Related papers: Text Categorization via Similarity Search: An Effi…

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…

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e.,…

The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate with their internal semantics undocumented or even…

In this paper we introduce a method to detect words or phrases in a given sequence of alphabets without knowing the lexicon. Our linear time unsupervised algorithm relies entirely on statistical relationships among alphabets in the input…

We explore the use of semantic word embeddings in text segmentation algorithms, including the C99 segmentation algorithm and new algorithms inspired by the distributed word vector representation. By developing a general framework for…

This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes. A novel bootstrapping technique is designed which samples multiple 'subsections' of a…

Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

Many current state-of-the-art methods for text recognition are based on purely local information and ignore the semantic correlation between text and its surrounding visual context. In this paper, we propose a post-processing approach to…

When searching for information, a human reader first glances over a document, spots relevant sections and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates to identify…

Representing documents into high dimensional embedding space while preserving the structural similarity between document sources has been an ultimate goal for many works on text representation learning. Current embedding models, however,…

This paper proposes integrating semantics-oriented similarity representation into RankingMatch, a recently proposed semi-supervised learning method. Our method, dubbed ReRankMatch, aims to deal with the case in which labeled and unlabeled…

Word feature vectors have been proven to improve many NLP tasks. With recent advances in unsupervised learning of these feature vectors, it became possible to train it with much more data, which also resulted in better quality of learned…

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an…

Tabular data is considered the last unconquered castle of deep learning, yet the task of data stream classification is stated to be an equally important and demanding research area. Due to the temporal constraints, it is assumed that deep…

The performance of many machine learning techniques depends on the choice of an appropriate similarity or distance measure on the input space. Similarity learning (or metric learning) aims at building such a measure from training data so…

As the Internet grows in size, so does the amount of text based information that exists. For many application spaces it is paramount to isolate and identify texts that relate to a particular topic. While one-class classification would be…

Class distribution mismatch (CDM) refers to the discrepancy between class distributions in training data and target tasks. Previous methods address this by designing classifiers to categorize classes known during training, while grouping…

Classifying research papers according to their research topics is an important task to improve their retrievability, assist the creation of smart analytics, and support a variety of approaches for analysing and making sense of the research…