Search Results for author: Mei Si

Found 11 papers, 5 papers with code

Enhancing Sentiment Analysis Results through Outlier Detection Optimization

no code implementations25 Nov 2023 Yuetian Chen, Mei Si

By employing both a small-sized language model (DistilBERT base model with 66 million parameters) and non-deep learning machine learning algorithms (decision tree, KNN, Logistic Regression, and LDA) as the classifier, our findings suggest that the removal of outliers can lead to enhanced results in most cases.

Language Modelling Large Language Model +3

Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework

1 code implementation16 Nov 2023 Matthew Pisano, Peter Ly, Abraham Sanders, Bingsheng Yao, Dakuo Wang, Tomek Strzalkowski, Mei Si

To help mitigate this issue, we introduce Bergeron: a framework designed to improve the robustness of LLMs against attacks without any additional parameter fine-tuning.

Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation

1 code implementation22 Jun 2023 Yuetian Chen, Bowen Shi, Mei Si

Artificial intelligence has made significant progress in natural language processing, with models like GPT-3 demonstrating impressive capabilities.

Visual Story Generation Based on Emotion and Keywords

1 code implementation7 Jan 2023 Yuetian Chen, Ruohua Li, Bowen Shi, Peiru Liu, Mei Si

Automated visual story generation aims to produce stories with corresponding illustrations that exhibit coherence, progression, and adherence to characters' emotional development.

Image Generation Object Recognition +2

A Review of Uncertainty for Deep Reinforcement Learning

no code implementations18 Aug 2022 Owen Lockwood, Mei Si

While there has been substantial effort and progress in understanding and working with uncertainty for supervised learning, the body of literature for uncertainty aware deep reinforcement learning is less developed.

reinforcement-learning Reinforcement Learning (RL)

Towards a Progression-Aware Autonomous Dialogue Agent

no code implementations NAACL 2022 Abraham Sanders, Tomek Strzalkowski, Mei Si, Albert Chang, Deepanshu Dey, Jonas Braasch, Dakuo Wang

Recent advances in large-scale language modeling and generation have enabled the creation of dialogue agents that exhibit human-like responses in a wide range of conversational scenarios spanning a diverse set of tasks, from general chit-chat to focused goal-oriented discourse.

Language Modelling

A System for Image Understanding using Sensemaking and Narrative

no code implementations21 Jan 2022 Zev Battad, Mei Si

Sensemaking and narrative are two inherently interconnected concepts about how people understand the world around them.

Visual Storytelling

Reinforcement Learning with Quantum Variational Circuits

2 code implementations15 Aug 2020 Owen Lockwood, Mei Si

This work explores the potential for quantum computing to facilitate reinforcement learning problems.

BIG-bench Machine Learning OpenAI Gym +3

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