paper-with-me

Papers

Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent

2019-07-08 · Zelin Dai, Weitang Liu, Guanhua Zhan

Multiple sequence to sequence models were used to establish an end-to-end multi-turns proactive dialogue generation agent, with the aid of data augmentation techniques and variant encoder-decoder structure designs. A rank-based ensemble approach was developed for boosting performance. Results indicate that our single model, in average, makes an obvious improvement in the terms of F1-score and BLEU over the baseline by 18.67% on the DuConv dataset. In particular, the ensemble methods further significantly outperform the baseline by 35.85%.

📄 PDF Abstract BibTeX arXiv:1907.03590

Code (4)

2023-MindSpore-1/ms-code-219/tree/main/duconv mindspore
circlePi/knowledge-driven-dialogue-lic2019 pytorch
cui0523/Code6/tree/main/duconv mindspore
lonePatient/knowledge-driven-dialogue-lic2019-rank5 pytorch

Tasks

Data AugmentationDecoderDialogue Generation

Similar Papers 제목 키워드 기반

KillChainGraph: ML Framework for Predicting and Mapping ATT&CK Techniques

2025-08-19 · Chitraksh Singh, Monisha Dhanraj, Ken Huang arxiv

The escalating complexity and volume of cyberattacks demand proactive detection strategies that go beyond traditional rule-based systems. This paper presents a phase-aware, multi-model machine learning framework that emu…

Graph Neural Network

Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models

2023-12-18 · Reek Majumder, Jacquan Pollard, M Sabbir Salek, David Werth 외

The environmental impacts of global warming driven by methane (CH4) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH4. Several dat…

Ensemble Learning

Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic

2026-08-14 · Jie Fang, Wei Zheng, Mengyun Xu, Eui-Jin Kim arxiv

In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into reinforcement learning (RL) models fail to capture latent interactive…

Reinforcement LearningAutonomous Vehicles

ProAI: Proactive Multi-Agent Conversational AI with Structured Knowledge Base for Psychiatric Diagnosis

2025-02-28 · Yuqi Wu, Guangya Wan, Jingjing Li, Shengming Zhao 외

Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. Most LLM-driven conversational AI systems operate reactively, responding to user prompts without g…

DiagnosticResponse Generation

Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling

2025-07-12 · Xinyue Liu, Xiao Peng, Shuyue Yan, Yuntian Chen 외 arxiv

Observed records of climate extremes provide an incomplete view of risk, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates hazards striking multiple locations simult…