Automatic Arabic Text Summarization using Analogical Proportions

TitleAutomatic Arabic Text Summarization using Analogical Proportions
Publication TypeJournal Article
Year of Publication2020
AuthorsElayeb, B, Chouigui, A, Bounhas, M, Ben Khiroun, O
JournalCognitive Computation, Springer
KeywordsAnalogical proportions, Analogical relevance., Arabic text summarization, Extractive summarization

Background / introduction: Automatic text summarization is the process of generating
or extracting a brief representation of an input text. There are several algorithms for extractive summarization in the literature tested by using English and other languages datasets, however only few extractive Arabic summarizers exist due to the lack of large collection in Arabic language.
Methods: This paper proposes and assesses new extractive single document summarization approaches based on analogical proportions which are statements of the form “a is to b as c is to d”. The goal is to study the capability of analogical proportions to represent the relationship between documents and their corresponding summaries. For this purpose, we suggest two algorithms to quantify the relevance/irrelevance of an extracted keyword from the input text, to build its summary. In the first algorithm, the analogical proportion representing this relationship is limited to check the existence/non-existence of the keyword in any document or summary in Binary way without considering keyword frequency in the text, whereas the analogical proportion of the second algorithm considers this frequency.
Results: We have assessed and compared these two algorithms to some language independent summarizers (LexRank, TextRank, Luhn and LSA (Latent Semantic Analysis))
using our large corpus ANT (Arabic News Texts) and a small test collection EASC (Essex
Arabic Summaries Corpus) by computing ROUGE (Recall-Oriented Understudy for Gisting
Evaluation) and BLEU (BiLingual Evaluation Understudy) metrics. The best-achieved
results are ROUGE-1 = 0.96 and BLEU-1 = 0.65 corresponding to Educational documents
from EASC collection which outperform the best LexRank algorithm. The proposed algorithms are also compared to three other Arabic extractive summarizers, using EASC collection, and show better results in terms ROUGE-1 = 0.75 and BLEU-1 = 0.47 for the first
algorithm, and ROUGE-1 = 0.74 and BLEU-1 = 0.49 for the second one.
Conclusions: Experimental results show the interest of analogical proportions for text
summarization. In particular, analogical summarizers significantly outperform three among four language-independent summarizers in case of BLEU-1 for ANT collection and they are not significantly outperformed by any other summarizer in case of EASC collection.