A Hierarchical Book Representation of Word Embeddings for Effective Semantic Clustering and Search
Avi Bleiweiss
2017
Abstract
Semantic word embeddings have shown to cluster in space based on linguistic similarities that are quantifiably captured using simple vector arithmetic. Recently, methods for learning distributed word vectors have progressively empowered neural language models to compute compositional vector representations for phrases of variable length. However, they remain limited in expressing more generic relatedness between instances of a larger and non-uniform sized body-of-text. In this work, we propose a formulation that combines a word vector set of variable cardinality to represent a verse or a sentence, with an iterative distance metric to evaluate similarity in pairs of non-conforming verse matrices. In contrast to baselines characterized by a bag of features, our model preserves word order and is more sustainable in performing semantic matching at any of a verse, chapter and book levels. Using our framework to train word vectors, we analyzed the clustering of bible books exploring multidimensional scaling for visualization, and experimented with book searches of both contiguous and out-of-order parts of verses. We report robust results that support our intuition for measuring book-to-book and verse-to-book similarity.
DownloadPaper Citation
in Harvard Style
Bleiweiss A. (2017). A Hierarchical Book Representation of Word Embeddings for Effective Semantic Clustering and Search . In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-220-2, pages 154-163. DOI: 10.5220/0006192701540163
in Bibtex Style
@conference{icaart17,
author={Avi Bleiweiss},
title={A Hierarchical Book Representation of Word Embeddings for Effective Semantic Clustering and Search},
booktitle={Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2017},
pages={154-163},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006192701540163},
isbn={978-989-758-220-2},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - A Hierarchical Book Representation of Word Embeddings for Effective Semantic Clustering and Search
SN - 978-989-758-220-2
AU - Bleiweiss A.
PY - 2017
SP - 154
EP - 163
DO - 10.5220/0006192701540163