当前位置： SCI文献检索 > JOURNAL OF BIOMEDICAL INFORMATICS期刊下所有文献 > Unsupervised low-dimensional vector representations for words, phrases and text that are transparent, scalable, and produce similarity metrics that are not redundant with neural embeddings.

Unsupervised low-dimensional vector representations for words, phrases and text that are transparent, scalable, and produce similarity metrics that are not redundant with neural embeddings.

Abstract：

:Neural embeddings are a popular set of methods for representing words, phrases or text as a low dimensional vector (typically 50-500 dimensions). However, it is difficult to interpret these dimensions in a meaningful manner, and creating neural embeddings requires extensive training and tuning of multiple parameters and hyperparameters. We present here a simple unsupervised method for representing words, phrases or text as a low dimensional vector, in which the meaning and relative importance of dimensions is transparent to inspection. We have created a near-comprehensive vector representation of words, and selected bigrams, trigrams and abbreviations, using the set of titles and abstracts in PubMed as a corpus. This vector is used to create several novel implicit word-word and text-text similarity metrics. The implicit word-word similarity metrics correlate well with human judgement of word pair similarity and relatedness, and outperform or equal all other reported methods on a variety of biomedical benchmarks, including several implementations of neural embeddings trained on PubMed corpora. Our implicit word-word metrics capture different aspects of word-word relatedness than word2vec-based metrics and are only partially correlated (rho = 0.5-0.8 depending on task and corpus). The vector representations of words, bigrams, trigrams, abbreviations, and PubMed title + abstracts are all publicly available from http://arrowsmith.psych.uic.edu/arrowsmith_uic/word_similarity_metrics.html for release under CC-BY-NC license. Several public web query interfaces are also available at the same site, including one which allows the user to specify a given word and view its most closely related terms according to direct co-occurrence as well as different implicit similarity metrics.

journal_name

J Biomed Inform

journal_title

Journal of biomedical informatics

authors

Smalheiser NR,Cohen AM,Bonifield G

doi

10.1016/j.jbi.2019.103096

subject

Has Abstract

pub_date

2019-02-01 00:00:00

pages

103096

eissn

1532-0464

issn

1532-0480

pii

S1532-0464(19)30006-1

journal_volume

pub_type

杂志文章

在线工具

Unsupervised low-dimensional vector representations for words, phrases and text that are transparent, scalable, and produce similarity metrics that are not redundant with neural embeddings.