paper-with-me

Papers

Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation

2026-06-01 · Woojun Jung, Susik Yoon arxiv

Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining framework that treats each header-value pair as the unit for aggregating schema-level structural evidence and column-level distributional evidence. We realize this design through Masked Segment Modeling and Entropy-driven Segment Alignment, which jointly enforce structured header-value coupling and semantic alignment across stable and instance-specific attributes. Experiments on heterogeneous in-domain tables show improved reconstruction, semantic consistency, and downstream utility across evaluation settings overall.

📄 PDF Abstract BibTeX arXiv:2606.01890

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models

2019-01-30 · Janneke van de Loo, Jort F. Gemmeke, Guy De Pauw, Bart Ons 외

We present a framework for the induction of semantic frames from utterances in the context of an adaptive command-and-control interface. The system is trained on an individual user's utterances and the corresponding sema…

Weakly Supervised Classification

SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation

2026-04-25 · Kaiwen Huang, Yi Zhou, Yizhe Zhang, Jingxiong Li 외 arxiv

Semi-supervised learning addresses label scarcity and high annotation costs in medical image segmentation by exploiting the latent information in unlabeled data to enhance model performance. Traditional discriminative se…

Semi-supervised Medical Image SegmentationRepresentation Learning

Improving Neural Language Models by Segmenting, Attending, and Predicting the Future

2019-06-04 · ACL 2019 7 · Hongyin Luo, Lan Jiang, Yonatan Belinkov, James Glass

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does …

Language ModelingLanguage ModellingSegmentation

CMaP-SAM: Contraction Mapping Prior for SAM-driven Few-shot Segmentation

2025-04-07 · Shuai Chen, Fanman Meng, Haoran Wei, Chenhao Wu 외

Few-shot segmentation (FSS) aims to segment new classes using few annotated images. While recent FSS methods have shown considerable improvements by leveraging Segment Anything Model (SAM), they face two critical limitat…

PositionSegmentation

Joint Learning Templates and Slots for Event Schema Induction

2016-03-04 · NAACL 2016 6 · Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui

Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type…

Image SegmentationSemantic SegmentationSentence