EntEval: A Holistic Evaluation Benchmark for Entity Representations

@article{Chen2019EntEvalAH,
  title={EntEval: A Holistic Evaluation Benchmark for Entity Representations},
  author={Mingda Chen and Z. Chu and Y. Chen and K. Stratos and Kevin Gimpel},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.00137}
}
Rich entity representations are useful for a wide class of problems involving entities. [...] Key Method In addition, we develop training techniques for learning better entity representations by using natural hyperlink annotations in Wikipedia. We identify effective objectives for incorporating the contextual information in hyperlinks into state-of-the-art pretrained language models and show that they improve strong baselines on multiple EntEval tasks.Expand
Exploring Neural Entity Representations for Semantic Information
DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions
Evaluation Benchmarks and Learning Criteriafor Discourse-Aware Sentence Representations
Mining Knowledge for Natural Language Inference from Wikipedia Categories
Interpretable Entity Representations through Large-Scale Typing
Modeling Fine-Grained Entity Types with Box Embeddings

References

SHOWING 1-10 OF 76 REFERENCES
Design Challenges for Entity Linking
Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks
Jointly Embedding Entities and Text with Distant Supervision
Entity Linking via Joint Encoding of Types, Descriptions, and Context
Improving Entity Linking by Modeling Latent Relations between Mentions
Dynamic Entity Representations in Neural Language Models
Zero-Shot Entity Linking by Reading Entity Descriptions
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
...
1
2
3
4
5
...