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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 61–70 of 458 papers

Title	Date	Tasks	Status	Hype
BERT for Joint Intent Classification and Slot Filling	Feb 28, 2019	General Classificationintent-classification	CodeCode Available	1
Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP	Jun 12, 2021	Entity DisambiguationEntity Retrieval	CodeCode Available	1
A weakly supervised sequence tagging and grammar induction approach to semantic frame slot filling	Jun 15, 2019	slot-fillingSlot Filling	—Unverified	0
Automatic Intent-Slot Induction for Dialogue Systems	Mar 16, 2021	Intent Detectionslot-filling	—Unverified	0
An Empirical Study of Automatic Chinese Word Segmentation for Spoken Language Understanding and Named Entity Recognition	Jun 1, 2016	Automatic Speech Recognition (ASR)Chinese Word Segmentation	—Unverified	0
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs	Dec 1, 2020	Graph GenerationMiscellaneous	—Unverified	0
An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistants	Jun 13, 2024	Dialogue State TrackingLanguage Modelling	—Unverified	0
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding	Nov 4, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?	Dec 20, 2022	Language ModelingLanguage Modelling	—Unverified	0
Augmenting Task-Oriented Dialogue Systems with Relation Extraction	Oct 24, 2022	intent-classificationIntent Classification	—Unverified	0

Show:10 25 50

← PrevPage 7 of 46Next →

All datasets KILT: Zero Shot RE KILT: T-REx MixSNIPS MixATIS ATIS SNIPS SLURP MASSIVE ATIS (vi)CAIS Dialogue State Tracking Challenge MULTIWOZ 2.2

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	single ngram	KILT-AC	73.2	—	Unverified
2	KGI_1	KILT-AC	72.31	—	Unverified
3	MetaRAG	KILT-AC	71.1	—	Unverified
4	KGI_0 (reupload)	KILT-AC	68.32	—	Unverified
5	Wikipedia	KILT-AC	67.2	—	Unverified
6	Multitask DPR + BART	KILT-AC	50.64	—	Unverified
7	10k	KILT-AC	41.34	—	Unverified
8	DensePhrases	KILT-AC	41.34	—	Unverified
9	RAG	KILT-AC	36.83	—	Unverified
10	Coop. Distil Bert	KILT-AC	34.13	—	Unverified

#	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

#	Model	Metric	Claimed	Verified	Status
1	BiSLU	Micro F1	97.2	—	Unverified
2	SLIM (PACL)	Micro F1	96.8	—	Unverified
3	SLIM	Micro F1	96.5	—	Unverified
4	Uni-MIS	Micro F1	96.4	—	Unverified
5	TFMN	Micro F1	96.4	—	Unverified
6	TFMN (PACL)	Micro F1	96.3	—	Unverified
7	RoBERTa (PACL)	Micro F1	96.2	—	Unverified
8	DGIF	Micro F1	95.9	—	Unverified
9	SSRAN	Micro F1	95.8	—	Unverified
10	MISCA	Micro F1	95.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MISCA	Micro F1	90.5	—	Unverified
2	Co-guiding Net	Micro F1	89.8	—	Unverified
3	SSRAN	Micro F1	89.4	—	Unverified
4	BiSLU	Micro F1	89.4	—	Unverified
5	UGEN	Micro F1	89.2	—	Unverified
6	Topic Information	Micro F1	88.7	—	Unverified
7	SLIM	Micro F1	88.5	—	Unverified
8	Global Intent-Slot Co-occurence	Micro F1	88.5	—	Unverified
9	DGIF	Micro F1	88.5	—	Unverified
10	Uni-MIS	Micro F1	88.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CTRAN	F1	0.98	—	Unverified
2	Bi-model with a decoder	F1	0.97	—	Unverified
3	Joint BERT	F1	0.96	—	Unverified
4	Stack-Propagation (+BERT)	F1	0.96	—	Unverified
5	JointBERT-CAE	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	Context Encoder	F1	0.96	—	Unverified
10	SF-ID	F1	0.96	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CTRAN	F1	98.3	—	Unverified
2	Stack-Propagation (+BERT)	F1	97	—	Unverified
3	JointBERT-CAE	F1	97	—	Unverified
4	AGIF	F1	94.8	—	Unverified
5	Stack-Propagation	F1	94.2	—	Unverified
6	Context Encoder	F1	93.6	—	Unverified
7	SF-ID	F1	92.23	—	Unverified
8	Slot-Gated BLSTM with Attension	F1	88.8	—	Unverified
9	DecomposedMetaSL	F1 (1-shot) avg	74.89	—	Unverified
10	Capsule-NLU	F1	0.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TDT 0-6	F1	0.81	—	Unverified
2	Partially Fine-tuned HuBERT	F1	0.75	—	Unverified
3	Multi-SLURP	F1	0.64	—	Unverified
4	Finstreder (Conformer)	F1	0.4	—	Unverified
5	Finstreder (Quartznet)	F1	0.31	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	XLM-R Base	Slot F1 Score	83.6	—	Unverified
2	mT5 Base (encoder-only)	Slot F1 Score	82.2	—	Unverified
3	mT5 Base (text-to-text)	Slot F1 Score	81.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	JointBERT-CAE	Slot F1	95.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CM-Net	F1	86.16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MIDAS	F1 score	98.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MIDAS	F1 score	99.28	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Fashion GAE	FITB	96.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	General SLU Model w/ Profile	F1	0.83	—	Unverified