Search Results for author:
Found 15 papers, 4 papers with code
Proto-Gen: An end-to-end neural generator for persona and knowledge grounded response generation
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.
UB Health Miners@SMM4H’22: Exploring Pre-processing Techniques To Classify Tweets Using Transformer Based Pipelines.
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).
Autobots Ensemble: Identifying and Extracting Adverse Drug Reaction from Tweets Using Transformer Based Pipelines
This paper details a system designed for Social Media Mining for Health Applications (SMM4H) Shared Task 2020.
Dialo-AP: A Dependency Parsing Based Argument Parser for Dialogues
While neural approaches to argument mining (AM) have advanced considerably, most of the recent work has been limited to parsing monologues.
Stylistic Response Generation by Controlling Personality Traits and Intent
Personality traits influence human actions and thoughts, which is manifested in day to day conversations.
Let’s Chat: Understanding User Expectations in Socialbot Interactions
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.
EDU-AP: Elementary Discourse Unit based Argument Parser
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.
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
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.
Improving Dialog Safety using Socially Aware Contrastive Learning
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.
Diving Deep into Modes of Fact Hallucinations in Dialogue Systems
Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination.
Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection
Ablation studies on the Persona-Chat dataset show that incorporating emotion and entailment improves the accuracy of response selection.
Proto: A Neural Cocktail for Generating Appealing Conversations
In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: Proto.
Medical Literature Mining and Retrieval in a Conversational Setting
The Covid-19 pandemic has caused a spur in the medical research literature.
Similarity Based Label Smoothing For Dialogue Generation
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits.
A multi-agent evolutionary robotics framework to train spiking neural networks
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.
