paper-with-me

Papers

Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment

2019-06-03 · ACL 2019 7 · Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu

In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning. Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents. The generated dialogues are comprehensively evaluated on aspects like informativeness and coherence, which are aligned with our objective and human instinct. These assessments are integrated as a compound reward to guide the evolution of dialogue strategy via policy gradient. Comprehensive experiments have been carried out on the publicly available dataset, demonstrating that the proposed method outperforms the other state-of-the-art approaches significantly.

📄 PDF Abstract BibTeX arXiv:1906.00549

Code (1)

PaddlePaddle/models 공식 구현 paddle

Tasks

InformativenessReinforcement Learning

Similar Papers 제목 키워드 기반

Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation

2020-12-22 · Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang 외

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large num…

DiagnosticDialogue GenerationMeta-Learning

Assume-Guarantee Reinforcement Learning

2023-12-15 · Milad Kazemi, Mateo Perez, Fabio Somenzi, Sadegh Soudjani 외

We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environments may be prohibitively large to lear…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

A System for Automated Open-Source Threat Intelligence Gathering and Management

2021-01-19 · Peng Gao, Xiaoyuan Liu, Edward Choi, Bhavna Soman 외

To remain aware of the fast-evolving cyber threat landscape, open-source Cyber Threat Intelligence (OSCTI) has received growing attention from the community. Commonly, knowledge about threats is presented in a vast numbe…

Management

Temporal Pattern Mining from Evolving Networks

2017-09-20 · Angelo Impedovo, Corrado Loglisci, Michelangelo Ceci

Recently, evolving networks are becoming a suitable form to model many real-world complex systems, due to their peculiarities to represent the systems and their constituting entities, the interactions between the entitie…

Dynamic Multi-Objectives Optimization with a Changing Number of Objectives

2016-08-23 · Renzhi Chen, Ke Li, Xin Yao

Existing studies on dynamic multi-objective optimization focus on problems with time-dependent objective functions, while the ones with a changing number of objectives have rarely been considered in the literature. Inste…