Papers by Ritesh Soun

4 papers
CIAug: Equipping Interpolative Augmentation with Curriculum Learning (2022.naacl-main)

Copied to clipboard

Challenge: Current methods for interpolative data augmentation select samples at random, which might make it difficult for the model to generalize better and converge faster.
Approach: They propose a curriculum-based learning method that leverages the relative position of samples in hyperbolic embedding space as a complexity measure to gradually mix up increasingly difficult and diverse samples along training.
Outcome: The proposed method achieves state-of-the-art results over existing methods on 10 benchmark datasets across 4 languages in text classification and named-entity recognition tasks.
HYPHEN: Hyperbolic Hawkes Attention For Text Streams (2022.acl-short)

Copied to clipboard

Challenge: Existing methods for text stream modeling ignore fine-grained timing irregularities and time-varying scale-free properties of texts.
Approach: They propose a hyperbolic Hawkes Attention Network which learns a data-driven hyperbolical space and models irregular powerlaw excitations using a Hawke's process.
Outcome: The proposed model can model online text sequences in a geometry agnostic manner.
Tweet Based Reach Aware Temporal Attention Network for NFT Valuation (2022.findings-emnlp)

Copied to clipboard

Challenge: Non-Fungible Tokens (NFTs) are a relatively unexplored class of assets due to their extremely volatile nature.
Approach: They propose a reach-aware temporal learning approach to predict future NFT trends from a dataset consisting of over 1.3 million tweets and 180 thousand NFT transactions .
Outcome: The proposed model outperforms state-of-the-art models by an average of 36% on a dataset consisting of over 1.3 million tweets and 180 thousand NFT transactions spanning over 15 NFT collections.
DMix: Adaptive Distance-aware Interpolative Mixup (2022.acl-short)

Copied to clipboard

Challenge: Interpolation-based regularisation methods such as Mixup have shown to be effective for various tasks and modalities.
Approach: They propose an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space.
Outcome: The proposed method achieves state-of-the-art on sentence classification over existing methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations