Search (21 results, page 1 of 2)

0.1487487 = product of:
  0.2974974 = sum of:
    0.07437435 = product of:
      0.22312303 = sum of:
        0.22312303 = weight(_text_:3a in 862) [ClassicSimilarity], result of:
          0.22312303 = score(doc=862,freq=2.0), product of:
            0.39700332 = queryWeight, product of:
              8.478011 = idf(docFreq=24, maxDocs=44218)
              0.046827413 = 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)
    0.22312303 = weight(_text_:2f in 862) [ClassicSimilarity], result of:
      0.22312303 = score(doc=862,freq=2.0), product of:
        0.39700332 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046827413 = 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(2/4)

Source

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

0.047176752 = product of:
  0.094353504 = sum of:
    0.07315732 = weight(_text_:data in 392) [ClassicSimilarity], result of:
      0.07315732 = score(doc=392,freq=16.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.49407038 = fieldWeight in 392, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=392)
    0.021196188 = product of:
      0.042392377 = sum of:
        0.042392377 = weight(_text_:processing in 392) [ClassicSimilarity], result of:
          0.042392377 = score(doc=392,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.22363065 = fieldWeight in 392, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0390625 = fieldNorm(doc=392)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

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.

0.03908867 = product of:
  0.07817734 = sum of:
    0.036211025 = weight(_text_:data in 568) [ClassicSimilarity], result of:
      0.036211025 = score(doc=568,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.24455236 = fieldWeight in 568, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0546875 = fieldNorm(doc=568)
    0.041966315 = product of:
      0.08393263 = sum of:
        0.08393263 = weight(_text_:processing in 568) [ClassicSimilarity], result of:
          0.08393263 = score(doc=568,freq=4.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.4427661 = fieldWeight in 568, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0546875 = fieldNorm(doc=568)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

Abstract

Argument mining targets structures in natural language related to interpretation and persuasion. Most scholarly discourse involves interpreting experimental evidence and attempting to persuade other scientists to adopt the same conclusions, which could benefit from argument mining techniques. However, While various argument mining studies have addressed student essays and news articles, those that target scientific discourse are still scarce. This paper surveys existing work in argument mining of scholarly discourse, and provides an overview of current models, data, tasks, and applications. We identify a number of key challenges confronting argument mining in the scientific domain, and suggest some possible solutions and future directions.

Source

Proceedings of the Second Workshop on Scholarly Document Processing,

0.023530604 = product of:
  0.04706121 = sum of:
    0.02586502 = weight(_text_:data in 471) [ClassicSimilarity], result of:
      0.02586502 = score(doc=471,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17468026 = fieldWeight in 471, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=471)
    0.021196188 = product of:
      0.042392377 = sum of:
        0.042392377 = weight(_text_:processing in 471) [ClassicSimilarity], result of:
          0.042392377 = score(doc=471,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.22363065 = fieldWeight in 471, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0390625 = fieldNorm(doc=471)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

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.

0.023530604 = product of:
  0.04706121 = sum of:
    0.02586502 = weight(_text_:data in 491) [ClassicSimilarity], result of:
      0.02586502 = score(doc=491,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17468026 = fieldWeight in 491, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=491)
    0.021196188 = product of:
      0.042392377 = sum of:
        0.042392377 = weight(_text_:processing in 491) [ClassicSimilarity], result of:
          0.042392377 = score(doc=491,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.22363065 = fieldWeight in 491, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0390625 = fieldNorm(doc=491)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

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.

0.023530604 = product of:
  0.04706121 = sum of:
    0.02586502 = weight(_text_:data in 1042) [ClassicSimilarity], result of:
      0.02586502 = score(doc=1042,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17468026 = fieldWeight in 1042, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1042)
    0.021196188 = product of:
      0.042392377 = sum of:
        0.042392377 = weight(_text_:processing in 1042) [ClassicSimilarity], result of:
          0.042392377 = score(doc=1042,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.22363065 = fieldWeight in 1042, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1042)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

Abstract

Natural language processing techniques can be used to analyze the linguistic content of a document to extract missing pieces of metadata. However, accurate metadata extraction may not depend solely on the linguistics, but also on structural problems such as extremely large documents, unordered multi-file documents, and inconsistency in manually labeled metadata. In this work, we start from two standard machine learning solutions to extract pieces of metadata from Environmental Impact Statements, environmental policy documents that are regularly produced under the US National Environmental Policy Act of 1969. We present a series of experiments where we evaluate how these standard approaches are affected by different issues derived from real-world data. We find that metadata extraction can be strongly influenced by nonlinguistic factors such as document length and volume ordering and that the standard machine learning solutions often do not scale well to long documents. We demonstrate how such solutions can be better adapted to these scenarios, and conclude with suggestions for other NLP practitioners cataloging large document collections.

0.020529725 = product of:
  0.0821189 = sum of:
    0.0821189 = weight(_text_:data in 255) [ClassicSimilarity], result of:
      0.0821189 = score(doc=255,freq=14.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.55459267 = fieldWeight in 255, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046875 = fieldNorm(doc=255)
  0.25 = coord(1/4)

Abstract

A basic distinction in agent-based data-driven Database Semantics (DBS) is between language and nonlanguage cognition. Language cognition transfers content between agents by means of raw data. Nonlanguage cognition maps between content and raw data inside the focus agent. {\it Recognition} applies a concept type to raw data, resulting in a concept token. In language recognition, the focus agent (hearer) takes raw language-data (surfaces) produced by another agent (speaker) as input, while nonlanguage recognition takes raw nonlanguage-data as input. In either case, the output is a content which is stored in the agent's onboard short term memory. {\it Action} adapts a concept type to a purpose, resulting in a token. In language action, the focus agent (speaker) produces language-dependent surfaces for another agent (hearer), while nonlanguage action produces intentions for a nonlanguage purpose. In either case, the output is raw action data. As long as the procedural implementation of place holder values works properly, it is compatible with the DBS requirement of input-output equivalence between the natural prototype and the artificial reconstruction.

0.01852868 = product of:
  0.07411472 = sum of:
    0.07411472 = sum of:
      0.042392377 = weight(_text_:processing in 1171) [ClassicSimilarity], result of:
        0.042392377 = score(doc=1171,freq=2.0), product of:
          0.18956426 = queryWeight, product of:
            4.048147 = idf(docFreq=2097, maxDocs=44218)
            0.046827413 = queryNorm
          0.22363065 = fieldWeight in 1171, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            4.048147 = idf(docFreq=2097, maxDocs=44218)
            0.0390625 = fieldNorm(doc=1171)
      0.03172234 = weight(_text_:22 in 1171) [ClassicSimilarity], result of:
        0.03172234 = score(doc=1171,freq=2.0), product of:
          0.16398162 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.046827413 = 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)
  0.25 = coord(1/4)

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

0.011102819 = product of:
  0.044411276 = sum of:
    0.044411276 = product of:
      0.08882255 = sum of:
        0.08882255 = weight(_text_:22 in 1079) [ClassicSimilarity], result of:
          0.08882255 = score(doc=1079,freq=2.0), product of:
            0.16398162 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046827413 = 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)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Date

27. 1.2023 16:22:55

0.009144665 = product of:
  0.03657866 = sum of:
    0.03657866 = weight(_text_:data in 5816) [ClassicSimilarity], result of:
      0.03657866 = score(doc=5816,freq=4.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.24703519 = fieldWeight in 5816, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5816)
  0.25 = coord(1/4)

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.

0.009144665 = product of:
  0.03657866 = sum of:
    0.03657866 = weight(_text_:data in 990) [ClassicSimilarity], result of:
      0.03657866 = score(doc=990,freq=4.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.24703519 = fieldWeight in 990, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
  0.25 = coord(1/4)

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.

0.008992782 = product of:
  0.035971127 = sum of:
    0.035971127 = product of:
      0.071942255 = sum of:
        0.071942255 = weight(_text_:processing in 943) [ClassicSimilarity], result of:
          0.071942255 = score(doc=943,freq=4.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.3795138 = fieldWeight in 943, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046875 = fieldNorm(doc=943)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Abstract

This article discusses OpenAI's ChatGPT, a generative pre-trained transformer, which uses natural language processing to fulfill text-based user requests (i.e., a "chatbot"). The history and principles behind ChatGPT and similar models are discussed. This technology is then discussed in relation to its potential impact on academia and scholarly research and publishing. ChatGPT is seen as a potential model for the automated preparation of essays and other types of scholarly manuscripts. Potential ethical issues that could arise with the emergence of large language models like GPT-3, the underlying technology behind ChatGPT, and its usage by academics and researchers, are discussed and situated within the context of broader advancements in artificial intelligence, machine learning, and natural language processing for research and scholarly publishing.

0.007418666 = product of:
  0.029674664 = sum of:
    0.029674664 = product of:
      0.05934933 = sum of:
        0.05934933 = weight(_text_:processing in 790) [ClassicSimilarity], result of:
          0.05934933 = score(doc=790,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.3130829 = fieldWeight in 790, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0546875 = fieldNorm(doc=790)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Abstract

Dieses Kapitel gibt eine Übersicht über die maschinelle Verarbeitung natürlicher Sprachen (wie das Deutsche oder Englische; natural language - NL) durch Computer. Grundlegende Konzepte der automatischen Sprachverarbeitung (natural language processing - NLP) stammen aus der Sprachwissenschaft (s. Abschnitt 2) und sind in zunehmend selbstständiger Weise mit formalen Methoden und technischen Grundlagen der Informatik in einer eigenständigen Disziplin, der Computerlinguistik (CL; s. Abschnitte 3 und 4), verknüpft worden. Natürlichsprachliche Systeme (NatS) mit anwendungsbezogenen Funktionalitätsvorgaben bilden den Kern der informationswissenschaftlich geprägten NLP, die häufig als Sprachtechnologie oder im Deutschen auch (mittlerweile veraltet) als Informationslinguistik bezeichnet wird (s. Abschnitt 5).

0.007418666 = product of:
  0.029674664 = sum of:
    0.029674664 = product of:
      0.05934933 = sum of:
        0.05934933 = weight(_text_:processing in 1139) [ClassicSimilarity], result of:
          0.05934933 = score(doc=1139,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.3130829 = fieldWeight in 1139, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1139)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

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.

0.006466255 = product of:
  0.02586502 = sum of:
    0.02586502 = weight(_text_:data in 900) [ClassicSimilarity], result of:
      0.02586502 = score(doc=900,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17468026 = fieldWeight in 900, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=900)
  0.25 = coord(1/4)

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.

0.006401266 = product of:
  0.025605064 = sum of:
    0.025605064 = weight(_text_:data in 923) [ClassicSimilarity], result of:
      0.025605064 = score(doc=923,freq=4.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17292464 = fieldWeight in 923, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.02734375 = fieldNorm(doc=923)
  0.25 = coord(1/4)

Abstract

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.
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."

0.0063588563 = product of:
  0.025435425 = sum of:
    0.025435425 = product of:
      0.05087085 = sum of:
        0.05087085 = weight(_text_:processing in 869) [ClassicSimilarity], result of:
          0.05087085 = score(doc=869,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.26835677 = fieldWeight in 869, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046875 = fieldNorm(doc=869)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Abstract

Generative Pre-trained Transformer (GPT) models by OpenAI have taken natural language processing (NLP) community by storm by introducing very powerful language models. These models can perform various NLP tasks like question answering, textual entailment, text summarisation etc. without any supervised training. These language models need very few to no examples to understand the tasks and perform equivalent or even better than the state-of-the-art models trained in supervised fashion. In this article we will cover the journey of these models and understand how they have evolved over a period of 2 years. 1. Discussion of GPT-1 paper (Improving Language Understanding by Generative Pre-training). 2. Discussion of GPT-2 paper (Language Models are unsupervised multitask learners) and its subsequent improvements over GPT-1. 3. Discussion of GPT-3 paper (Language models are few shot learners) and the improvements which have made it one of the most powerful models NLP has seen till date. This article assumes familiarity with the basics of NLP terminologies and transformer architecture.

0.006344468 = product of:
  0.025377871 = sum of:
    0.025377871 = product of:
      0.050755743 = sum of:
        0.050755743 = weight(_text_:22 in 5749) [ClassicSimilarity], result of:
          0.050755743 = score(doc=5749,freq=2.0), product of:
            0.16398162 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046827413 = 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)
  0.25 = coord(1/4)

Date

2. 3.2020 19:04:22

0.006344468 = product of:
  0.025377871 = sum of:
    0.025377871 = product of:
      0.050755743 = sum of:
        0.050755743 = weight(_text_:22 in 835) [ClassicSimilarity], result of:
          0.050755743 = score(doc=835,freq=2.0), product of:
            0.16398162 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046827413 = queryNorm
            0.30952093 = fieldWeight in 835, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0625 = fieldNorm(doc=835)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Date

29.12.2022 18:22:55

0.006344468 = product of:
  0.025377871 = sum of:
    0.025377871 = product of:
      0.050755743 = sum of:
        0.050755743 = weight(_text_:22 in 912) [ClassicSimilarity], result of:
          0.050755743 = score(doc=912,freq=2.0), product of:
            0.16398162 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046827413 = queryNorm
            0.30952093 = fieldWeight in 912, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0625 = fieldNorm(doc=912)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Date

16. 3.2023 19:22:55