.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.33457235 = fieldWeight in 159, product of:
          5.477226 = tf(freq=30.0), with freq of:
            30.0 = termFreq=30.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=159)
    0.00955682 = product of:
      0.01911364 = sum of:
        0.01911364 = weight(_text_:on in 159) [ClassicSimilarity], result of:
          0.01911364 = score(doc=159,freq=6.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.21044704 = fieldWeight in 159, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=159)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

Abstract

Frequency is one of the major factors for training quality word embeddings. Several studies have recently discussed the stability of word embeddings in general domain and suggested factors influencing the stability. In this work, we conduct a detailed analysis on the stability of concept embeddings in medical domain, particularly in relations with concept frequency. The analysis reveals the surprising high stability of low-frequency concepts: low-frequency (<100) concepts have the same high stability as high-frequency (>1,000) concepts. To develop a deeper understanding of this finding, we propose a new factor, the noisiness of context words, which influences the stability of medical concept embeddings regardless of high or low frequency. We evaluate the proposed factor by showing the linear correlation with the stability of medical concept embeddings. The correlations are clear and consistent with various groups of medical concepts. Based on the linear relations, we make suggestions on ways to adjust the noisiness of context words for the improvement of stability. Finally, we demonstrate that the linear relation of the proposed factor extends to the word embedding stability in general domain.

Source

Journal of the Association for Information Science and Technology. 72(2021) no.3, S.346-356

0.007709788 = product of:
  0.030839153 = sum of:
    0.01850135 = weight(_text_:of in 392) [ClassicSimilarity], result of:
      0.01850135 = score(doc=392,freq=22.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.28651062 = fieldWeight in 392, product of:
          4.690416 = tf(freq=22.0), with freq of:
            22.0 = termFreq=22.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=392)
    0.012337802 = product of:
      0.024675604 = sum of:
        0.024675604 = weight(_text_:on in 392) [ClassicSimilarity], result of:
          0.024675604 = score(doc=392,freq=10.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.271686 = fieldWeight in 392, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=392)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

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

0.007600447 = product of:
  0.030401789 = sum of:
    0.018933605 = weight(_text_:of in 1205) [ClassicSimilarity], result of:
      0.018933605 = score(doc=1205,freq=16.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.2932045 = fieldWeight in 1205, 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=1205)
    0.011468184 = product of:
      0.022936368 = sum of:
        0.022936368 = weight(_text_:on in 1205) [ClassicSimilarity], result of:
          0.022936368 = score(doc=1205,freq=6.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.25253648 = fieldWeight in 1205, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.046875 = fieldNorm(doc=1205)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

Abstract

Detecting science-technology hierarchical linkages is beneficial for understanding deep interactions between science and technology (S&T). Previous studies have mainly focused on linear linkages between S&T but ignored their structural linkages. In this paper, we propose a network coupling approach to inspect hierarchical interactions of S&T by integrating their knowledge linkages and structural linkages. S&T knowledge networks are first enhanced with bidirectional encoder representation from transformers (BERT) knowledge alignment, and then their hierarchical structures are identified based on K-core decomposition. Hierarchical coupling preferences and strengths of the S&T networks over time are further calculated based on similarities of coupling nodes' degree distribution and similarities of coupling edges' weight distribution. Extensive experimental results indicate that our approach is feasible and robust in identifying the coupling hierarchy with superior performance compared to other isomorphism and dissimilarity algorithms. Our research extends the mindset of S&T linkage measurement by identifying patterns and paths of the interaction of S&T hierarchical knowledge.

Source

Journal of the Association for Information Science and Technology. 75(2023) no.2, S.167-187

0.007168902 = product of:
  0.028675608 = sum of:
    0.017640345 = weight(_text_:of in 5816) [ClassicSimilarity], result of:
      0.017640345 = score(doc=5816,freq=20.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.27317715 = fieldWeight in 5816, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5816)
    0.0110352645 = product of:
      0.022070529 = sum of:
        0.022070529 = weight(_text_:on in 5816) [ClassicSimilarity], result of:
          0.022070529 = score(doc=5816,freq=8.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.24300331 = fieldWeight in 5816, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5816)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

Abstract

Millions of messages are produced on microblog platforms every day, leading to the pressing need for automatic identification of key points from the massive texts. To absorb salient content from the vast bulk of microblog posts, this article focuses on the task of microblog keyphrase extraction. In previous work, most efforts treat messages as independent documents and might suffer from the data sparsity problem exhibited in short and informal microblog posts. On the contrary, we propose to enrich contexts via exploiting conversations initialized by target posts and formed by their replies, which are generally centered around relevant topics to the target posts and therefore helpful for keyphrase identification. Concretely, we present a neural keyphrase extraction framework, which has 2 modules: a conversation context encoder and a keyphrase tagger. The conversation context encoder captures indicative representation from their conversation contexts and feeds the representation into the keyphrase tagger, and the keyphrase tagger extracts salient words from target posts. The 2 modules were trained jointly to optimize the conversation context encoding and keyphrase extraction processes. In the conversation context encoder, we leverage hierarchical structures to capture the word-level indicative representation and message-level indicative representation hierarchically. In both of the modules, we apply character-level representations, which enables the model to explore morphological features and deal with the out-of-vocabulary problem caused by the informal language style of microblog messages. Extensive comparison results on real-life data sets indicate that our model outperforms state-of-the-art models from previous studies.

Source

Journal of the Association for Information Science and Technology. 71(2020) no.5, S.553-567

0.007096812 = product of:
  0.028387249 = sum of:
    0.020662563 = weight(_text_:of in 1139) [ClassicSimilarity], result of:
      0.020662563 = score(doc=1139,freq=14.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = queryNorm
        0.31997898 = fieldWeight in 1139, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1139)
    0.007724685 = product of:
      0.01544937 = sum of:
        0.01544937 = weight(_text_:on in 1139) [ClassicSimilarity], result of:
          0.01544937 = score(doc=1139,freq=2.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.17010231 = fieldWeight in 1139, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1139)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

Abstract

In light of AI (Artificial Intelligence) and NLP (Natural language processing) technologies, this article examines the feasibility of using AI/NLP models to enhance the subject indexing of digital resources. While BERT (Bidirectional Encoder Representations from Transformers) models are widely used in scholarly communities, the authors assess whether BERT models can be used in machine-assisted indexing in the Project Gutenberg collection, through suggesting Library of Congress subject headings filtered by certain Library of Congress Classification subclass labels. The findings of this study are informative for further research on BERT models to assist with automatic subject indexing for digital library collections.

0.0070743347 = product of:
  0.028297339 = sum of:
    0.018933605 = weight(_text_:of in 873) [ClassicSimilarity], result of:
      0.018933605 = score(doc=873,freq=16.0), product of:
        0.06457475 = queryWeight, product of:
          1.5637573 = idf(docFreq=25162, maxDocs=44218)
          0.041294612 = 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)
    0.009363732 = product of:
      0.018727465 = sum of:
        0.018727465 = weight(_text_:on in 873) [ClassicSimilarity], result of:
          0.018727465 = score(doc=873,freq=4.0), product of:
            0.090823986 = queryWeight, product of:
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.041294612 = queryNorm
            0.20619515 = fieldWeight in 873, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              2.199415 = idf(docFreq=13325, maxDocs=44218)
              0.046875 = fieldNorm(doc=873)
      0.5 = coord(1/2)
  0.25 = coord(2/8)

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.