no code implementations • LREC 2022 • Bingsheng Yao, Ethan Joseph, Julian Lioanag, Mei Si
The SOTA models can achieve over 90% accuracy on predicting the last sentence.
no code implementations • 25 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.
1 code implementation • 16 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.
1 code implementation • 22 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.
1 code implementation • 7 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.
no code implementations • 18 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.
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.
no code implementations • 21 Jan 2022 • Zev Battad, Mei Si
Sensemaking and narrative are two inherently interconnected concepts about how people understand the world around them.
2 code implementations • 15 Aug 2020 • Owen Lockwood, Mei Si
This work explores the potential for quantum computing to facilitate reinforcement learning problems.
1 code implementation • 1st Proceedings of Alexa Prize (Alexa Prize 2017) 2017 • Jieming Ji, Qingyun Wang, Zev Battad, Jiashun Gou, Jingfei Zhou, Rahul Divekar, Craig Carlson, Mei Si
We experimented with a range of conversational activities, such as providing news and playing games, and strategies for controlling the dialogue flow.
no code implementations • NAACL 2016 • Di Lu, Clare Voss, Fangbo Tao, Xiang Ren, Rachel Guan, Rostyslav Korolov, Tongtao Zhang, Dongang Wang, Hongzhi Li, Taylor Cassidy, Heng Ji, Shih-Fu Chang, Jiawei Han, William Wallace, James Hendler, Mei Si, Lance Kaplan