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 | Re2G | KILT-AC | 75.84 | — | Unverified |
| 2 | KGI_1 | KILT-AC | 69.14 | — | Unverified |
| 3 | Wikipedia | KILT-AC | 64.64 | — | Unverified |
| 4 | MetaRAG | KILT-AC | 61.88 | — | Unverified |
| 5 | single ngram | KILT-AC | 60.08 | — | Unverified |
| 6 | KGI_0 (reupload) | KILT-AC | 55.54 | — | Unverified |
| 7 | Coop. DistilBert | KILT-AC | 36.68 | — | Unverified |
| 8 | DensePhrases | KILT-AC | 27.84 | — | Unverified |
| 9 | 10k | KILT-AC | 27.84 | — | Unverified |
| 10 | RAG | KILT-AC | 23.12 | — | Unverified |