Search (38 results, page 2 of 2)

  • × language_ss:"e"
  • × theme_ss:"Computerlinguistik"
  • × year_i:[2020 TO 2030}
  1. Al-Khatib, K.; Ghosa, T.; Hou, Y.; Waard, A. de; Freitag, D.: Argument mining for scholarly document processing : taking stock and looking ahead (2021) 0.00 
    0.0020506454 = product of:
  0.004101291 = sum of:
    0.004101291 = product of:
      0.008202582 = sum of:
        0.008202582 = weight(_text_:a in 568) [ClassicSimilarity], result of:
          0.008202582 = score(doc=568,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1544581 = fieldWeight in 568, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=568)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  2. Corbara, S.; Moreo, A.; Sebastiani, F.: Syllabic quantity patterns as rhythmic features for Latin authorship attribution (2023) 0.00 
    0.0020296127 = product of:
  0.0040592253 = sum of:
    0.0040592253 = product of:
      0.008118451 = sum of:
        0.008118451 = weight(_text_:a in 846) [ClassicSimilarity], result of:
          0.008118451 = score(doc=846,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.15287387 = fieldWeight in 846, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=846)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  3. Metz, C.: ¬The new chatbots could change the world : can you trust them? (2022) 0.00 
    0.0020296127 = product of:
  0.0040592253 = sum of:
    0.0040592253 = product of:
      0.008118451 = sum of:
        0.008118451 = weight(_text_:a in 854) [ClassicSimilarity], result of:
          0.008118451 = score(doc=854,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.15287387 = fieldWeight in 854, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.09375 = fieldNorm(doc=854)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Type
    a
  4. Azpiazu, I.M.; Soledad Pera, M.: Is cross-lingual readability assessment possible? (2020) 0.00 
    0.001913537 = product of:
  0.003827074 = sum of:
    0.003827074 = product of:
      0.007654148 = sum of:
        0.007654148 = weight(_text_:a in 5868) [ClassicSimilarity], result of:
          0.007654148 = score(doc=5868,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14413087 = fieldWeight in 5868, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.03125 = fieldNorm(doc=5868)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    Most research efforts related to automatic readability assessment focus on the design of strategies that apply to a specific language. These state-of-the-art strategies are highly dependent on linguistic features that best suit the language for which they were intended, constraining their adaptability and making it difficult to determine whether they would remain effective if they were applied to estimate the level of difficulty of texts in other languages. In this article, we present the results of a study designed to determine the feasibility of a cross-lingual readability assessment strategy. For doing so, we first analyzed the most common features used for readability assessment and determined their influence on the readability prediction process of 6 different languages: English, Spanish, Basque, Italian, French, and Catalan. In addition, we developed a cross-lingual readability assessment strategy that serves as a means to empirically explore the potential advantages of employing a single strategy (and set of features) for readability assessment in different languages, including interlanguage prediction agreement and prediction accuracy improvement for low-resource languages.Friend request acceptance and information disclosure constitute 2 important privacy decisions for users to control the flow of their personal information in social network sites (SNSs). These decisions are greatly influenced by contextual characteristics of the request. However, the contextual influence may not be uniform among users with different levels of privacy concerns. In this study, we hypothesize that users with higher privacy concerns may consider contextual factors differently from those with lower privacy concerns. By conducting a scenario-based survey study and structural equation modeling, we verify the interaction effects between privacy concerns and contextual factors. We additionally find that users' perceived risk towards the requester mediates the effect of context and privacy concerns. These results extend our understanding about the cognitive process behind privacy decision making in SNSs. The interaction effects suggest strategies for SNS providers to predict user's friend request acceptance and to customize context-aware privacy decision support based on users' different privacy attitudes.
    Type
    a
  5. Lee, G.E.; Sun, A.: Understanding the stability of medical concept embeddings (2021) 0.00 
    0.0018909799 = product of:
  0.0037819599 = sum of:
    0.0037819599 = product of:
      0.0075639198 = sum of:
        0.0075639198 = weight(_text_:a in 159) [ClassicSimilarity], result of:
          0.0075639198 = score(doc=159,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14243183 = fieldWeight in 159, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=159)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  6. Andrushchenko, M.; Sandberg, K.; Turunen, R.; Marjanen, J.; Hatavara, M.; Kurunmäki, J.; Nummenmaa, T.; Hyvärinen, M.; Teräs, K.; Peltonen, J.; Nummenmaa, J.: Using parsed and annotated corpora to analyze parliamentarians' talk in Finland (2022) 0.00 
    0.0018909799 = product of:
  0.0037819599 = sum of:
    0.0037819599 = product of:
      0.0075639198 = sum of:
        0.0075639198 = weight(_text_:a in 471) [ClassicSimilarity], result of:
          0.0075639198 = score(doc=471,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14243183 = fieldWeight in 471, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=471)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  7. Ali, C.B.; Haddad, H.; Slimani, Y.: Multi-word terms selection for information retrieval (2022) 0.00 
    0.0018909799 = product of:
  0.0037819599 = sum of:
    0.0037819599 = product of:
      0.0075639198 = sum of:
        0.0075639198 = weight(_text_:a in 900) [ClassicSimilarity], result of:
          0.0075639198 = score(doc=900,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14243183 = fieldWeight in 900, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=900)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  8. Meng, K.; Ba, Z.; Ma, Y.; Li, G.: ¬A network coupling approach to detecting hierarchical linkages between science and technology (2024) 0.00 
    0.001757696 = product of:
  0.003515392 = sum of:
    0.003515392 = product of:
      0.007030784 = sum of:
        0.007030784 = weight(_text_:a in 1205) [ClassicSimilarity], result of:
          0.007030784 = score(doc=1205,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.13239266 = fieldWeight in 1205, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=1205)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  9. Zhang, Y.; Zhang, C.; Li, J.: Joint modeling of characters, words, and conversation contexts for microblog keyphrase extraction (2020) 0.00 
    0.0016913437 = product of:
  0.0033826875 = sum of:
    0.0033826875 = product of:
      0.006765375 = sum of:
        0.006765375 = weight(_text_:a in 5816) [ClassicSimilarity], result of:
          0.006765375 = score(doc=5816,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12739488 = fieldWeight in 5816, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5816)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  10. Harari, Y.N.: ¬[Yuval-Noah-Harari-argues-that] AI has hacked the operating system of human civilisation (2023) 0.00 
    0.0016913437 = product of:
  0.0033826875 = sum of:
    0.0033826875 = product of:
      0.006765375 = sum of:
        0.006765375 = weight(_text_:a in 953) [ClassicSimilarity], result of:
          0.006765375 = score(doc=953,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12739488 = fieldWeight in 953, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.078125 = fieldNorm(doc=953)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Type
    a
  11. Laparra, E.; Binford-Walsh, A.; Emerson, K.; Miller, M.L.; López-Hoffman, L.; Currim, F.; Bethard, S.: Addressing structural hurdles for metadata extraction from environmental impact statements (2023) 0.00 
    0.0016913437 = product of:
  0.0033826875 = sum of:
    0.0033826875 = product of:
      0.006765375 = sum of:
        0.006765375 = weight(_text_:a in 1042) [ClassicSimilarity], result of:
          0.006765375 = score(doc=1042,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12739488 = fieldWeight in 1042, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1042)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  12. Aizawa, A.; Kohlhase, M.: Mathematical information retrieval (2021) 0.00 
    0.001674345 = product of:
  0.00334869 = sum of:
    0.00334869 = product of:
      0.00669738 = sum of:
        0.00669738 = weight(_text_:a in 667) [ClassicSimilarity], result of:
          0.00669738 = score(doc=667,freq=4.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12611452 = fieldWeight in 667, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=667)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Type
    a
  13. Zhai, X.: ChatGPT user experience: : implications for education (2022) 0.00 
    0.0014647468 = product of:
  0.0029294936 = sum of:
    0.0029294936 = product of:
      0.005858987 = sum of:
        0.005858987 = weight(_text_:a in 849) [ClassicSimilarity], result of:
          0.005858987 = score(doc=849,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.11032722 = fieldWeight in 849, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=849)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
  14. Tao, J.; Zhou, L.; Hickey, K.: Making sense of the black-boxes : toward interpretable text classification using deep learning models (2023) 0.00 
    0.0014647468 = product of:
  0.0029294936 = sum of:
    0.0029294936 = product of:
      0.005858987 = sum of:
        0.005858987 = weight(_text_:a in 990) [ClassicSimilarity], result of:
          0.005858987 = score(doc=990,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.11032722 = fieldWeight in 990, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=990)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  15. Shree, P.: ¬The journey of Open AI GPT models (2020) 0.00 
    0.0014351527 = product of:
  0.0028703054 = sum of:
    0.0028703054 = product of:
      0.005740611 = sum of:
        0.005740611 = weight(_text_:a in 869) [ClassicSimilarity], result of:
          0.005740611 = score(doc=869,freq=4.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.10809815 = fieldWeight in 869, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=869)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  16. Xiang, R.; Chersoni, E.; Lu, Q.; Huang, C.-R.; Li, W.; Long, Y.: Lexical data augmentation for sentiment analysis (2021) 0.00 
    0.0011959607 = product of:
  0.0023919214 = sum of:
    0.0023919214 = product of:
      0.0047838427 = sum of:
        0.0047838427 = weight(_text_:a in 392) [ClassicSimilarity], result of:
          0.0047838427 = score(doc=392,freq=4.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.090081796 = fieldWeight in 392, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=392)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    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.
    Type
    a
  17. Chou, C.; Chu, T.: ¬An analysis of BERT (NLP) for assisted subject indexing for Project Gutenberg (2022) 0.00 
    0.0011839407 = product of:
  0.0023678814 = sum of:
    0.0023678814 = product of:
      0.0047357627 = sum of:
        0.0047357627 = weight(_text_:a in 1139) [ClassicSimilarity], result of:
          0.0047357627 = score(doc=1139,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.089176424 = fieldWeight in 1139, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1139)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Type
    a
  18. Zaitseva, E.M.: Developing linguistic tools of thematic search in library information systems (2023) 0.00 
    8.4567186E-4 = product of:
  0.0016913437 = sum of:
    0.0016913437 = product of:
      0.0033826875 = sum of:
        0.0033826875 = weight(_text_:a in 1187) [ClassicSimilarity], result of:
          0.0033826875 = score(doc=1187,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.06369744 = fieldWeight in 1187, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1187)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Type
    a

Authors

Types

  • a 29
  • el 16
  • p 7
  • x 1
  • More… Less…

Themes