Search Results for author: Rohini K. Srihari

Found 8 papers, 3 papers with code

Dialo-AP: A Dependency Parsing Based Argument Parser for Dialogues

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.

Argument Mining Dependency Parsing

Improving Dialog Safety using Socially Aware Contrastive Learning

no code implementations1 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.

Contrastive Learning

Domain Specific Question Answering Over Knowledge Graphs Using Logical Programming and Large Language Models

1 code implementation3 Mar 2023 Navid Madani, Rohini K. Srihari, Kenneth Joseph

Overall, our work presents a promising approach to addressing question answering over domain-specific graphs, offering an explainable and robust solution by incorporating logical programming languages.

Knowledge Graphs Logical Reasoning +1

Diving Deep into Modes of Fact Hallucinations in Dialogue Systems

1 code implementation11 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.

Hallucination

Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection

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.

Assessing Effectiveness of Using Internal Signals for Check-Worthy Claim Identification in Unlabeled Data for Automated Fact-Checking

no code implementations2 Nov 2021 Archita Pathak, Rohini K. Srihari

While recent work on automated fact-checking has focused mainly on verifying and explaining claims, for which the list of claims is readily available, identifying check-worthy claim sentences from a text remains challenging.

Fact Checking Retrieval +3

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