Single Document Summarization Based on Local Topic Identification and Word Frequency

2008 Seventh Mexican International Conference on Artificial Intelligence ◽

10.1109/micai.2008.12 ◽

2008 ◽

Cited By ~ 9

Author(s):

Zhi Teng ◽

Ye Liu ◽

Fuji Ren ◽

Seiji Tsuchiya ◽

Fuji Ren

Keyword(s):

Word Frequency ◽

Document Summarization ◽

Topic Identification

Download Full-text

Text Summarization

10.1093/oxfordhb/9780199276349.013.0032 ◽

2012 ◽

Cited By ~ 11

Author(s):

Eduard Hovy

Keyword(s):

Research And Development ◽

Evaluation Studies ◽

Text Summarization ◽

Single Measurement ◽

Document Summarization ◽

Topic Identification ◽

Evaluation Strategies ◽

And Performance

This article describes research and development on the automated creation of summaries of one or more texts. It defines the concept of summary and presents an overview of the principal approaches in summarization. It describes the design, implementation, and performance of various summarization systems. The stages of automated text summarization are topic identification, interpretation, and summary generation, each having its sub stages. Due to the challenges involved, multi-document summarization is much less developed than single-document summarization. This article reviews particular techniques used in several summarization systems. Finally, this article assesses the methods of evaluating summaries. This article reviews evaluation strategies, from previous evaluation studies, to the two-basic measures method. Summaries are so task and genre specific; therefore, no single measurement covers all cases of evaluation

Download Full-text

Experience Matters

Zeitschrift für Psychologie ◽

10.1027/2151-2604/a000423 ◽

2020 ◽

Vol 228 (4) ◽

pp. 254-263 ◽

Cited By ~ 1

Author(s):

Pedro S. Mendes ◽

Karlos Luna ◽

Pedro B. Albuquerque

Keyword(s):

Word Frequency ◽

High Frequency ◽

Recall Test ◽

Judgments Of Learning ◽

Direct Experience ◽

Frequency Effects ◽

Actual Frequency ◽

Actual Word ◽

High Frequency Words

Abstract. The present study tested if word frequency effects on judgments of learning (JOLs) are exclusively due to beliefs or if the direct experience with the items also plays a role. Across four experiments, participants read prompts about the frequency of the words (high/low), which could be congruent/incongruent with the words’ actual frequency. They made pre-study JOLs (except Experiment 1b), immediate JOLs, and completed a recall test. If experience drives the effect, JOLs should be based on actual word frequency rather than the prompts. Results showed higher pre-study JOLs for prompts of high frequency, but higher immediate JOLs for high-frequency words regardless of the prompt, suggesting an effect of direct experience with the words. In Experiments 2 and 3, we manipulated participants’ beliefs, finding a small effect of beliefs on JOLs. We conclude that, regarding word frequency, direct experience with the items seems more relevant than beliefs when making immediate JOLs.

Download Full-text