Papers by Pritom Saha Akash

9 papers
Coordinated Topic Modeling (2022.emnlp-main)

Copied to clipboard

Challenge: Rather than finding arbitrary topics, people often want to explore the text based on some welldefined topics.
Approach: They propose a problem called coordinated topic modeling that imitates human behavior while describing a text corpus.
Outcome: The proposed model is superior to baseline models on multiple domains.
MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for rewriting query terms struggle with natural language understanding . generative methods face high inference latency and cost in offline settings .
Approach: They propose a hybrid pipeline for rewriting query queries using offline knowledge distillation and online reinforcement learning.
Outcome: The proposed pipeline improves query relevance, diversity, adaptability and cost-effective evaluation without manual annotations on Amazon ESCI dataset.
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Extract-Refine-Retrieve-Read is a query optimization framework for large language models . it is designed to bridge the pre-retrieval information gap in Retriev-Augmented Generation systems .
Approach: They propose a framework to extract parametric knowledge from Large Language Models and refine them using a specialized query optimizer.
Outcome: The extract-refine-retrieve-read framework outperforms baselines on QA datasets . it is designed to meet the knowledge requirements of large language models (LLMs)
ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing iterative retrieval-augmented generation approaches struggle to delve deeply into each facet of complex queries.
Approach: They propose a framework that employs a tree-structured retrieval approach to enhance the depth and relevance of retrieved content.
Outcome: The proposed framework outperforms state-of-the-art models on multiple datasets and a newly introduced dataset.
Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing topic modeling models struggle in low-resource settings where data is limited . et al., 2003: domain adaptation for low-source topic modeling is challenging in low resources .
Approach: They propose a domain adaptation framework that disentangles domaininvariant and domain-specific components to improve topic adaptation.
Outcome: The proposed model outperforms state-of-the-art methods on low-resource datasets on diverse datasets.
Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing topic models often lack sufficient word co-occurrence in short texts, resulting in incoherent topics.
Approach: They propose to use large language models to extend short texts into more detailed sequences before applying topic modeling to solve semantic inconsistency problem.
Outcome: The proposed approach significantly outperforms current state-of-the-art topic models on real-world datasets with extreme data sparsity.
Unsupervised Open-domain Keyphrase Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing models that generate keyphrases without human-labeled data are lacking in this area.
Approach: They propose a model that consists of two modules that can be built in an unsupervised fashion and can perform consistently across domains.
Outcome: The proposed model performs consistently across domains and narrows the gap between supervised and unsupervised models down to about 16%.
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for keyphrase prediction rely on heuristicically defined importance scores . existing methods lack consideration for time efficiency .
Approach: They propose an unsupervised keyphrase generation model that combines informativeness and phraseness modules.
Outcome: The proposed model outperforms baseline models and achieves 89% of the performance of a supervised model for top 10 predictions.
Domain Representative Keywords Selection: A Probabilistic Approach (2022.findings-acl)

Copied to clipboard

Challenge: a probabilistic approach to select a subset of a target domain representative keywords is crucial for many downstream tasks in natural language processing.
Approach: They propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain.
Outcome: The proposed approach provides more importance to distinctive keywords than common keywords contrasting with the context domain.

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