Papers by Aniket Pramanick

5 papers
A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why? (2023.emnlp-main)

Copied to clipboard

Challenge: a systematic framework to analyze the evolution of research topics in a scientific field is crucial for keeping abreast of its continuous advancement.
Approach: They propose a framework for analyzing the evolution of research topics in a scientific field using causal discovery and inference techniques.
Outcome: The proposed framework uncovers evolutionary trends and causes for a wide range of NLP topics.
The Nature of NLP: Analyzing Contributions in NLP Papers (2025.acl-long)

Copied to clipboard

Challenge: despite this, what constitutes NLP research remains debated .
Approach: They propose a taxonomy of research contributions and introduce a task of automatically identifying contribution statements and classifying their types from NLP research papers.
Outcome: The proposed model analyzes 29k NLP research papers to understand their contributions .
The challenges of temporal alignment on Twitter during crises (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing models consider data spanning years to decades, but shorter time spans are critical for crisis data.
Approach: They propose to use domain adaptation techniques to cope with performance degradation by leveraging domain adaptation.
Outcome: The proposed models outperform baseline models under conditions of natural and human-induced disasters while highlighting the limitations of current models.
Joint Learning of Representations for Web-tables, Entities and Types using Graph Convolutional Network (2021.eacl-main)

Copied to clipboard

Challenge: Existing approaches for table annotation with entities and types capture the syntactic structure of tables using graphical models or learn embeddings of table entries without accounting for the complete syntaktic structure.
Approach: They propose a Graph Convolutional Network that captures the complete structure of tables, knowledge graph and the training annotations and jointly learns embeddings for table elements as well as the entities and types.
Outcome: The proposed model significantly outperforms state-of-the-art methods on 5 benchmark datasets while showing promising performance on downstream table-related applications.

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