Related papers: SSMix: Saliency-Based Span Mixup for Text Classifi…

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotation costs, severely…

Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models' predictions transparent have inspired an…

Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving…

In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between…

Tree-structured neural network architectures for sentence encoding draw inspiration from the approach to semantic composition generally seen in formal linguistics, and have shown empirical improvements over comparable sequence models by…

The integration of large language models (LLMs) into information retrieval systems introduces new attack surfaces, particularly for adversarial ranking manipulations. We present $\textbf{StealthRank}$, a novel adversarial attack method that…

Self-supervised Learning (SSL) has recently gained much attention due to the high cost and data limitation in the training of supervised learning models. The current paradigm in the SSL is to utilize data augmentation at the input space to…

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to…

An accurate language identification tool is an absolute necessity for building complex NLP systems to be used on code-mixed data. Lot of work has been recently done on the same, but there's still room for improvement. Inspired from the…

Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and…

In this paper, we present a MLP-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications. In designing Triangular Mixer, we simplify the cross-token operation in MLP as the…

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from…

Randomized neural networks for representation learning have consistently achieved prominent results in texture recognition tasks, effectively combining the advantages of both traditional techniques and learning-based approaches. However,…

Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal. Previous methods for this task require manual feature…

Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and…

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more…

Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in…

MSmix is a recently developed R package implementing maximum likelihood estimation of finite mixtures of Mallows models with Spearman distance for full and partial rankings. The package is designed to implement computationally tractable…