ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation
This work addresses intent detection for spoken queries, an incremental improvement in a domain-specific task.
The authors tackled the problem of intent detection for noisy, short spoken queries by semantically expanding them using a conditioned GPT-2 model, which improved detection performance as shown in experiments.
Intent detection of spoken queries is a challenging task due to their noisy structure and short length. To provide additional information regarding the query and enhance the performance of intent detection, we propose a method for semantic expansion of spoken queries, called ConQX, which utilizes the text generation ability of an auto-regressive language model, GPT-2. To avoid off-topic text generation, we condition the input query to a structured context with prompt mining. We then apply zero-shot, one-shot, and few-shot learning. We lastly use the expanded queries to fine-tune BERT and RoBERTa for intent detection. The experimental results show that the performance of intent detection can be improved by our semantic expansion method.