paper-with-me

Papers

Word Embedding Dimension Reduction via Weakly-Supervised Feature Selection

2024-07-17 · Jintang Xue, Yun-Cheng Wang, Chengwei Wei, C. -C. Jay Kuo

As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases, which can lead to a vast model size. Storing and processing word vectors are resource-demanding, especially for mobile edge-devices applications. This paper explores word embedding dimension reduction. To balance computational costs and performance, we propose an efficient and effective weakly-supervised feature selection method named WordFS. It has two variants, each utilizing novel criteria for feature selection. Experiments on various tasks (e.g., word and sentence similarity and binary and multi-class classification) indicate that the proposed WordFS model outperforms other dimension reduction methods at lower computational costs. We have released the code for reproducibility along with the paper.

📄 PDF Abstract BibTeX arXiv:2407.12342

Code (1)

jintangxue/wordfs 공식 구현

Tasks

Dimensionality Reductionfeature selectionMulti-class ClassificationSentenceSentence Similarity

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Simple and Effective Dimensionality Reduction for Word Embeddings

2017-08-11 · Vikas Raunak

Word embeddings have become the basic building blocks for several natural language processing and information retrieval tasks. Pre-trained word embeddings are used in several downstream applications as well as for constr…

Dimensionality ReductionInformation RetrievalRetrievalWord Embeddings+1

Understanding and Improving Multi-Sense Word Embeddings via Extended Robust Principal Component Analysis

2018-03-03 · Haoyue Shi, Yuqi Sun, Junfeng Hu

Unsupervised learned representations of polysemous words generate a large of pseudo multi senses since unsupervised methods are overly sensitive to contextual variations. In this paper, we address the pseudo multi-sense …

Dimensionality ReductionWord EmbeddingsWord Similarity

Factor Augmented Supervised Learning with Text Embeddings

2025-08-06 · Zhanye Luo, Yuefeng Han, Xiufan Yu arxiv

Large language models (LLMs) generate text embeddings from text data, producing vector representations that capture the semantic meaning and contextual relationships of words. However, the high dimensionality of these em…

Anomaly Detection

An Uncertainty-Aware Encoder for Aspect Detection

2021-11-01 · Findings (EMNLP) 2021 11 · Thi-Nhung Nguyen, Kiem-Hieu Nguyen, Young-In Song, Tuan-Dung Cao

Aspect detection is a fundamental task in opinion mining. Previous works use seed words either as priors of topic models, as anchors to guide the learning of aspects, or as features of aspect classifiers. This paper pres…

Opinion MiningTopic Models

SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings

2020-12-01 · COLING 2020 8 · Cindy Aloui, Carlos Ramisch, Alexis Nasr, Lucie Barque

Contextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances. However, their opaqueness makes it hard to interpret their behavi…