paper-with-me

Papers

Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

2020-02-04 · Jinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan Liang

Target-guided open-domain conversation aims to proactively and naturally guide a dialogue agent or human to achieve specific goals, topics or keywords during open-ended conversations. Existing methods mainly rely on single-turn datadriven learning and simple target-guided strategy without considering semantic or factual knowledge relations among candidate topics/keywords. This results in poor transition smoothness and low success rate. In this work, we adopt a structured approach that controls the intended content of system responses by introducing coarse-grained keywords, attains smooth conversation transition through turn-level supervised learning and knowledge relations between candidate keywords, and drives an conversation towards an specified target with discourse-level guiding strategy. Specially, we propose a novel dynamic knowledge routing network (DKRN) which considers semantic knowledge relations among candidate keywords for accurate next topic prediction of next discourse. With the help of more accurate keyword prediction, our keyword-augmented response retrieval module can achieve better retrieval performance and more meaningful conversations. Besides, we also propose a novel dual discourse-level target-guided strategy to guide conversations to reach their goals smoothly with higher success rate. Furthermore, to push the research boundary of target-guided open-domain conversation to match real-world scenarios better, we introduce a new large-scale Chinese target-guided open-domain conversation dataset (more than 900K conversations) crawled from Sina Weibo. Quantitative and human evaluations show our method can produce meaningful and effective target-guided conversations, significantly improving over other state-of-the-art methods by more than 20% in success rate and more than 0.6 in average smoothness score.

📄 PDF Abstract BibTeX arXiv:2002.01196

Code (1)

James-Yip/TGODC-DKRN 공식 구현 tf

Tasks

Retrieval

Similar Papers 제목 키워드 기반

SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks

2026-05-22 · Yukai Yang, Chenxi Qin, Jungang Li, Xin Zhang 외 arxiv

Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer with a Mixture-of-Experts (MoE) framework for dynamic computa…

Teacher-Guided Routing for Sparse Vision Mixture-of-Experts

2026-04-23 · Masahiro Kada, Ryota Yoshihashi, Satoshi Ikehata, Rei Kawakami 외 arxiv

Recent progress in deep learning has been driven by increasingly large-scale models, but the resulting computational cost has become a critical bottleneck. Sparse Mixture of Experts (MoE) offers an effective solution by …

Question Guided Modular Routing Networks for Visual Question Answering

2019-04-17 · Yanze Wu, Qiang Sun, Jianqi Ma, Bin Li 외

This paper studies the task of Visual Question Answering (VQA), which is topical in Multimedia community recently. Particularly, we explore two critical research problems existed in VQA: (1) efficiently fusing the visual…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing

2023-12-22 · Jinmin He, Kai Li, Yifan Zang, Haobo Fu 외

Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy. To enhance data efficiency by sharing parameters across multiple tasks, a common practice segments the network into…

AllDeep Reinforcement Learning

Budget-Aware Agentic Routing via Boundary-Guided Training

2026-02-04 · Caiqi Zhang, Menglin Xia, Xuchao Zhang, Daniel Madrigal 외 arxiv

As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for s…