Combining Text Vector Representations for Information Retrieval

A Data-Driven Strategy to Combine Word Embeddings in Information Retrieval

10.5121/csit.2021.110107 ◽

2021 ◽

Author(s):

Alfredo Silva ◽

Marcelo Mendoza

Keyword(s):

Information Retrieval ◽

Natural Language Processing ◽

Language Processing ◽

Ad Hoc ◽

Data Driven ◽

Word Embeddings ◽

Continuous Vector ◽

Benchmark Data ◽

Promising Line ◽

Vector Representations

Word embeddings are vital descriptors of words in unigram representations of documents for many tasks in natural language processing and information retrieval. The representation of queries has been one of the most critical challenges in this area because it consists of a few terms and has little descriptive capacity. Strategies such as average word embeddings can enrich the queries' descriptive capacity since they favor the identification of related terms from the continuous vector representations that characterize these approaches. We propose a datadriven strategy to combine word embeddings. We use Idf combinations of embeddings to represent queries, showing that these representations outperform the average word embeddings recently proposed in the literature. Experimental results on benchmark data show that our proposal performs well, suggesting that data-driven combinations of word embeddings are a promising line of research in ad-hoc information retrieval.

Download Full-text

Demonstration of the Use of Tape-Recorded Information from a High Vacuum Electron Microscope

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100063007 ◽

1969 ◽

Vol 27 ◽

pp. 218-219

Author(s):

Richard E. Hartman ◽

Roberta S. Hartman ◽

Peter L. Ramos

Keyword(s):

Information Retrieval ◽

Electron Microscope ◽

Magnetic Tape ◽

High Vacuum ◽

Data Retrieval ◽

Electronic Information ◽

Electronic Data ◽

Subsequent Processing ◽

Continuous Record

We have long felt that some form of electronic information retrieval would be more desirable than conventional photographic methods in a high vacuum electron microscope for various reasons. The most obvious of these is the fact that with electronic data retrieval the major source of gas load is removed from the instrument. An equally important reason is that if any subsequent analysis of the data is to be made, a continuous record on magnetic tape gives a much larger quantity of data and gives it in a form far more satisfactory for subsequent processing.

Download Full-text

Stain contamination and embedding in electron microscopy

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100141986 ◽

1986 ◽

Vol 44 ◽

pp. 50-53

Author(s):

Hilton H. Mollenhauer

Keyword(s):

Electron Microscopy ◽

Information Retrieval ◽

Epoxy Resins ◽

Image Contrast ◽

Sample Preservation ◽

Factors Associated ◽

Amount Of Information ◽

Electron Microscopical ◽

Contrast Information

Many factors (e.g., resolution of microscope, type of tissue, and preparation of sample) affect electron microscopical images and alter the amount of information that can be retrieved from a specimen. Of interest in this report are those factors associated with the evaluation of epoxy embedded tissues. In this context, informational retrieval is dependant, in part, on the ability to “see” sample detail (e.g., contrast) and, in part, on tue quality of sample preservation. Two aspects of this problem will be discussed: 1) epoxy resins and their effect on image contrast, information retrieval, and sample preservation; and 2) the interaction between some stains commonly used for enhancing contrast and information retrieval.

Download Full-text

Information and Dose in the Scanning Transmission Ion Microscope

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s1431927600001021 ◽

1980 ◽

Vol 38 ◽

pp. 232-233

Author(s):

Fox T. R. ◽

R. Levi-Setti

Keyword(s):

Information Retrieval ◽

Electron Microscope ◽

Elastic Scattering ◽

Energy Loss ◽

Cross Sections ◽

Previous Analysis ◽

Single Scattering ◽

Screening Length ◽

Relative Damage ◽

Scanning Transmission

At an earlier meeting [1], we discussed information retrieval in the scanning transmission ion microscope (STIM) compared with the electron microscope at the same energy. We treated elastic scattering contrast, using total elastic cross sections; relative damage was estimated from energy loss data. This treatment is valid for “thin” specimens, where the incident particles suffer only single scattering. Since proton cross sections exceed electron cross sections, a given specimen (e.g., 1 μg/cm2 of carbon at 25 keV) may be thin for electrons but “thick” for protons. Therefore, we now extend our previous analysis to include multiple scattering. Our proton results are based on the calculations of Sigmund and Winterbon [2], for 25 keV protons on carbon, using a Thomas-Fermi screened potential with a screening length of 0.0226 nm. The electron results are from Crewe and Groves [3] at 30 keV.

Download Full-text