Papers by Niharika Niharika

4 papers
Deep Learning Based Named Entity Recognition Models for Recipes (2024.lrec-main)

Copied to clipboard

Challenge: Named entity recognition is a technique for extracting information from unstructured data with known labels.
Approach: They use named entity recognition to annotate ingredients from recipe data . they use a clustering-based approach to annnotate 88,526 phrases .
Outcome: The proposed method improves on a dataset of 88,526 phrases from RecipeDB . the fine-tuned spaCy-transformer performs better than the previous methods .
Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods for deepfake detection suffer from two limitations: modality fragmentation and shallow inter-modal reasoning.
Approach: They propose a framework for multimodal deepfake detection that uses contrastive learning and large language models to mitigate modality fragmentation and refine embeddings to address shallow inter-modal reasoning.
Outcome: ConLLM reduces audio deepfake EER by 50%, improves video accuracy by 8%, and achieves approximately 9% accuracy gains in audio-visual tasks.
JobXMLC: EXtreme Multi-Label Classification of Job Skills with Graph Neural Networks (2023.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to predict missing skills are limited to contextual modelling and do not exploit inter-relational structures like job-job and job-skill relationships.
Approach: They propose a skill prediction framework that exploits structural relationships to predict missing skills using job descriptions.
Outcome: The proposed framework outperforms the state-of-the-art approaches by 6% in precision and 3% in recall on real-world recruitment datasets.
DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting (2026.acl-industry)

Copied to clipboard

Challenge: Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together.
Approach: They propose to use document packet splitting to improve document understanding in real-world applications.
Outcome: The proposed datasets and evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains.

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