Search Results for author:
Found 6 papers, 1 papers with code
R3 : Refined Retriever-Reader pipeline for Multidoc2dial
In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset.
PEFTDebias : Capturing debiasing information using PEFTs
The increasing use of foundation models highlights the urgent need to address and eliminate implicit biases present in them that arise during pretraining.
Few-shot Unified Question Answering: Tuning Models or Prompts?
Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks.
Debiasing Multilingual Word Embeddings: A Case Study of Three Indian Languages
In this paper, we advance the current state-of-the-art method for debiasing monolingual word embeddings so as to generalize well in a multilingual setting.
Code-switching patterns can be an effective route to improve performance of downstream NLP applications: A case study of humour, sarcasm and hate speech detection
In this paper we demonstrate how code-switching patterns can be utilised to improve various downstream NLP applications.
A deep-learning framework to detect sarcasm targets
In this paper we propose a deep learning framework for sarcasm target detection in predefined sarcastic texts.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
