https://github.com/pangolulu/DCMTL
공식 코드Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant
Multilingual Relation Extraction using Compositional Universal Schema
CTRAN: CNN-Transformer-based Network for Natural Language Understanding
Template-based Question Answering using Recursive Neural Networks
SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling
Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling
TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
Extracting a Knowledge Base of COVID-19 Events from Social Media
MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention
From Disfluency Detection to Intent Detection and Slot Filling
An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling
A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models
In-game Toxic Language Detection: Shared Task and Attention Residuals
$R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.