all AI news
Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-turn Spoken Language Understanding. (arXiv:2206.12209v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
Spoken Language Understanding (SLU), a core component of the task-oriented
dialogue system, expects a shorter inference facing the impatience of human
users. Existing work increases inference speed by designing non-autoregressive
models for single-turn SLU tasks but fails to apply to multi-turn SLU in
confronting the dialogue history. The intuitive idea is to concatenate all
historical utterances and utilize the non-autoregressive models directly.
However, this approach seriously misses the salient historical information and
suffers from the uncoordinated-slot problems. To overcome those …
arxiv autoregressive model information language spoken language understanding understanding