Papers by Debarshi Kumar Sanyal
Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling (2023.eacl-main)
Copied to clipboard
| Challenge: | Dropout is a regularization trick used to resolve overfitting in large feedforward neural networks, but there is nil analysis of it for unsupervised models and in particular, VAE-based neural topic models. |
| Approach: | They propose to use dropout to solve overfitting problems in unsupervised neural topic models by stochastically dropping out the activation of neurons to prevent complex co-adaptations of feature vectors. |
| Outcome: | The proposed class of neural topic models can be used to improve the quality and predictive performance of the generated topics. |
S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Variational autoencoder-based neural topic models lack posterior collapse in high-dimensional text data. |
| Approach: | They propose a Spherical Sliced Wasserstein Autoencoder for Topic Modeling to model latent representations in a hyperspherical space. |
| Outcome: | The proposed model outperforms state-of-the-art topic models while improving performance on downstream tasks. |
Few-TK: A Dataset for Few-shot Scientific Typed Keyphrase Recognition (2024.findings-naacl)
Copied to clipboard
| Challenge: | Named Entities are a common form of Information Extraction (IE) tasks for scientific texts. |
| Approach: | They propose a rechristening of Named Entities as Typed Keyphrases (TK) they advocate for exploring this task in the few-shot domain due to the scarcity of labeled scientific IE data. |
| Outcome: | The proposed dataset includes scientific Typed Keyphrase annotations on abstracts of 500 research papers. |
TaxoAlign: Scholarly Taxonomy Generation Using Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for taxonomy generation do not compare structure of generated surveys with those written by human experts. |
| Approach: | They propose a method that bridges the gap between human-generated and automatically-created taxonomies. |
| Outcome: | The proposed method surpasses baselines on CS-TaxoBench on nearly all metrics. |
Can Small Vision–Language Models Perform Sign Language Translation? (2026.findings-acl)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) have shown strong generalization across multimodal tasks, but their capacity to handle sign language translation (SLT) remains unclear. |
| Approach: | They propose entity- and semantics-aware metrics tailored for SLT to evaluate their performance. |
| Outcome: | The proposed metrics highlight the limitations of general-purpose VLMs to SLT, unlike their applicability in other tasks. |