K
Kunfeng Lai
Publications - 6
Citations - 23
Kunfeng Lai is an academic researcher. The author has contributed to research in topics: Question answering & Entity linking. The author has an hindex of 1, co-authored 6 publications receiving 5 citations.
Papers
More filters
Book ChapterDOI
KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph.
TL;DR: Zhang et al. as mentioned in this paper proposed a novel entity synonyms discovery framework, named KGSynNet, which pre-trains subword embeddings for mentions and entities using a large-scale domain-specific corpus while learning the knowledge embedding of entities via a joint TransC-TransE model.
Proceedings ArticleDOI
Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network
TL;DR: A framework of Monte Carlo Tree Search with Double-q Dueling network (MCTS-DDU) for task-completion dialogue policy learning that performs decision-time planning based on dialogue state search trees built by Monte Carlo simulations and is robust to the simulation errors.
Proceedings ArticleDOI
Make Templates Smarter: A Template Based Data2Text System Powered by Text Stitch Model
TL;DR: This work proposes a novel template-based data2text system powered by a text stitch model that outperforms SOTA NN-based systems in fidelity and surpasses template- based systems in diversity and human involvement.
Patent
Intelligent question and answer method and device based on knowledge graph and computer equipment
TL;DR: In this article, an intelligent question-answering method and device based on a knowledge graph, and computer equipment, is presented. But the method comprises the steps: receiving a question text online, extracting a first entity in the question text, searching a first node corresponding to the first entity, utilizing a preset intentionrecognition rule engine to recognize a first intention of the question texts, the intention recognition rule engine being an engine established according to a Trie tree, and searching the first answer corresponding to question text in the knowledge graph by taking the first node as a starting point according to
Posted Content
KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph
TL;DR: This paper proposed a novel entity synonyms discovery framework, named KGSynNet, which pre-trains subword embeddings for mentions and entities using a large-scale domain-specific corpus while learning the knowledge embedding of entities via a joint TransC-TransE model.