ACL Findings2023
Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph
Yue Tan, Bo Wang, Anqi Liu, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
Abstract
In target-oriented dialogue, the representation and achievement of targets are two interrelated essential issues. In current approaches, the target is typically assumed to be a single object represented as a word, which makes it relatively easy to achieve through dialogue with the help of a knowledge graph (KG). However, when the target has complex semantics, the existing KG is often incomplete in tracking semantic relations. This paper studies target-oriented dialog where the target is a topic sentence. We combine the methods of knowledge retrieval and relationship prediction to construct a contextrelated dynamic KG, in which we can track the implicit semantic paths in the speaker's mind that may not exist in the existing KGs. In addition, we also designed a novel metric to evaluate the tracked path automatically. The experimental results show that our method can control the agent more logically and smoothly toward the complex target.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on8
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Language Generation with Multi-Hop Reasoning on Commonsense Knowledge GraphHaozhe Ji, Pei Ke, Shaohan Huang, Furu Wei et al.EMNLP 2020 · 96 citations
- Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional NetworksPavan Kapanipathi, Veronika Thost, Siva Sankalp Patel, Spencer Whitehead et al.AAAI 2020 · 48 citations
- Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response GenerationPei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim et al.ACL 2022 · 45 citations
- Dynamic Knowledge Routing Network for Target-Guided Open-Domain ConversationJinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan LiangAAAI 2020 · 36 citations
Related papers
- AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded DialogueJaehun Jung, Bokyung Son, Sungwon LyuEMNLP 2020 · 33 citations
- MTGP: Multi-turn Target-oriented Dialogue Guided by Generative Global Path with Flexible TurnsAnqi Liu, Bo Wang, Yue Tan, Dongming Zhao et al.ACL Findings 2023 · 4 citations
- Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog GenerationJinyoung Park, Minseok Joo, Joo-Kyung Kim, Hyunwoo J. KimEMNLP 2024 · 3 citations
- HiTKG: Towards Goal-Oriented Conversations via Multi-Hierarchy LearningJinjie Ni, Vlad Pandelea, Tom Young, Haicang Zhou et al.AAAI 2022 · 35 citations
- Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past ExperienceZhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang et al.ACL Findings 2026
