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.
@article{arxiv.2005.08866,
title = {Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations},
author = {Sam Coope and Tyler Farghly and Daniela Gerz and Ivan Vulić and Matthew Henderson},
journal= {arXiv preprint arXiv:2005.08866},
year = {2020}
}