Skip to Main content Skip to Navigation
New interface
Conference papers

Weak supervision for Question Type Detection with large language models

Abstract : Large pre-trained language models (LLM) have shown remarkable Zero-Shot Learning performances in many Natural Language Processing tasks. However, designing effective prompts is still very difficult for some tasks, in particular for dialogue act recognition. We propose an alternative way to leverage pretrained LLM for such tasks that replace manual prompts with simple rules, which are more intuitive and easier to design for some tasks. We demonstrate this approach on the question type recognition task, and show that our zero-shot model obtains competitive performances both with a supervised LSTM trained on the full training corpus, and another supervised model from previously published works on the MRDA corpus. We further analyze the limits of the proposed approach, which can not be applied on any task, but may advantageously complement prompt programming for specific classes.
Document type :
Conference papers
Complete list of metadata
Contributor : Christophe Cerisara Connect in order to contact the contributor
Submitted on : Friday, September 23, 2022 - 3:11:23 PM
Last modification on : Saturday, September 24, 2022 - 3:37:55 AM


Files produced by the author(s)


  • HAL Id : hal-03786135, version 1



Jiří Martínek, Christophe Cerisara, Pavel Král, Ladislav Lenc, Josef Baloun. Weak supervision for Question Type Detection with large language models. INTERSPEECH 2022 -, Sep 2022, Incheon, South Korea. ⟨hal-03786135⟩



Record views


Files downloads