no code implementations • 27 Apr 2023 • Solomon Ubani, Suleyman Olcay Polat, Rodney Nielsen
In this paper, we investigate the use of data obtained from prompting a large generative language model, ChatGPT, to generate synthetic training data with the aim of augmenting data in low resource scenarios.
no code implementations • WS 2019 • Brad Aiken, Jared Kelly, Alexis Palmer, Suleyman Olcay Polat, Taraka Rama, Rodney Nielsen
While our system results are dramatically below the average system submitted for the shared task evaluation campaign, our method is (we suspect) unique in its minimal reliance on labeled training data.
no code implementations • WS 2018 • Natalie Parde, Rodney Nielsen
The automatic generation of stimulating questions is crucial to the development of intelligent cognitive exercise applications.
no code implementations • WS 2018 • Natalie Parde, Rodney Nielsen
Detecting sarcasm in text is a particularly challenging problem in computational semantics, and its solution may vary across different types of text.
no code implementations • EMNLP 2017 • Natalie Parde, Rodney Nielsen
Crowdsourcing offers a convenient means of obtaining labeled data quickly and inexpensively.
no code implementations • COLING 2016 • Hamed Khanpour, Guntak, Nishitha la, Rodney Nielsen
In this study, we applied a deep LSTM structure to classify dialogue acts (DAs) in open-domain conversations.
Automatic Speech Recognition (ASR) Dialogue Act Classification +5
no code implementations • COLING 2016 • Andreea Godea, Florin Bulgarov, Rodney Nielsen
Truly effective and practical educational systems will only be achievable when they have the ability to fully recognize deep relationships between a learner{'}s interpretation of a subject and the desired conceptual understanding.