Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 74Machine Learning
- 70Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 22Natural Language Processing
- 22Reinforcement learning
-
Spring 2020
In this thesis, we focus on finding efficient practical random sampling methods for time-changing discrete distributions. We empirically study ten methods including existing algorithms, and two new ones: three level search and the flat method. We review the core ideas of existing methods...
-
An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing
DownloadSpring 2022
Research in unsupervised text generation has been gaining attention over the years. One recent approach is local search towards a heuristically defined objective, which specifies language fluency, semantic meanings, and other task-specific attributes. Search in the sentence space is realized by...
-
Spring 2013
The game of Amazons is a young board game with simple rules, nice mathematical properties yet a high complexity between chess and Go. The state of the art Amazons solver was presented by Martin Müller in 2001 with which he solved the Amazons 5 × 5 starting position as a first player win. This...
-
Fall 2022
Building intelligent open-domain dialogue systems is a long-standing goal of artificial intelligence. These systems, also known as chatbots, aim to hold conversations with humans in an open-ended fashion. However, it is well known that standard encoder-decoder dialogue systems tend to generate...
-
An Exploration of Dialog Act Classification in Open-domain Conversational Agents and the Applicability of Text Data Augmentation
DownloadFall 2023
Recognizing dialog acts of users is an essential component in building successful conversational agents. In this work, we propose a dialog act (DA) classifier for two of our open domain conversational agents. For this, we curated a high-quality, multi-domain dataset with ∼24k user utterances...