English

Bib2vec: An Embedding-based Search System for Bibliographic Information

Computation and Language 2018-04-06 v3 Artificial Intelligence Information Retrieval

Abstract

We propose a novel embedding model that represents relationships among several elements in bibliographic information with high representation ability and flexibility. Based on this model, we present a novel search system that shows the relationships among the elements in the ACL Anthology Reference Corpus. The evaluation results show that our model can achieve a high prediction ability and produce reasonable search results.

Keywords

Cite

@article{arxiv.1706.05122,
  title  = {Bib2vec: An Embedding-based Search System for Bibliographic Information},
  author = {Takuma Yoneda and Koki Mori and Makoto Miwa and Yutaka Sasaki},
  journal= {arXiv preprint arXiv:1706.05122},
  year   = {2018}
}

Comments

EACL2017 extended version. The demonstration is available at http://tti-coin.jp/demo/bib2vec/

R2 v1 2026-06-22T20:20:30.561Z