Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations
This work addresses slot-filling in conversational AI for domains like restaurant booking, offering an incremental improvement with a new dataset.
The paper tackles dialog slot-filling by framing it as a turn-based span extraction task, introducing Span-ConveRT, which leverages pretrained conversational models to achieve consistent gains in few-shot learning scenarios over baseline methods.
We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained conversational models such as ConveRT (Henderson et al., 2019). We show that leveraging such knowledge in Span-ConveRT is especially useful for few-shot learning scenarios: we report consistent gains over 1) a span extractor that trains representations from scratch in the target domain, and 2) a BERT-based span extractor. In order to inspire more work on span extraction for the slot-filling task, we also release RESTAURANTS-8K, a new challenging data set of 8,198 utterances, compiled from actual conversations in the restaurant booking domain.