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.
Source: Real-time On-Demand Crowd-powered Entity Extraction
Image credit: Robust Retrieval Augmented Generation for Zero-shot Slot Filling
Papers
Showing 1–10 of 458 papers
All datasetsKILT: Zero Shot REKILT: T-RExMixSNIPSMixATISATISSNIPSSLURPMASSIVEATIS (vi)CAISDialogue State Tracking ChallengeMULTIWOZ 2.2
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CTRAN | F1 | 0.98 | — | Unverified |
| 2 | Bi-model with a decoder | F1 | 0.97 | — | Unverified |
| 3 | Stack-Propagation (+BERT) | F1 | 0.96 | — | Unverified |
| 4 | JointBERT-CAE | F1 | 0.96 | — | Unverified |
| 5 | Joint BERT | F1 | 0.96 | — | Unverified |
| 6 | AGIF | F1 | 0.96 | — | Unverified |
| 7 | Joint BERT + CRF | F1 | 0.96 | — | Unverified |
| 8 | Attention Encoder-Decoder NN | F1 | 0.96 | — | Unverified |
| 9 | SF-ID | F1 | 0.96 | — | Unverified |
| 10 | Context Encoder | F1 | 0.96 | — | Unverified |