Results 31 to 40 of about 623,633 (264)
Реализация параллельного алгоритма извлечения N-gram из текста на функциональном языке
Вестник КазНУ. Серия математика, механика, информатика, 2020 В данной статье рассматривается реализация параллельного алгоритма извлечения N-gram из слабоструктурированного текста на функциональном языке системы LuNA реализующий технологию фрагментированного программирования. Алгоритм извлечения N-gram относится к
B. S. Daribayev +2 more
doaj +1 more source
Morphological Skip-Gram: Replacing FastText characters n-gram with morphological knowledge
Inteligencia Artificial, 2021 Natural language processing systems have attracted much interest of the industry. This branch of study is composed of some applications such as machine translation, sentiment analysis, named entity recognition, question and answer, and others.
Thiago Dias Bispo +3 more
doaj +1 more source
N-Gram Representations For Comment Filtering [PDF]
Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 2015 Accurate classifiers for short texts are valuable assets in many applications. Especially in online communities, where users contribute to content in the form of posts and com- ments, an effective way of automatically categorising posts proves highly valuable.
Brand, D. +3 more
openaire +2 more sources
Language Modeling with Power Low Rank Ensembles [PDF]
, 2014 We present power low rank ensembles (PLRE), a flexible framework for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of words in context.
Dyer, Chris +3 more
core +2 more sources
Document Categorization with Modified Statistical Language Models for Agglutinative Languages [PDF]
International Journal of Computational Intelligence Systems, 2010 In this paper, we investigate the document categorization task with statistical language models. Our study mainly focuses on categorization of documents in agglutinative languages.
Ahmet Cüneyd Tantug
doaj +1 more source
Auto-Sizing Neural Networks: With Applications to n-gram Language Models [PDF]
, 2015 Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings.
Chiang, David, Murray, Kenton
core +1 more source
, 2009 In language modeling, n-gram models are probabilistic models of text that use some limited amount of history, or word dependencies, where n refers to the number of words that participate in the dependence relation.
openaire +1 more source
Continuous N-gram Representations for Authorship Attribution [PDF]
, 2017 This paper presents work on using continuous representations for authorship attribution. In contrast to previous work, which uses discrete feature representations, our model learns continuous representations for n-gram features via a neural network
Sari, Y., Stevenson, R.M., Vlachos, A.
core +1 more source
Better Word Embeddings by Disentangling Contextual n-Gram Information
, 2019 Pre-trained word vectors are ubiquitous in Natural Language Processing applications. In this paper, we show how training word embeddings jointly with bigram and even trigram embeddings, results in improved unigram embeddings.
Gupta, Prakhar +2 more
core +1 more source
Pseudo-Conventional N-Gram Representation of the Discriminative N-Gram Model for LVCSR [PDF]
IEEE Journal of Selected Topics in Signal Processing, 2010 The discriminative n-gram modeling approach re-ranks the N-best hypotheses generated during decoding and can effectively improve the performance of large-vocabulary continuous speech recognition (LVCSR). This work recasts the discriminative n-gram model as a pseudo-conventional n-gram model.
Zhengyu Zhou, Helen Meng
openaire +1 more source