Micro F1: 87.3
Papers with Code · CC BY-SA 4.0
Slot Filling
The goal of Slot Filling is to identify from a running dialog different slots, which correspond to different parameters of the user’s query. For instance, when a user queries for nearby restaurants, key slots for location and preferred food are required for a dialog system to retrieve the appropriate information. Thus, the main challenge in the slot-filling task is to extract the target entity.
<span class="description-source">Source: Real-time On-Demand Crowd-powered Entity Extraction </span>
Image credit: Robust Retrieval Augmented Generation for Zero-shot Slot Filling
논문
Slot F1 Score: 83.6
F1: 0.395
Micro F1: 88.5
F1: 0.753
Micro F1: 89.4
Micro F1: 88.0
Slot F1: 95.5
F1: 86.16
Micro F1: 89.8
FITB: 96.9
F1 (1-shot) avg: 74.89F1 (5-shot) avg: 84.54
F1: 0.8061
Micro F1: 88.5
Micro F1: 88.7
Micro F1: 88.3
Micro F1: 89.2
Micro F1: 89.4
F1 score: 98.56
Micro F1: 90.5
Micro F1: 88.5
F1: 0.642
F1: 0.8327
Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction
Micro F1: 88.3