paper-with-me

홈 › Papers

Delta Embedding Learning

2018-12-11 · ACL 2019 7 · Xiao Zhang, Ji Wu, Dejing Dou

Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without "forgetting." We apply the method to various NLP tasks and see a consistent improvement in performance. Evaluation also confirms the tuned word embeddings have better semantic properties.

📄 PDF Abstract BibTeX arXiv:1812.04160

Code (0)

등록된 구현이 없습니다.

Tasks

Reading ComprehensionWord Embeddings

Similar Papers 제목 키워드 기반

Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR

2026-01-28 · Zilai Wang, Natarajan Balaji Shankar, Kaiyuan Zhang, Zihan Wang 외 arxiv

Self-supervised learning (SSL) models have achieved impressive results across many speech tasks, yet child automatic speech recognition (ASR) remains challenging due to limited data and pretraining domain mismatch. Fine-…

Self-Supervised LearningSpeech Recognition

Near-Optimal Bounds for Binary Embeddings of Arbitrary Sets

2015-12-14 · Samet Oymak, Ben Recht

We study embedding a subset $K$ of the unit sphere to the Hamming cube $\{-1,+1\}^m$. We characterize the tradeoff between distortion and sample complexity $m$ in terms of the Gaussian width $\omega(K)$ of the set. For s…

Metric Embeddings Beyond Bi-Lipschitz Distortion via Sherali-Adams

2023-11-29 · Ainesh Bakshi, Vincent Cohen-Addad, Samuel B. Hopkins, Rajesh Jayaram 외

Metric embeddings are a widely used method in algorithm design, where generally a ``complex'' metric is embedded into a simpler, lower-dimensional one. Historically, the theoretical computer science community has focused…

Data Visualization

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

2025-08-14 · Eunseo Koh, Seunghoo Hong, Tae-Young Kim, Simon S. Woo 외 arxiv

Text-to-Image (T2I) diffusion models have made significant progress in generating diverse high-quality images from textual prompts. However, these models still face challenges in suppressing content that is strongly enta…

DELTA: Dynamic Embedding Learning with Truncated Conscious Attention for CTR Prediction

2023-05-03 · Chen Zhu, Liang Du, Hong Chen, Shuang Zhao 외

Click-Through Rate (CTR) prediction is a pivotal task in product and content recommendation, where learning effective feature embeddings is of great significance. However, traditional methods typically learn fixed featur…

Click-Through Rate Prediction