Papers with Code 아카이브
Dialogue
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 21
- 평가표
- 1
- 보존된 평가 기록
- 1
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access
EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization
Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations
Selective Prompting Tuning for Personalized Conversations with LLMs
Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting
Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding
Unsupervised Extraction of Dialogue Policies from Conversations
Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
A Contrastive Learning Approach to Mitigate Bias in Speech Models
DialSim: A Real-Time Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents
Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model
A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding
Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting
A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
On the Evaluation of Speech Foundation Models for Spoken Language Understanding
An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistants
Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation
Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech
DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests
PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Item-Language Model for Conversational Recommendation
Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue
Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning
Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation
MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.