Document Similarity for Texts of Varying Lengths via Hidden Topics
Computation and Language
2019-03-27 v1
Abstract
Measuring similarity between texts is an important task for several applications. Available approaches to measure document similarity are inadequate for document pairs that have non-comparable lengths, such as a long document and its summary. This is because of the lexical, contextual and the abstraction gaps between a long document of rich details and its concise summary of abstract information. In this paper, we present a document matching approach to bridge this gap, by comparing the texts in a common space of hidden topics. We evaluate the matching algorithm on two matching tasks and find that it consistently and widely outperforms strong baselines. We also highlight the benefits of incorporating domain knowledge to text matching.
Keywords
Cite
@article{arxiv.1903.10675,
title = {Document Similarity for Texts of Varying Lengths via Hidden Topics},
author = {Hongyu Gong and Tarek Sakakini and Suma Bhat and Jinjun Xiong},
journal= {arXiv preprint arXiv:1903.10675},
year = {2019}
}