Search Results for author: Debanjana Kar

Found 5 papers, 3 papers with code

ArgFuse: A Weakly-Supervised Framework for Document-Level Event Argument Aggregation

1 code implementation21 Jun 2021 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 information from a given document.

Active Learning Document-level

Event Argument Extraction using Causal Knowledge Structures

no code implementations2 May 2021 Debanjana Kar, Sudeshna Sarkar, Pawan Goyal

We develop a causal network for our event-annotated dataset by extracting relevant event causal structures from ConceptNet and phrases from Wikipedia.

Document-level

No Rumours Please! A Multi-Indic-Lingual Approach for COVID Fake-Tweet Detection

1 code implementation14 Oct 2020 Debanjana Kar, Mohit Bhardwaj, Suranjana Samanta, Amar Prakash Azad

Towards this, we propose an approach to detect fake news about COVID-19 early on from social media, such as tweets, for multiple Indic-Languages besides English.

Fake News Detection Misinformation +2

Meta-Context Transformers for Domain-Specific Response Generation

1 code implementation12 Oct 2020 Debanjana Kar, Suranjana Samanta, Amar Prakash Azad

Though these models have exhibited excellent language coherence, they often lack relevance and terms when used for domain-specific response generation.

Dialogue Generation Language Modelling +2

Designing a Frame-Semantic Machine Translation Evaluation Metric

no code implementations RANLP 2019 Oliver Czulo, Tiago Timponi Torrent, Ely Edison da Silva Matos, Alex Costa, re Diniz da, Debanjana Kar

We propose a metric for machine translation evaluation based on frame semantics which does not require the use of reference translations or human corrections, but is aimed at comparing original and translated output directly.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.