相关论文: HTCInfoMax: A Global Model for Hierarchical Text C…

The viral spread of fake news has caused great social harm, making fake news detection an urgent task. Current fake news detection methods rely heavily on text information by learning the extracted news content or writing style of internal…

Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous…

Recent advancements in recommender systems have focused on integrating knowledge graphs (KGs) to leverage their auxiliary information. The core idea of KG-enhanced recommenders is to incorporate rich semantic information for more accurate…

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods…

Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…

Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing…

Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain…

Recently, a number of competitive methods have tackled unsupervised representation learning by maximising the mutual information between the representations produced from augmentations. The resulting representations are then invariant to…

An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels.…

State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Transformer encoders…

Networks have been widely used to represent the relations between objects such as academic networks and social networks, and learning embedding for networks has thus garnered plenty of research attention. Self-supervised network…

Hypergraphs are characterized by complex topological structure, representing higher-order interactions among multiple entities through hyperedges. Lately, hypergraph-based deep learning methods to learn informative data representations for…

Noisy data, crawled from the web or supplied by volunteers such as Mechanical Turkers or citizen scientists, is considered an alternative to professionally labeled data. There has been research focused on mitigating the effects of label…

Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label…

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…

Hierarchical text classification (HTC) aims to assign one or more labels in the hierarchy for each text. Many methods represent this structure as a global hierarchy, leading to redundant graph structures. To address this, incorporating a…

This paper presents CAALM-TC (Combining Autoregressive and Autoencoder Language Models for Text Classification), a novel method that enhances text classification by integrating autoregressive and autoencoder language models. Autoregressive…

Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…

Some news headlines mislead readers with overrated or false information, and identifying them in advance will better assist readers in choosing proper news stories to consume. This research introduces million-scale pairs of news headline…