Встраивание Документа
Related Papers
Learning Outside the Box: Discourse-level Features Improve Metaphor Identification
AbstractMost current approaches to metaphor identification use restricted linguistic contexts, e.g. by considering only a verb’s arguments or the sentence containing a phrase. Inspired by pragmatic accounts of metaphor, we …...
Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
AbstractText classification is fundamental in natural language processing (NLP) and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual …...
LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text Classification
AbstractText classification has achieved great success with the prosperity of deep learning and pre-trained language models. However, we often encounter labeled data deficiency problems in real-world text-classification tasks. To overcome …...
Multilingual and Multimodal Topic Modelling with Pretrained Embeddings
AbstractThis paper presents M3L-Contrast—a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is …...