Related papers: Minimally Supervised Categorization of Text with M…
Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by…
Automatic hashtag annotation plays an important role in content understanding for microblog posts. To date, progress made in this field has been restricted to phrase selection from limited candidates, or word-level hashtag discovery using…
Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons. While the existing approaches tackle this problem using a lexically…
To advance the development of science and technology, research proposals are submitted to open-court competitive programs developed by government agencies (e.g., NSF). Proposal classification is one of the most important tasks to achieve…
We study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly available datasets. We also propose an attention-based graph…
Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to…
In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects,…
In this paper, we tackle the problem of selecting the optimal model for a given structured pattern classification dataset. In this context, a model can be understood as a classifier and a hyperparameter configuration. The proposed…
One of the emerging techniques in node classification in heterogeneous graphs is to restrict message aggregation to pre-defined, semantically meaningful structures called metapaths. This work is the first attempt to incorporate attention…
Healthcare providers usually record detailed notes of the clinical care delivered to each patient for clinical, research, and billing purposes. Due to the unstructured nature of these narratives, providers employ dedicated staff to assign…
Semi-supervised classification is an interesting idea where classification models are learned from both labeled and unlabeled data. It has several advantages over supervised classification in natural language processing domain. For…
Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…
Few-shot learning aims to handle previously unseen tasks using only a small amount of new training data. In preparing (or meta-training) a few-shot learner, however, massive labeled data are necessary. In the real world, unfortunately,…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…
One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the…
BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…
The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on…
Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this…
Supervisory signals are a critical resource for training learning to rank models. In many real-world search and retrieval scenarios, these signals may not be readily available or could be costly to obtain for some queries. The examples…
The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…