SOTAVerified

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 151–200 of 458 papers

TitleStatusHype
Joint Intent Detection And Slot Filling Based on Continual Learning Model—0
Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems—0
A Career Interview Dialogue System using Large Language Model-based Dynamic Slot Generation—0
Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding—0
Exploiting Topic Information for Joint Intent Detection and Slot Filling—0
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding—0
Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling—0
A Graph-to-Sequence Model for Joint Intent Detection and Slot Filling in Task-Oriented Dialogue Systems—0
Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond—0
Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch—0
ezDI: A Supervised NLP System for Clinical Narrative Analysis—0
Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling—0
Federated Learning for Spoken Language Understanding—0
Few-shot Intent Classification and Slot Filling with Retrieved Examples—0
Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF—0
Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking—0
Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding—0
Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling—0
FLIN: A Flexible Natural Language Interface for Web Navigation—0
CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training—0
CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling—0
Generalized Multiple Intent Conditioned Slot Filling—0
Generation of complex database queries and API calls from natural language utterances—0
Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability—0
Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture—0
A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding—0
Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque—0
Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling—0
Event Linking with Sentential Features from Convolutional Neural Networks—0
HCLD: A Hierarchical Framework for Zero-shot Cross-lingual Dialogue System—0
Combining Distant and Partial Supervision for Relation Extraction—0
HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals—0
Combining Supervised and Unsupervised Enembles for Knowledge Base Population—0
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation—0
How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?—0
Combining Word Feature Vector Method with the Convolutional Neural Network for Slot Filling in Spoken Language Understanding—0
Hybrid Dialog State Tracker with ASR Features—0
I^2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding—0
IBC-C: A Dataset for Armed Conflict Analysis—0
Comparing Automatic Evaluation Measures for Image Description—0
Event Extraction Using Distant Supervision—0
Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding—0
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding—0
Impact of ASR N-Best Information on Bayesian Dialogue Act Recognition—0
Impact of Coreference Resolution on Slot Filling—0
Improved NL2SQL based on Multi-layer Expert Network—0
Confidence Estimation for Knowledge Base Population—0
Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis—0
Answer Extraction by Recursive Parse Tree Descent—0
Evaluation of Online Dialogue Policy Learning Techniques—0
Show:102550
← PrevPage 4 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1single ngramKILT-AC73.2—Unverified
2KGI_1KILT-AC72.31—Unverified
3MetaRAGKILT-AC71.1—Unverified
4KGI_0 (reupload)KILT-AC68.32—Unverified
5WikipediaKILT-AC67.2—Unverified
6Multitask DPR + BARTKILT-AC50.64—Unverified
710kKILT-AC41.34—Unverified
8DensePhrasesKILT-AC41.34—Unverified
9RAGKILT-AC36.83—Unverified
10Coop. Distil BertKILT-AC34.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Re2GKILT-AC75.84—Unverified
2KGI_1KILT-AC69.14—Unverified
3WikipediaKILT-AC64.64—Unverified
4MetaRAGKILT-AC61.88—Unverified
5single ngramKILT-AC60.08—Unverified
6KGI_0 (reupload)KILT-AC55.54—Unverified
7Coop. DistilBertKILT-AC36.68—Unverified
8DensePhrasesKILT-AC27.84—Unverified
910kKILT-AC27.84—Unverified
10RAGKILT-AC23.12—Unverified
#ModelMetricClaimedVerifiedStatus
1BiSLUMicro F197.2—Unverified
2SLIM (PACL)Micro F196.8—Unverified
3SLIMMicro F196.5—Unverified
4Uni-MISMicro F196.4—Unverified
5TFMNMicro F196.4—Unverified
6TFMN (PACL)Micro F196.3—Unverified
7RoBERTa (PACL)Micro F196.2—Unverified
8DGIFMicro F195.9—Unverified
9SSRANMicro F195.8—Unverified
10MISCAMicro F195.2—Unverified
#ModelMetricClaimedVerifiedStatus
1MISCAMicro F190.5—Unverified
2Co-guiding NetMicro F189.8—Unverified
3SSRANMicro F189.4—Unverified
4BiSLUMicro F189.4—Unverified
5UGENMicro F189.2—Unverified
6Topic InformationMicro F188.7—Unverified
7SLIMMicro F188.5—Unverified
8Global Intent-Slot Co-occurenceMicro F188.5—Unverified
9DGIFMicro F188.5—Unverified
10Uni-MISMicro F188.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CTRANF10.98—Unverified
2Bi-model with a decoderF10.97—Unverified
3Joint BERTF10.96—Unverified
4Stack-Propagation (+BERT)F10.96—Unverified
5JointBERT-CAEF10.96—Unverified
6AGIFF10.96—Unverified
7Joint BERT + CRFF10.96—Unverified
8Attention Encoder-Decoder NNF10.96—Unverified
9Context EncoderF10.96—Unverified
10SF-IDF10.96—Unverified
#ModelMetricClaimedVerifiedStatus
1CTRANF198.3—Unverified
2Stack-Propagation (+BERT)F197—Unverified
3JointBERT-CAEF197—Unverified
4AGIFF194.8—Unverified
5Stack-PropagationF194.2—Unverified
6Context EncoderF193.6—Unverified
7SF-IDF192.23—Unverified
8Slot-Gated BLSTM with AttensionF188.8—Unverified
9DecomposedMetaSLF1 (1-shot) avg74.89—Unverified
10Capsule-NLUF10.92—Unverified
#ModelMetricClaimedVerifiedStatus
1TDT 0-6F10.81—Unverified
2Partially Fine-tuned HuBERTF10.75—Unverified
3Multi-SLURPF10.64—Unverified
4Finstreder (Conformer)F10.4—Unverified
5Finstreder (Quartznet)F10.31—Unverified
#ModelMetricClaimedVerifiedStatus
1XLM-R BaseSlot F1 Score83.6—Unverified
2mT5 Base (encoder-only)Slot F1 Score82.2—Unverified
3mT5 Base (text-to-text)Slot F1 Score81.3—Unverified
#ModelMetricClaimedVerifiedStatus
1JointBERT-CAESlot F195.5—Unverified
#ModelMetricClaimedVerifiedStatus
1CM-NetF186.16—Unverified
#ModelMetricClaimedVerifiedStatus
1MIDASF1 score98.56—Unverified
#ModelMetricClaimedVerifiedStatus
1MIDASF1 score99.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Fashion GAEFITB96.9—Unverified
#ModelMetricClaimedVerifiedStatus
1General SLU Model w/ ProfileF10.83—Unverified