Related papers: Text Classification Using Label Names Only: A Lang…
Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature.…
Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to…
As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…
In this paper, we introduce a novel weighted co-training approach that is guided by Large Language Models (LLMs). Namely, in our co-training approach, we use LLM labels on unlabeled data as target labels and co-train two encoder-only based…
Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training…
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…
Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems. This means classifiers must generalize from limited evidence, but…
Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these…
Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…
We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data. We consider a setting with multiple classification problems where the target classes may be tied together through logical constraints. For…
Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data…
Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…
Text classification is the task of assigning a document to a predefined class. However, it is expensive to acquire enough labeled documents or to label them. In this paper, we study the regularization methods' effects on various…
Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…
In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…
We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self-Pretraining is threshold-free, it can potentially update…
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…
In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into…
Text classification is crucial for applications such as sentiment analysis and toxic text filtering, but it still faces challenges due to the complexity and ambiguity of natural language. Recent advancements in deep learning, particularly…