• Publications
  • Influence
Knowledge Graph Embedding via Dynamic Mapping Matrix
TLDR
In this paper, we propose a more fine-grained model named TransD, which is an improvement of TransR/CTransR. Expand
  • 592
  • 104
  • PDF
Learning to Represent Knowledge Graphs with Gaussian Embedding
TLDR
This paper switches to density-based embedding and propose KG2E for explicitly modeling the certainty of entities and relations, which learn the representations of KGs in the space of multi-dimensional Gaussian distributions. Expand
  • 190
  • 27
  • PDF
Knowledge Graph Completion with Adaptive Sparse Transfer Matrix
TLDR
We model knowledge graphs for their completion by encoding each entity and relation into a numerical space. Expand
  • 205
  • 22
  • PDF
Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions
TLDR
We propose a sentence-level attention model to select the valid instances, which makes full use of the supervision information from knowledge bases. Expand
  • 200
  • 21
  • PDF
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism
TLDR
We propose an end to end model based on sequence-to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of Normal, EntityPairOverlap and SingleEntiyOverlap. Expand
  • 72
  • 18
  • PDF
Leveraging FrameNet to Improve Automatic Event Detection
TLDR
We investigate whether there exists a good mapping from frames to event-types and if it is possible to improve event detection by using FN. Expand
  • 65
  • 11
  • PDF
Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning
TLDR
We propose an end-to-end question answering system called COREQA, which incorporates copying and retrieving mechanisms to generate natural answers within an encoder-decoder framework. Expand
  • 69
  • 9
  • PDF
CASIA@V2: A MLN-based Question Answering System over Linked Data
TLDR
We present a question answering system (CASIA@V2) over Linked Data (DBpedia), which translates natural language questions into structured queries automatically. Expand
  • 33
  • 8
  • PDF
How to Generate a Good Word Embedding
TLDR
The authors analyze three critical components in training word embeddings: model, corpus, and training parameters. Expand
  • 221
  • 7
  • PDF
An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge
TLDR
We present an end-to-end neural network model to represent the questions and their corresponding scores dynamically according to the various candidate answer aspects via cross-attention mechanism. Expand
  • 142
  • 7
  • PDF