1 code implementation • NLP4ConvAI (ACL) 2022 • Sougata Saha, Souvik Das, Rohini Srihari
Personality traits influence human actions and thoughts, which is manifested in day to day conversations.
no code implementations • CCGPK (COLING) 2022 • Sougata Saha, Souvik Das, Rohini Srihari
In this paper we detail the implementation of Proto-Gen, an end-to-end neural response generator capable of selecting appropriate persona and fact sentences from available options, and generating persona and fact grounded responses.
no code implementations • SMM4H (COLING) 2022 • Roshan Khatri, Sougata Saha, Souvik Das, Rohini Srihari
Here we discuss our implementation of two tasks in the Social Media Mining for Health Applications (SMM4H) 2022 shared tasks – classification, detection, and normalization of Adverse Events (AE) mentioned in English tweets (Task 1) and classification of English tweets self-reporting exact age (Task 4).
1 code implementation • COLING 2022 • Sougata Saha, Souvik Das, Rohini K. Srihari
While neural approaches to argument mining (AM) have advanced considerably, most of the recent work has been limited to parsing monologues.
1 code implementation • SIGDIAL (ACL) 2022 • Sougata Saha, Souvik Das, Rohini Srihari
Neural approaches to end-to-end argument mining (AM) are often formulated as dependency parsing (DP), which relies on token-level sequence labeling and intricate post-processing for extracting argumentative structures from text.
no code implementations • SMM4H (COLING) 2020 • Sougata Saha, Souvik Das, Prashi Khurana, Rohini Srihari
This paper details a system designed for Social Media Mining for Health Applications (SMM4H) Shared Task 2020.
no code implementations • NAACL (HCINLP) 2022 • Elizabeth Soper, Erin Pacquetet, Sougata Saha, Souvik Das, Rohini Srihari
This paper analyzes data from the 2021 Amazon Alexa Prize Socialbot Grand Challenge 4, in order to better understand the differences between human-computer interactions (HCI) in a socialbot setting and conventional human-to-human interactions.
no code implementations • 7 May 2024 • Sayantan Pal, Souvik Das, Rohini K. Srihari
This study introduces 'clickbait spoiling', a novel technique designed to detect, categorize, and generate spoilers as succinct text responses, countering the curiosity induced by clickbait content.
no code implementations • 14 Apr 2024 • Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi, Baolin Peng, Dong Yu
Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure.
no code implementations • 1 Feb 2024 • Souvik Das, Rohini K. Srihari
To understand the extent of this problem, we study prosociality in both adversarial and casual dialog contexts and audit the response quality of general-purpose language models in terms of propensity to produce unsafe content.
1 code implementation • 11 Jan 2023 • Souvik Das, Sougata Saha, Rohini K. Srihari
Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination.
no code implementations • COLING 2022 • Souvik Das, Sougata Saha, Rohini K. Srihari
Ablation studies on the Persona-Chat dataset show that incorporating emotion and entailment improves the accuracy of response selection.
no code implementations • 6 Sep 2021 • Sougata Saha, Souvik Das, Elizabeth Soper, Erin Pacquetet, Rohini K. Srihari
In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: Proto.
no code implementations • 23 Jul 2021 • Sougata Saha, Souvik Das, Rohini Srihari
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits.
no code implementations • 23 Jul 2021 • Souvik Das, Sougata Saha, Rohini K. Srihari
The Covid-19 pandemic has caused a spur in the medical research literature.
no code implementations • 7 Dec 2020 • Souvik Das, Anirudh Shankar, Vaneet Aggarwal
Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment.