Text Representation, Retrieval, and Understanding with Knowledge Graphs

Chenyan XiongSIGIR 2018 · OpenReview

Abstract

This dissertation aims to improve text representation, retrieval, and understanding with knowledge graphs. Previous information retrieval systems were mostly built upon bag-ofwords representations and frequency-based retrieval models. Effective as they are, wordbased representations and frequency signals only provide shallow text understanding and have various intrinsic challenges. Utilizing entities and their structured semantics from knowledge graphs, this dissertation goes beyond bag-of-words and improves search with richer text representations, customized semantic structures, sophisticated ranking models and neural networks.
BibTeX
@inproceedings{xiong2018text,
  author = {Chenyan Xiong},
  title = {{Text Representation, Retrieval, and Understanding with Knowledge Graphs}},
  booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year = {2018},
  url = {https://openreview.net/forum?id=8TDT-9mAAHP},
}

Loading related content...

Figure