Blar i Institutt for IKT og realfag på forfatter "Pasquine, Mark"
-
Deep Learning for Low-Resource and Morphology-Rich Language Processing
Sun, Mengtao (Doctoral theses at NTNU;2023:50, Doctoral thesis, 2023)Since data-driven Natural Language Processing (NLP) approaches emerged in the late 60s, many practical applications have been proposed, such as automatic sentiment analyzers and named entity recognizers. Today, the robust ... -
Learning the Morphological and Syntactic Grammars for Named Entity Recognition
Sun, Mengtao; Yang, Qiang; Wang, Hao; Pasquine, Mark; Hameed, Ibrahim A. (Journal article; Peer reviewed, 2022)In some languages, Named Entity Recognition (NER) is severely hindered by complex linguistic structures, such as inflection, that will confuse the data-driven models when perceiving the word’s actual meaning. This work ... -
Machine Translation in Low-Resource Languages by an Adversarial Neural Network
Sun, Mengtao; Wang, Hao; Pasquine, Mark; Abdelfattah Abdelhameed, Ibrahim (Peer reviewed; Journal article, 2021)Existing Sequence-to-Sequence (Seq2Seq) Neural Machine Translation (NMT) shows strong capability with High-Resource Languages (HRLs). However, this approach poses serious challenges when processing Low-Resource Languages ... -
Perceiving the Narrative Style for Fake News Detection Using Deep Learning
Sun, Mengtao; Hameed, Ibrahim A.; Wang, Hao; Pasquine, Mark (Chapter, 2021)Existing deep-learning-based features have shown strong enough results (more than 90% accuracy) if a large amount of annotated data is available. However, in reality, data annotation is labor-intensive and expensive. This ... -
Skip Truncation for Sentiment Analysis of Long Review Information Based on Grammatical Structures
Sun, Mengtao; Hameed, Ibrahim A.; Wang, Hao; Pasquine, Mark (Peer reviewed; Journal article, 2022)In reality, some emotional utterances are especially long, such as the critiques of a movie. Compared with short sentences, the sentiment of a longer paragraph is more difficult to be detected. Moreover, longer paragraphs ...