paper-with-me

홈 › Papers

SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment

2018-06-14 · ACL 2018 7 · Jisun An, Haewoon Kwak, Yong-Yeol Ahn

Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word- vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.

📄 PDF Abstract BibTeX arXiv:1806.05521

Code (1)

ghdi6758/SemAxis 공식 구현

Similar Papers 제목 키워드 기반

Using Full-Text Content to Characterize and Identify Best Seller Books

2022-10-05 · Giovana D. da Silva, Filipi N. Silva, Henrique F. de Arruda, Bárbara C. e Souza 외

Artistic pieces can be studied from several perspectives, one example being their reception among readers over time. In the present work, we approach this interesting topic from the standpoint of literary works, particul…

A Causal Inspired Early-Branching Structure for Domain Generalization

2024-03-13 · Liang Chen, Yong Zhang, Yibing Song, Zhen Zhang 외

Learning domain-invariant semantic representations is crucial for achieving domain generalization (DG), where a model is required to perform well on unseen target domains. One critical challenge is that standard training…

Domain Generalization

SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings

2023-01-11 · Jan Engler, Sandipan Sikdar, Marlene Lutz, Markus Strohmaier

Adding interpretability to word embeddings represents an area of active research in text representation. Recent work has explored thepotential of embedding words via so-called polar dimensions (e.g. good vs. bad, correct…

Word Embeddings

3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

2022-01-01 · CVPR 2022 1 · Daigang Cai, Lichen Zhao, Jing Zhang, Lu Sheng 외

Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closel…

3D dense captioningAttributeDense CaptioningVisual Grounding

Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network

2023-02-07 · Jinyu Zhang, Huichuan Duan, Lei Guo, Liancheng Xu 외

Cross-domain Sequential Recommendation (CSR) is an emerging yet challenging task that depicts the evolution of behavior patterns for overlapped users by modeling their interactions from multiple domains. Existing studies…

Collaborative FilteringSequential Recommendation