Related papers: Minimally Supervised Categorization of Text with M…

The recent advanced deep learning techniques have shown the promising results in various domains such as computer vision and natural language processing. The success of deep neural networks in supervised learning heavily relies on a large…

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…

Many applications require categorization of text documents using predefined categories. The main approach to performing text categorization is learning from labeled examples. For many tasks, it may be difficult to find examples in one…

Manually labeling documents is tedious and expensive, but it is essential for training a traditional text classifier. In recent years, a few dataless text classification techniques have been proposed to address this problem. However,…

The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last ten years, due to the increased availability of documents in digital form and the ensuing need to organize…

Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks. We describe TAGLETS,…

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…

Scientific document classification is a critical task for a wide range of applications, but the cost of obtaining massive amounts of human-labeled data can be prohibitive. To address this challenge, we propose a weakly-supervised approach…

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations…

Short video recommendations often face limitations due to the quality of user feedback, which may not accurately depict user interests. To tackle this challenge, a new task has emerged: generating more dependable labels from original…

Metadata presents a medium for connection, elaboration, examination, and comprehension of relativity between two datasets. Metadata can be enriched to calculate the existence of a connection between different disintegrated datasets. In…

In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more,…

Creating large, good quality labeled data has become one of the major bottlenecks for developing machine learning applications. Multiple techniques have been developed to either decrease the dependence of labeled data (zero/few-shot…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

We study open-world multi-label text classification under extremely weak supervision (XWS), where the user only provides a brief description for classification objectives without any labels or ground-truth label space. Similar single-label…

Most existing scene text detectors require large-scale training data which cannot scale well due to two major factors: 1) scene text images often have domain-specific distributions; 2) collecting large-scale annotated scene text images is…

In this paper we propose a new document classification method, bridging discrepancies (so-called semantic gap) between the training set and the application sets of textual data. We demonstrate its superiority over classical text…