Papers by Pankaj Gupta

9 papers
Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time (N18-1)

Copied to clipboard

Challenge: a novel topic model is proposed to allow topical trends to be captured in temporal collections of documents.
Approach: They propose a novel unsupervised neural dynamic topic model where topics are influenced by topic discovery over time.
Outcome: The proposed model shows better generalization, topic interpretation, evolution and trends compared to state-of-the-art models .
Multi-source Neural Topic Modeling in Multi-view Embedding Spaces (2021.naacl-main)

Copied to clipboard

Challenge: Recent work has used pre-trained word embeddings to address data sparsity in short-text or small document collections.
Approach: They propose a neural topic modeling framework using multi-view embedding spaces to improve topic quality and deal with polysemy.
Outcome: The proposed framework improves topic quality and deal with polysemy.
Joint Bootstrapping Machines for High Confidence Relation Extraction (N18-1)

Copied to clipboard

Challenge: Existing semi-supervised bootstrapping methods for relationship extraction lack labeled data.
Approach: They propose a semi-supervised bootstrapping method that protects against semantic drift . they expand entities and templates in parallel and in mutually constraining fashion in each iteration .
Outcome: Experimental results show that BREX improves on state-of-the-art methods for four relationships.
Linguistically Informed Relation Extraction and Neural Architectures for Nested Named Entity Recognition in BioNLP-OST 2019 (D19-57)

Copied to clipboard

Challenge: Named Entity Recognition (NER) and Relation Extraction (RE) are essential tools in distilling knowledge from biomedical literature.
Approach: They propose to use Named Entities to perform nested entities extraction, Entity Normalization and Relation Extraction to generalize the approach to different languages.
Outcome: The proposed approach can be generalized to different languages and showed it’s effectiveness for English and Spanish text.
BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions (D19-57)

Copied to clipboard

Challenge: Our best systems achieved 1st rank and scored 0.86 mAP and 0.58 macro average accuracy in Task-1 and Task-2 respectively.
Approach: They propose to use attention-based supervised neural topic model and SVM for retrieval and ranking of PubMed abstracts and to use BM25 and other relevance measures for re-ranking.
Outcome: The proposed system scored 0.86 mAP and 0.58 macro average accuracy in the RDoC Tasks of BioNLP-OST 2019 .
TopicBERT for Energy Efficient Document Classification (2020.findings-emnlp)

Copied to clipboard

Challenge: Prior work has noted that BERT’s computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions.
Approach: They propose to combine topic and language models to optimize the computational cost of fine-tuning for document classification by complementary learning.
Outcome: The proposed model achieves a 1.4x speedup with 40% reduction in CO2 emission while retaining 99.9% performance over 5 datasets.
SEPSIS: I Can Catch Your Lies – A New Paradigm for Deception Detection (2025.acl-srw)

Copied to clipboard

Challenge: a new framework categorizes deception into three forms: lies of omission, lies of commission, and lies of influence . a novel framework for deception detection leveraging NLP techniques is proposed .
Approach: They propose a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence.
Outcome: The proposed framework achieves an impressive F1 score of 0.87 across all layers . it can be used to investigate lies of omission, lies of commission and lies of influence .
Federated Continual Learning for Text Classification via Selective Inter-client Transfer (2022.findings-emnlp)

Copied to clipboard

Challenge: Continual Learning (CL) is a privacy-preserving machine learning technique that enables collaborative training of ML models by sharing model parameters across distributed clients.
Approach: They propose a framework which selectively combines model parameters of foreign clients to maximize knowledge transfer while preserving privacy.
Outcome: The proposed framework improves the performance of a text classification task using five datasets from diverse domains while preserving privacy.
Neural Architectures for Fine-Grained Propaganda Detection in News (D19-50)

Copied to clipboard

Challenge: MIC-CIS is a fine grained propaganda detection system . previous work focused on document level, labeling articles as propaganda .
Approach: They propose to use different neural architectures to jointly perform propaganda detection tasks . they also investigate different ensemble schemes such as majority-voting, relax-vote, etc.
Outcome: The proposed system performs sentences and fragment level propaganda detection tasks.

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