Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification
28. listopadu 2022
Řečníci
Karish Grover
Speaker · 0 followers
Phaneendra Angara
Speaker · 0 followers
Md. Shad Akhtar
Speaker · 0 followers
Tanmoy Chakraborty
Speaker · 0 followers
O prezentaci
Social media has become the fulcrum of all forms of communication. Classifying social texts such as fake news, rumour, sarcasm, etc. has gained significant attention. The surface-level signals expressed by a social-text itself may not be adequate for such tasks; therefore, recent methods attempted to incorporate other intrinsic signals such as user behavior and the underlying graph structure. Oftentimes, the `public wisdom' expressed through the comments/replies to a social-text acts as a surrogate of crowd-sourced view and may provide us with complementary signals. State-of-the-art methods on social-text classification tend to ignore such a rich hierarchical signal. Here, we propose Hyphen, a discourse-aware hyperbolic spectral co-attention network. Hyphen is a fusion of hyperbolic graph representation learning with a novel Fourier co-attention mechanism in an attempt to generalise the social-text classification tasks by incorporating public discourse. We parse public discourse as an Abstract Meaning Representation (AMR) graph and use the powerful hyperbolic geometric representation to model graphs with hierarchical structure. Finally, we equip it with a novel Fourier co-attention mechanism to capture the correlation between the source post and public discourse. Extensive experiments on four different social-text classification tasks, namely detecting fake news, hate speech, rumour, and sarcasm, show that Hyphen generalises well, and achieves state-of-the-art results on ten benchmark datasets. We also employ a sentence-level fact-checked and annotated dataset to evaluate how Hyphen is capable of producing explanations as analogous evidence to the final prediction.Social media has become the fulcrum of all forms of communication. Classifying social texts such as fake news, rumour, sarcasm, etc. has gained significant attention. The surface-level signals expressed by a social-text itself may not be adequate for such tasks; therefore, recent methods attempted to incorporate other intrinsic signals such as user behavior and the underlying graph structure. Oftentimes, the `public wisdom' expressed through the comments/replies to a social-text acts as a surrog…
Organizátor
NeurIPS 2022
Account · 961 followers
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Locating and Editing Factual Associations in GPT
Watch later
Kevin Meng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Mixture Of Surprises for Unsupervised Reinforcement Learning
Watch later
Andrew Zhao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Infinite-Fidelity Coregionalization for Physical Simulation
Watch later
Shibo Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Best Combination for Efficient N:M Sparsity
Watch later
Yuxin Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SKFlow: Learning Optical Flow with Super Kernels
Watch later
Shangkun Sun, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Short-range forecasts of global precipitation using deep learning-augmented numerical weather prediction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%