paper-with-me

Papers

Improving Semantic Composition with Offset Inference

2017-04-21 · ACL 2017 7 · Thomas Kober, Julie Weeds, Jeremy Reffin, David Weir

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.

📄 PDF Abstract BibTeX arXiv:1704.06692

Code (1)

tttthomasssss/acl2017 공식 구현

Tasks

Semantic Composition

Similar Papers 제목 키워드 기반

Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking

2026-04-02 · Zhanliang Wang, Hongzhuo Chen, Quan Minh Nguyen, Mian Umair Ahsan 외 arxiv

Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent classes at inference time. Existing post-hoc methods such as …

Image ClassificationScene Recognition

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

2025-08-12 · Shi-Chen Zhang, Yunheng Li, Yu-Huan Wu, Qibin Hou 외 arxiv

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-t…

Semantic SegmentationScene Understanding

SD-GAN: Semantic Decomposition for Face Image Synthesis with Discrete Attribute

2022-07-12 · Zhou Kangneng, Zhu Xiaobin, Gao Daiheng, Lee Kai 외

Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face …

AttributeImage Generation

ConceptWeaver: Weaving Disentangled Concepts with Flow

2026-03-30 · Jintao Chen, Aiming Hao, Xiaoqing Chen, Chengyu Bai 외 arxiv

Pre-trained flow-based models excel at synthesizing complex scenes yet lack a direct mechanism for disentangling and customizing their underlying concepts from one-shot real-world sources. To demystify this process, we f…

OVeNet: Offset Vector Network for Semantic Segmentation

2023-03-25 · Stamatis Alexandropoulos, Christos Sakaridis, Petros Maragos

Semantic segmentation is a fundamental task in visual scene understanding. We focus on the supervised setting, where ground-truth semantic annotations are available. Based on knowledge about the high regularity of real-w…

Optical Character Recognition (OCR)Scene UnderstandingSemantic Segmentation