Knowledge Based Hyperbolic Propagation

Tai, Chang-You; Huang, Chien-Kun; Huang, Liang-Ying; Ku, Lun-Wei

doi:10.1145/3404835.3462980

Cited by 3 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To model the interdependence of seed word pairs, we use the hyperbolic distance function d P () to achieve fine-grained relationship modeling, since hyperbolic space offers the ability to not only preserve hierarchical (tree-like) information (Nickel and Kiela 2017;Zhang and Gao 2020;Gülc ¸ehre et al 2018;Chami et al 2019) but also nuanced differences (to better group them) (Sun et al 2021;Tai et al 2021) and outperforms Euclidean counterparts in various kinds of data (Zhang and Gao 2020;Gülc ¸ehre et al 2018;Chami et al 2019Chami et al , 2020Sun et al 2021;Tai et al 2021). Thus, it is assumed that with more space (hyperbolic space) to organize points, the model can divide disentangled representations and better group them.…”

Section: Hyperbolic Disentangled Aspect Extractormentioning

confidence: 99%

Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction

Tai

2022

AAAI

Self Cite

View full text Add to dashboard Cite

Automatic identification of salient aspects from user reviews is especially useful for opinion analysis. There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers. However, there is always room for improvement. First, no weakly supervised approaches fully utilize latent hierarchies between words. Second, each seed word’s representation should have different latent semantics and be distinct when it represents a different aspect. In this paper we propose HDAE, a hyperbolic disentangled aspect extractor in which a hyperbolic aspect classifier captures words’ latent hierarchies, and an aspect-disentangled representation models the distinct latent semantics of each seed word. Compared to previous baselines, HDAE achieves average F1 performance gains of 18.2% and 24.1% on Amazon product review and restaurant review datasets, respectively. In addition, the embedding visualization experience demonstrates that HDAE is a more effective approach to leveraging seed words. An ablation study and a case study further attest the effectiveness of the proposed components.

show abstract