Zero-shot Slot Filling

5 papers with code • 2 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Datasets


Greatest papers with code

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

zliucr/coach ACL 2019

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains.

Zero-shot Slot Filling

Robust Retrieval Augmented Generation for Zero-shot Slot Filling

ibm/kgi-slot-filling 31 Aug 2021

Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI.

Domain Adaptation Few-Shot Learning +3

Zero-shot Slot Filling with DPR and RAG

ibm/kgi-slot-filling 17 Apr 2021

Recently, there has been a promising direction in evaluating language models in the same way we would evaluate knowledge bases, and the task of slot filling is the most suitable to this intent.

Knowledge Base Population Knowledge Graphs +1

GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling

shikib/generative_slot_filling 13 Jun 2021

We instead achieve strong alignment by simultaneously modifying both the pre-trained model and the formulation of the downstream task, which is more efficient and preserves the scalability of transfer learning.

Open-Domain Dialog Transfer Learning +1

Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling

w-lw/pclc 7 Oct 2021

Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research.

Contrastive Learning Transfer Learning +2