Bib2vec: An Embedding-based Search System for Bibliographic Information

TL;DR

This paper introduces Bib2vec, an embedding model that captures relationships in bibliographic data, enabling a flexible and effective search system demonstrated on the ACL Anthology corpus.

Contribution

The paper presents a novel embedding model for bibliographic information and a search system that effectively visualizes relationships among elements.

Findings

High prediction accuracy of the embedding model

Effective retrieval of related bibliographic elements

Reasonable search results demonstrated on ACL corpus

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.