https://github.com/IBM/modified-bAbI-dialog-tasks
공식 코드Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use
Learning End-to-End Goal-Oriented Dialog with Multiple Answers
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding
Are You for Real? Detecting Identity Fraud via Dialogue Interactions
Incremental Learning from Scratch for Task-Oriented Dialogue Systems
Recurrent Neural Networks with Pre-trained Language Model Embedding for Slot Filling Task
Bilateral Personalized Dialogue Generation with Contrastive Learning
AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
Exploring Human-Like Thinking in Search Simulations with Large Language Models
SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning
Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
Learning Spoken Language Representations with Neural Lattice Language Modeling
Learning Spoken Language Representations with Neural Lattice Language Modeling
Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding
Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.