Search Constraints

Number of results to display per page
Results for: Learning-to-learn Remove constraint Learning-to-learn Keywords Computational linguistics Remove constraint Keywords: Computational linguistics

Search Results

  • Video 
    Distinguished lectures in humanities : language learning in humans and machines : two sides of the same coin

    Distinguished lectures in humanities : language learning in humans and machines : two sides of the same coin

    Psychology, Computer Science and Neuroscience have a history of shared questions and inter-related advances. Recently, new technology has enabled those fields to move from “toy” small-scale approaches to the study of language learning from raw sensory input and to do so at a large scale that constitutes daily life. The three primary goals of my research are 1) to quantify the statistical regularities in the real world, 2) to examine the underlying computational mechanisms operated on the statistical data, and 3) to apply the findings from basic science to real-world applications. In this talk, I will present several projects in my research lab to show that the advances in human learning and machine learning fields place us at the tipping point for powerful and consequential new insights into mechanisms of (and algorithms for) learning.

    Event Date: 28/06/2023
    Speaker: Prof. Chen YU (University of Texas at Austin)
    Hosted by: Faculty of Humanities

    Subjects:
    Language and Languages
    Keywords:
    Computational linguistics Language acquisition Machine learning
    Resource Type:
    Video
     
  • Presentation 
    Analyzing Word Frequencies in Large Text Corpora using Inter-arrival Times and Bootstrapping

    Analyzing Word Frequencies in Large Text Corpora using Inter-arrival Times and Bootstrapping

    This video was recorded at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Athens 2011. Comparing frequency counts over texts or corpora is an important task in many applications and scientific disciplines. Given a text corpus, we want to test a hypothesis, such as "word X is frequent", "word X has become more frequent over time", or "word X is more frequent in male than in female speech". For this purpose we need a null model of word frequencies. The commonly used bag-of-words model, which corresponds to a Bernoulli process with fixed parameter, does not account for any structure present in natural languages. Using this model for word frequencies results in large numbers of words being reported as unexpectedly frequent. We address how to take into account the inherent occurrence patterns of words in significance testing of word frequencies. Based on studies of words in two large corpora, we propose two methods for modeling word frequencies that both take into account the occurrence patterns of words and go beyond the bag-of-words assumption. The first method models word frequencies based on the spatial distribution of individual words in the language. The second method is based on bootstrapping and takes into account only word frequency at the text level. The proposed methods are compared to the current gold standard in a series of experiments on both corpora. We find that words obey different spatial patterns in the language, ranging from bursty to non-bursty/uniform, independent of their frequency, showing that the traditional approach leads to many false positives.

    Subjects:
    Computing, Data Science and Artificial Intelligence and Management
    Keywords:
    Computational linguistics Text processing (Computer science) Discourse analysis -- Data processing
    Resource Type:
    Presentation
     
    OER