Slot Filling

75 papers with code • 7 benchmarks • 13 datasets

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

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
ATIS	Bi-model SLU	A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling	See all
KILT: T-REx	DensePhrases	Learning Dense Representations of Phrases at Scale	See all
KILT: Zero Shot RE	Multitask DPR + BART		See all
Polyvore	Fashion GAE	Context-Aware Visual Compatibility Prediction	See all
MixATIS	GL-GIN	GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling	See all
MixSNIPS	GL-GIN	GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling	See all
SLURP	Partially Fine-tuned HuBERT	A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding	See all

Datasets

Subtasks

Greatest papers with code

Without code Latest Greatest

Learning End-to-End Goal-Oriented Dialog

facebookresearch/ParlAI • • 24 May 2016

We show similar result patterns on data extracted from an online concierge service.

Goal-Oriented Dialog Slot Filling

8,453

Paper
Code

Data Programming: Creating Large Training Sets, Quickly

HazyResearch/snorkel • • NeurIPS 2016

Additionally, in initial user studies we observed that data programming may be an easier way for non-experts to create machine learning models when training data is limited or unavailable.

Slot Filling

4,926

Paper
Code

Learning Dense Representations of Phrases at Scale

princeton-nlp/SimCSE • • ACL 2021

Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019).

Ranked #1 on Question Answering on Natural Questions (long)

Fine-tuning Open-Domain Question Answering +4

1,456

Paper
Code

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising

salesforce/WikiSQL • 17 May 2021

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture.

Denoising Slot Filling +1

1,069

Paper
Code

KILT: a Benchmark for Knowledge Intensive Language Tasks

facebookresearch/KILT • NAACL 2021

We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance.

Ranked #3 on Entity Linking on KILT: WNED-CWEB

Entity Linking Fact Checking +4

625

Paper
Code

Neural Baby Talk

jiasenlu/NeuralBabyTalk • • CVPR 2018

We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image.

Image Captioning Slot Filling