4 papers
ArgFuse: A Weakly-Supervised Framework for Document-Level Event Argument Aggregation
Debanjana Kar, Sudeshna Sarkar, Pawan Goyal
Most of the existing information extraction frameworks (Wadden et al., 2019; Veysehet al., 2020) focus on sentence-level tasks and are hardly able to capture the consolidated infor…
Event Argument Extraction using Causal Knowledge Structures
Debanjana Kar, Sudeshna Sarkar, Pawan Goyal
Event Argument extraction refers to the task of extracting structured information from unstructured text for a particular event of interest. The existing works exhibit poor capabil…
No Rumours Please! A Multi-Indic-Lingual Approach for COVID Fake-Tweet Detection
Debanjana Kar, Mohit Bhardwaj, Suranjana Samanta +1
The sudden widespread menace created by the present global pandemic COVID-19 has had an unprecedented effect on our lives. Man-kind is going through humongous fear and dependence o…
Meta-Context Transformers for Domain-Specific Response Generation
Debanjana Kar, Suranjana Samanta, Amar Prakash Azad
Despite the tremendous success of neural dialogue models in recent years, it suffers a lack of relevance, diversity, and some times coherence in generated responses. Lately, transf…