Related papers: Semantic Text Compression for Classification

Learned image compression (LIC) techniques have achieved remarkable progress; however, effectively integrating high-level semantic information remains challenging. In this work, we present a \underline{S}emantic-\underline{E}nhanced…

Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it…

Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents often introduce redundant content. This issue not only weakens…

Word embeddings typically represent different meanings of a word in a single conflated vector. Empirical analysis of embeddings of ambiguous words is currently limited by the small size of manually annotated resources and by the fact that…

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant…

We propose semantic communication over wireless channels for various modalities, e.g., text and images, in a task-oriented communications setup where the task is classification. We present two approaches based on memory and learning. Both…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

Can textual data be compressed intelligently without losing accuracy in evaluating sentiment? In this study, we propose a novel evolutionary compression algorithm, PARSEC (PARts-of-Speech for sEntiment Compression), which makes use of…

Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise…

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore…

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Transformer-based embedding models frequently exhibit geometric pathologies, such as anisotropy and length-induced representation collapse, which can degrade downstream retrieval performance. While prior work often attributes these issues…

Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text. However, in most cases it is not possible to assign a direct…

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

Recent works on word representations mostly rely on predictive models. Distributed word representations (aka word embeddings) are trained to optimally predict the contexts in which the corresponding words tend to appear. Such models have…

Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…

Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the…

Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…