D
Debjit Paul
Researcher at Heidelberg University
Publications - 17
Citations - 137
Debjit Paul is an academic researcher from Heidelberg University. The author has contributed to research in topics: Abductive reasoning & Computer science. The author has an hindex of 5, co-authored 14 publications receiving 91 citations.
Papers
More filters
Posted Content
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
Debjit Paul,Anette Frank +1 more
TL;DR: A novel method to extract, rank, filter and select multi-hop relation paths from a commonsense knowledge resource to interpret the expression of sentiment in terms of their underlying human needs is presented.
Proceedings ArticleDOI
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
Debjit Paul,Anette Frank +1 more
TL;DR: The authors proposed a method to extract, rank, filter and select multi-hop relation paths from a commonsense knowledge resource to interpret the expression of sentiment in terms of their underlying human needs.
Proceedings ArticleDOI
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
TL;DR: Clean and Noisy Label Neural Networks as discussed by the authors combine self-training with noise handling on the self-labeled data to train on clean and noisy data separately by explicitly modeling clean and noise labels separately.
Proceedings ArticleDOI
Argumentative Relation Classification with Background Knowledge.
TL;DR: This paper proposes an unsupervised graph-based ranking method that extracts relevant multi-hop knowledge from a background knowledge resource and is integrated into a neural argumentative relation classifier via an attention-based gating mechanism.
Journal ArticleDOI
REFINER: Reasoning Feedback on Intermediate Representations
Debjit Paul,Mete Ismayilzada,Maxime Peyrard,Beatriz Borges,Antoine Bosselut,Robert West,Boi Faltings +6 more
TL;DR: This paper proposed a framework for finetuning LMs to explicitly generate intermediate reasoning steps while interacting with a critic model that provides automated feedback on the reasoning, where the critic provides structured feedback that the reasoning LM uses to iteratively improve its intermediate arguments.